CN117831744B - Remote monitoring method and system for critically ill patients - Google Patents
Remote monitoring method and system for critically ill patients Download PDFInfo
- Publication number
- CN117831744B CN117831744B CN202410252017.XA CN202410252017A CN117831744B CN 117831744 B CN117831744 B CN 117831744B CN 202410252017 A CN202410252017 A CN 202410252017A CN 117831744 B CN117831744 B CN 117831744B
- Authority
- CN
- China
- Prior art keywords
- change
- gray level
- image frame
- pixel point
- distribution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000012544 monitoring process Methods 0.000 title claims abstract description 52
- 208000028399 Critical Illness Diseases 0.000 title description 3
- 230000008859 change Effects 0.000 claims abstract description 335
- 230000033001 locomotion Effects 0.000 claims abstract description 45
- 208000023504 respiratory system disease Diseases 0.000 claims abstract description 21
- 230000005540 biological transmission Effects 0.000 claims abstract description 20
- 230000000241 respiratory effect Effects 0.000 claims abstract description 11
- 230000002776 aggregation Effects 0.000 claims description 44
- 238000004220 aggregation Methods 0.000 claims description 44
- 238000010606 normalization Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 18
- 238000013507 mapping Methods 0.000 claims description 9
- 230000000739 chaotic effect Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 206010038687 Respiratory distress Diseases 0.000 claims 1
- 238000004590 computer program Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 12
- 238000004458 analytical method Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 4
- 230000006835 compression Effects 0.000 description 3
- 238000007906 compression Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 230000029058 respiratory gaseous exchange Effects 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000036391 respiratory frequency Effects 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
- G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/169—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N19/17—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object
- H04N19/172—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding the unit being an image region, e.g. an object the region being a picture, frame or field
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Signal Processing (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of video image coding, in particular to a method and a system for remotely monitoring a patient suffering from severe respiratory disease. According to the method, a changed pixel point is obtained according to the change condition of the pixel point between a current image frame and a historical image frame; obtaining a first preferred parameter from the local distribution of the changed pixel points and the integral gray scale deviation; obtaining a second preferred parameter from the varying movement of the varying pixel point between adjacent historical image frames and the varying degree in all the historical image frames; combining the first preferred parameter and the second preferred parameter under the gray level and the gray level distribution frequency to obtain the priority parameter of the gray level; the encoded transmission is implemented based on the priority parameter of the gray level and the gray level distribution probability. According to the invention, through analyzing the pixel point characteristics of the changes in the current image frame and the historical image frame, higher coding weight is given to the gray level of the possibly changed region of the patient, the coding transmission reliability is improved, and the respiratory serious patient is effectively monitored.
Description
Technical Field
The invention relates to the technical field of video image coding, in particular to a method and a system for remotely monitoring a patient suffering from severe respiratory disease.
Background
In the ward of a patient suffering from severe respiratory disease, the patient is usually monitored in full-day health, the monitoring system is usually integrated with various sensors and image acquisition to carry out omnibearing real-time detection on the patient, sensor detection data mainly comprise respiratory frequency, heart rate, blood oxygen saturation, blood pressure and the like, image acquisition mainly acquires real-time monitoring images, the data and the real-time monitoring images are transmitted to a data management system through an instrument, and medical staff can carry out remote monitoring on the condition of the patient in real time through the management system.
Because of the large content of image data, the image is compressed and encoded in the image transmission process, and for images with high accuracy requirements such as medical monitoring, a lossless compression encoding method is needed for compression, so huffman encoding is often used for compression and encryption. However, if the transmission network has abnormal conditions such as fluctuation, the packet loss occurs in the process of monitoring data transmission, the situation of loss of the monitoring picture will be caused, and because the important part of the monitored image, which is changed by the patient, is not analyzed and coded in priority during Huffman coding, the loss rate of the code of the important part of the image, which needs to be observed, is higher, so that the loss of the important part of the transmitted monitored image is serious, and effective monitoring management on the critical patient cannot be performed.
Disclosure of Invention
In order to solve the technical problems that in the prior art, the loss rate of codes of important parts to be observed in images is high, so that the important parts in the transmitted monitoring images are seriously lost, and effective monitoring management cannot be carried out on severe patients, the invention aims to provide a remote monitoring method and a remote monitoring system for the severe patients, and the adopted technical scheme is as follows:
The invention provides a remote monitoring method for a patient suffering from severe respiratory diseases, which comprises the following steps:
Acquiring a historical image frame in a preset time period before a current image frame according to a respiratory critical patient monitoring video; determining a changed pixel point in the current image frame according to the change condition of the pixel point between the current image frame and each historical image frame;
Obtaining a local estimation range of each change pixel point according to the position distribution condition of the change pixel point in the current image frame and the distribution difference condition between each change pixel point and other change pixel points; obtaining a first preferred parameter of each change pixel point according to the position distribution density of other change pixel points and the overall deviation condition of gray distribution in the local estimation range of each change pixel point;
Obtaining a movement index of each change pixel point according to the change difference condition of the corresponding change pixel point and other change pixel points between adjacent historical image frames in the local estimation range of each change pixel point; obtaining a second preferred parameter of each change pixel point according to the change quantity and the movement index of each change pixel point in all historical image frames;
Obtaining priority parameters of each gray level according to the first preferred parameters and the second preferred parameters of the gray level corresponding to all the changed pixel points and the gray level distribution probability; and obtaining the image code of the current image frame for transmission monitoring according to the priority parameter of each gray level in the current image frame and the gray level distribution probability.
Further, the method for obtaining the changed pixel point comprises the following steps:
Obtaining a change point between the current image frame and each historical image frame by adopting a frame difference method; and taking all corresponding change points in the current image frame as change pixel points.
Further, the method for acquiring the local estimation range includes:
Calculating the coordinate variance of all the change pixel points in the current image frame, performing negative correlation mapping and normalization processing to obtain a change distribution chaotic value of the current image frame;
For any one of the change pixel points, calculating the distance between the change pixel point and each other change pixel point to obtain the distribution difference of the change pixel points; arranging all distribution differences of the change pixel points in order from small to large to obtain a distribution difference sequence of the change pixel points;
Carrying out negative correlation mapping and normalization processing on the serial number of each distribution difference in the distribution difference sequence of the change pixel point to obtain an adjustment coefficient of each distribution difference; multiplying each distribution difference in the distribution difference sequence by a corresponding adjusting coefficient to obtain a distance sequence of the changed pixel point;
Calculating the difference of every two adjacent element values in the distance sequence to be used as a distance difference value; taking the distribution difference corresponding to the smallest element value as the distance distribution index of the change pixel point in the two element values corresponding to the largest distance difference value;
Calculating the average value of the distance distribution indexes of all the change pixel points in the current image frame, and obtaining the distance threshold value of each change pixel point; taking the product of the distance threshold value of each change pixel point and the change distribution chaotic value as a local range value of each change pixel point; and taking each change pixel point as a center, taking the local range value as a radius, and obtaining a circular range corresponding to each change pixel point as a local estimation range of each change pixel point.
Further, the method for acquiring the first preferred parameter includes:
For any one of the change pixel points, taking other change pixel points in the local estimation range of the change pixel point as local points of the change pixel point; counting the number of the changed pixel points in the local estimation range of each local point, and taking the number as the local number of each local point; taking the corresponding local point with the maximum local quantity as the gathering point of the changed pixel point;
obtaining a high gray level average value of the current image frame according to the distribution condition of pixel points corresponding to gray levels in the current image frame;
calculating the difference between the gray value of each change pixel point and the high gray level mean value in the local estimation range of each aggregation point to obtain the gray difference of each change pixel point; calculating the average value of the gray differences of all the changed pixel points in the local estimation range of each aggregation point, and carrying out normalization processing to obtain a local gray distribution index of each aggregation point;
normalizing the product of the local gray level distribution index and the local quantity of each aggregation point to obtain a preferred value of each aggregation point; the average value of the preferred values of all the aggregation points is taken as the first preferred parameter of the changed pixel point.
Further, the method for obtaining the movement index comprises the following steps:
Performing frame difference method calculation on each historical image frame and the previous historical image frame in time sequence, and obtaining a difference point in each historical image frame;
Sequentially taking each change pixel point as a reference point; when the position of the difference point in the historical image frame is the same as the reference point, taking the corresponding historical image frame as the reference frame of the reference point; calculating the average value of the distances between the difference points of each reference frame in the local estimation range of the reference point and the reference point, and obtaining the movement change value of the reference point under each reference frame; and calculating the average value of the movement change values of the reference points under all corresponding reference frames, performing negative correlation mapping and normalization processing, and obtaining the movement index of the reference points.
Further, the method for obtaining the second preferred parameter includes:
for any one change pixel point, counting the same times of the positions of the change points between the current image frame and each historical image frame as the change pixel point to obtain the change quantity of the change pixel point;
And carrying out normalization processing on the product of the change quantity of the change pixel points and the movement index to obtain a second preferred parameter of the change pixel points.
Further, the method for acquiring the priority parameter includes:
taking the sum value of the first preferred parameter and the second preferred parameter of each changed pixel point as the total preferred parameter of each changed pixel point; taking the average value of the total preferred parameters of all the changed pixel points corresponding to each gray level as a preferred index of each gray level; taking the occurrence probability of each gray level in the current image frame as the gray level distribution probability of each gray level;
the product of the preference index and the gray level distribution probability of each gray level is used as the priority parameter of each gray level.
Further, the obtaining the image code of the current image frame for transmission monitoring according to the priority parameter and the gray level distribution of each gray level in the current image frame includes:
Combining the priority parameter of each gray level and the gray level distribution probability to obtain a Huffman tree of the gray level in the current image frame; the left subtree of the Huffman tree is constructed according to the priority parameters for the gray level corresponding to each non-zero priority parameter, and the right subtree of the Huffman tree is constructed according to the gray level distribution probability for the gray level with zero priority parameter;
performing Huffman coding on the current image frame according to the Huffman tree of the gray level in the current image frame to obtain the image coding of the current image frame and the gray level coding of each gray level; the image code and all gray scale codes are transmitted.
Further, the method for obtaining the high gray level average value comprises the following steps:
Arranging all pixel points in the current image frame according to the sequence from big to small of gray level to obtain a gray level distribution sequence; and calculating the average value of the gray levels of the preset number of pixel points in the gray distribution sequence, and obtaining the high gray level average value of the current image frame.
The invention provides a remote monitoring system for a patient suffering from severe respiratory diseases, which comprises a memory and a processor, wherein the processor executes a computing program stored in the memory so as to realize the remote monitoring method for the patient suffering from severe respiratory diseases.
The invention has the following beneficial effects:
1. The invention considers the importance degree of the patient change area to the current image frame in the continuous monitoring, obtains the change pixel point according to the change condition of the pixel point between the current image frame and the historical image frame, and analyzes the priority degree of gray level coding from the pixel point characteristic in the change area. The first preferred parameter for each changed pixel is derived from the local distribution density of the changed pixel and the overall deviation of the gray scale, giving higher priority to pixels more likely to be patient change areas in terms of location and gray scale characteristics. And obtaining a second preferred parameter of each change pixel point from the change movement condition of the change pixel point between adjacent historical image frames and the change degree of each change pixel point in all the historical image frames, and giving higher priority to the change pixel points of the change area of the patient more likely from the change movement condition of the change pixel point position. Combining the distribution characteristics and the change characteristics of each change pixel point under each gray level, namely a first preferred parameter and a second preferred parameter, and adding the gray level distribution frequency to obtain the priority parameter of each gray level, namely giving higher coding importance to the gray level of the pixel point of the change region of the patient, and finally realizing coding transmission based on the priority parameter of the gray level and the gray level distribution probability. According to the invention, by analyzing the characteristics of the pixel points in the current image frame and the change in the historical image frame, the gray level of the pixel point in the change area possibly occurring for the patient is given a higher coding level, the loss rate of the coding of the important part is reduced, the transmission reliability is improved, the important part in the transmitted monitoring image is reserved, and the important patient can be effectively monitored and managed.
2. In the process of acquiring the first preferred parameters, as a plurality of change areas exist in the image and the importance degree of the change part corresponding to the patient is higher, the local estimation range of each change pixel point is obtained according to the distribution position of each change pixel point in the current image frame and the distribution difference of the change pixel points with other change pixel points, and the optimal local range analyzed for each change pixel point is reflected through the local estimation range in consideration of the different distribution conditions of the change pixel points. Further, in the local estimation range of each of the changed pixel points, considering the difference between the light generation change area and the patient change area, according to the position distribution among the changed pixel points and the overall deviation condition of the gray distribution, obtaining a first preferred parameter, analyzing from the aggregation degree of the distribution and the overall deviation degree of the gray distribution, and obtaining the first preferred parameter on the position gray distribution characteristics of the change area.
3. In the process of acquiring the second preferred parameters, the difference of the change degree and the change persistence of the change region of the patient and other change regions is considered, so that the movement index is obtained according to the change condition of the change pixel points between adjacent historical image frames and other change pixel points in a local estimation range, the change movement characteristic is reflected from the local overall change condition when the change pixel point position is changed, the change quantity of the change pixel points in all the historical image frames is further combined, namely the change continuity of the change pixel points is combined, the second preferred parameters of each change pixel point are obtained, the analysis is carried out from the change degree, and the second preferred parameters are obtained on the change movement characteristic of the change region.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for remotely monitoring a patient suffering from a severe respiratory disease according to an embodiment of the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to the specific implementation, structure, characteristics and effects of a method and a system for remotely monitoring a patient suffering from severe respiratory disease according to the invention, which are provided by the invention, with reference to the accompanying drawings and the preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of a method and a system for remotely monitoring a patient suffering from severe respiratory disease provided by the invention with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for remotely monitoring a patient suffering from severe respiratory diseases according to an embodiment of the present invention is shown, the method includes the following steps:
S1: acquiring a historical image frame in a preset time period before a current image frame according to a respiratory critical patient monitoring video; and determining the changed pixel point in the current image frame according to the change condition of the pixel point between the current image frame and each historical image frame.
For a respiratory critical patient monitoring video, the condition of the respiratory state of a patient and the like can be observed remotely, so that images in the monitoring video need to be transmitted to a medical care monitoring system remotely in real time. Each image frame is an image frame after image preprocessing so as to be convenient for analyzing image features, and it should be noted that the image preprocessing process may specifically include image graying processing and filtering denoising processing, the image preprocessing process is a technical means well known to those skilled in the art, and specifically may select a gray weighting method to perform graying, a bilateral filtering method to perform filtering denoising, and the like, which will not be described herein.
Because the conventional Huffman coding is used for sorting coding based on the gray level distribution condition, only the pixel points with more gray level numbers can be better coded and protected, but in the monitored image of the patient with severe respiratory disease, the image area representing the actual condition of the patient is more important, so when the current image frame is coded, the higher the pixel point preference degree with high importance degree is, the shorter the coding length is, so as to reduce the loss probability of the pixel points with high importance degree when the network fluctuation data packet loss occurs.
Because the pixel points with high importance degree are the pixel points with changes in the image, the pixel points are usually reflected in the body movement, illumination change or other change parts of medical equipment of the patient with severe respiratory disease, and the parts are also usually important points of monitoring. Therefore, the pixel points generating the change are first filtered out, and the change pixel points in the current image frame are determined according to the change condition of the pixel points between the current image frame and each historical image frame.
Preferably, a frame difference method is adopted for the current image frame and each historical image frame, so as to obtain a change point between the current image frame and each historical image frame. The frame difference method can screen out the moving pixel points according to the gray level difference condition of the pixel points between two image frames, and the frame difference method is a technical means known to those skilled in the art and will not be described herein. Because the current image frame and each historical image frame can screen out the change points with motion characteristics, all the corresponding change points in the current image frame are used as change pixel points, and all the changed pixel points in the current image frame in a preset time period are analyzed uniformly.
In the past period, the pixel points which change the current image frame are screened out, the change areas represented by the change pixel points are more important, and the corresponding gray level is required to be encoded by increasing the corresponding priority degree, so that the transmission safety is improved while the transmission efficiency is ensured. But the importance of the different regions of variation is different, and for regions where the patient is changing, a higher priority needs to be given to reduce the loss of their transmission.
S2: obtaining a local estimation range of each change pixel point according to the position distribution condition of the change pixel point in the current image frame and the distribution difference condition between each change pixel point and other change pixel points; and in the local estimation range of each change pixel point, obtaining a first preferred parameter of each change pixel point according to the position distribution density of other change pixel points and the overall deviation condition of gray distribution.
The change areas are usually of the change pixel point gathering and distribution strokes, and as the change areas are more, the corresponding features of different change areas are different, so that each change pixel point needs to be analyzed according to the integral features of the local range so as to ensure accurate screening of the features of different change areas. Therefore, firstly, according to the overall distribution condition of the change pixel points in the current image frame, the optimal local analysis of each change pixel point is obtained, namely, according to the position distribution condition of the change pixel points in the current image frame and the distribution difference condition between each change pixel point and other change pixel points, the local estimation range of each change pixel point is obtained.
Preferably, the coordinate variance of all the changed pixel points in the current image frame is calculated, and the change distribution chaotic value of the current image frame is obtained through negative correlation mapping and normalization processing; firstly, calculating the discrete condition of the distribution positions of all the change pixels, and when the coordinate of the change pixels is distributed in the current image frame more chaotic, namely the coordinate variance is larger, indicating that a plurality of change areas exist in the current image frame, and analyzing the local part of each change pixel, analyzing the change pixel in a smaller range. In the embodiment of the invention, the average value can be calculated for the abscissa and the ordinate of each change pixel point respectively, the average coordinate point of all change pixel points is obtained, the distance between each change pixel point and the average coordinate point is calculated, and the variance of the distance is used as the coordinate variance. It should be noted that, the coordinate acquisition of the pixel points, the calculation of the distance between the pixel points, and the variance calculation are all technical means well known to those skilled in the art, such as establishing a coordinate system to obtain the coordinate of each pixel point and calculating the distance between the pixel points through euclidean distance, which are not described herein.
Further, for any one of the changed pixel points, calculating the distance between the changed pixel point and each other changed pixel point to obtain the distribution difference of the changed pixel point, and arranging all the distribution differences of the changed pixel points in order from small to large to obtain the distribution difference sequence of the changed pixel point. The distribution position distance degree between the change pixel point and each other change pixel point is reflected by the distribution difference sequence.
The aggregation distribution condition of the pixel points of the change points can be approximately seen through the size of the distribution differences in the distribution difference sequence, and the aggregation part or the aggregation range is the change region part where the change pixel points are located. Although the point range of the changed pixel points close to each other can be selected according to the distribution difference sequence, namely, the difference degree between the distribution differences is calculated, when the difference degree is large, the aggregation degree is suddenly changed under the distribution condition, and the local range of the changed pixel points can be stopped, the local judgment of the changed pixel points can be influenced by the difference degree between the far distribution differences, and therefore the weight adjustment is carried out on the distribution differences through the sequence numbers. For example, when the distribution difference sequence of a change pixel is {1,1,2,2,3,10,11,11,12,21,22,22}, it can be approximately seen that under the current change pixel distribution difference, the aggregation situation of the change pixel can be approximately classified into three categories, {1, 2,3} {10,11,11,12} and {21,22,22}, wherein 3 to 10 of the abrupt change can reflect that the optimal range of the change pixel should be 3, but because the larger difference influence between 12 and 21 will cause the judgment of the local range to be influenced, the addition of the distribution weight of the serial number makes the selection of the local range more reliable.
Therefore, further, the sequence number of each distribution difference in the distribution difference sequence of the changed pixel point is subjected to negative correlation mapping and normalization processing to obtain the adjustment coefficient of each distribution difference, and when the sequence number is smaller, the distribution difference analysis can reflect local distance change. And multiplying each distribution difference in the distribution difference sequence by a corresponding adjusting coefficient to obtain a distance sequence of the changed pixel point, and reflecting the local distribution distance change condition between the changed pixel point and other changed pixel points through the distance sequence.
Further, the difference between every two adjacent element values in the distance sequence is calculated and used as a distance difference value, wherein the distance difference value is the difference between the aggregation range of the changed pixel point and other nearest aggregation parts. And taking the distribution difference corresponding to the smallest element value as the distance distribution index of the changed pixel point in the two element values corresponding to the largest distance difference value. When the distribution distance mutation occurs, the minimum element value is the adjusted distance value corresponding to the distribution difference value and the adjustment coefficient, and each element value is obtained by calculating the distribution difference value and the adjustment coefficient, so that each element value corresponds to one distribution difference, and the distribution difference representing the distance is used as the distance distribution index of the change pixel.
Finally, calculating the average value of the distance distribution indexes of all the change pixel points in the current image frame, obtaining the distance threshold value of each change pixel point, and synthesizing the distance conditions of the aggregation range where the integral change pixel points correspond to, thus obtaining the integral distance threshold value. And taking the product of the distance threshold value of each change pixel point and the change distribution confusion value as a local range value of each change pixel point, and adjusting by combining the confusion degree of the position distribution to obtain the optimal range size of each change pixel point in the whole analysis. In the embodiment of the present invention, the expression of the local range value is:
In the method, in the process of the invention, Expressed as/>Local range values of each changed pixel point,/>Expressed as current image frame/>Coordinate variance of all the changed pixels in (a)/>Expressed as the total number of changed pixels in the current image frame,/>Expressed as/>Distance distribution index of each changed pixel point,/>Represented as an exponential function with a base of natural constant.
Wherein,Expressed as current image frame/>Variable distribution chaotic value,/>Represented as a distance threshold for each changing pixel point in the current image frame. The larger the variation distribution disorder value is, the more consistent the variation pixel point distribution is, namely the larger the local analysis range is, namely the larger the local range value is, and the larger the distance threshold value of each variation pixel point is, the larger the boundary distance between the whole variation pixel point and the aggregation range is, namely the larger the local range can be when each variation pixel point is analyzed, namely the larger the local range value is. Therefore, the circular range corresponding to each change pixel point is obtained as the local estimation range of each change pixel point by taking each change pixel point as a center and taking the local range value as a radius. In other embodiments of the present invention, a square range with a local range value of a size centered on a changed pixel point may be used as the local estimation range of each changed pixel point, which is not limited herein.
After the local estimation range is obtained, the density distribution and the gray value distribution of the local variation pixel points can be used for judging the variation area, and the local range of each variation pixel point when the local range is at the edge and the center of the aggregation part is different, so that the distribution range of the variation pixel points in the optimal range needs to be considered in calculation, and the analysis is performed through the range which can be more representative of the aggregation condition of the variation area where the variation distribution point is located. And therefore, in the local estimation range of each change pixel point, obtaining the first preferred parameter of each change pixel point according to the position distribution density of other change pixel points and the overall deviation condition of gray distribution.
Preferably, for any one of the variable pixel points, other variable pixel points within the local estimation range of the variable pixel point are taken as local points of the variable pixel point, the number of the variable pixel points within the local estimation range of each local point is counted, the local number of each local point is taken as the local number of each local point, the local density condition of each variable pixel point can be reflected within the local range of the variable pixel point through the local number. The local points corresponding to the maximum local quantity are used as the aggregation points of the change pixel points, and the aggregation points are the change pixel points which can represent the change area where the change pixel points are located most, so that the local characteristics of the change pixel points can be reflected according to the distribution characteristics of the aggregation points, and meanwhile, the aggregation points can correspond to one or more because the local quantity is possibly more than one.
Further, according to the distribution situation of the pixel points corresponding to the gray level in the current image frame, a high gray level average value of the current image frame is obtained, and since the body change caused by the breathing of the patient is outside, and the light change caused by a ward or a corridor and the like is likely to cause a larger change area in the image, in the embodiment of the invention, all the pixel points in the current image frame are arranged according to the sequence of gray levels from large to small to obtain a gray level distribution sequence, the average value of the gray levels of the preset number of pixel points in the gray level distribution sequence is calculated, the high gray level average value of the current image frame is obtained, and the gray level size caused by the light brightness in the current image frame can be reflected through the high gray level average value. The preset number is set to be 0.1% of the total number of pixels in the current image frame, and the specific numerical value implementation can be adjusted according to specific implementation conditions.
Further, in the local estimation range of each aggregation point, calculating the difference between the gray value of each change pixel point and the high gray level mean value to obtain the gray level difference of each change pixel point, and when the gray level difference is smaller, indicating that the gray value of the change pixel point is closer to the light part gray value. Calculating the average value of the gray level differences of all the changed pixel points in the local estimation range of each aggregation point, and carrying out normalization processing to obtain local gray level distribution indexes of each aggregation point, wherein the local gray level distribution indexes reflect the overall difference degree of the gray level value of the change region where the aggregation point is positioned and the gray level value of the light part, and when the local gray level distribution indexes are smaller, the pixel points in the corresponding local range of the aggregation point are more likely to be light change regions, and the importance degree is lower.
In general, the movement of the patient is the main reason for the variation of different image frames, for the serious respiratory illness, various auxiliary respiratory or monitoring medical instruments are connected, the part of the image variation caused by the respiratory process is related to the movement of the connecting part of the medical instrument besides the variation of the chest of the patient, therefore, in the preset time period, the part of the image variation is mainly the part of the patient respiration which causes the body variation and the movement of the connected medical instrument, therefore, the product of the local gray level distribution index and the local quantity of each aggregation point is normalized to obtain the preferred value of each aggregation point, and when the local quantity is larger, the larger the part of the variation main body in the corresponding variation area is indicated to be the important patient self variation distribution. Taking the average value of the preferred values of all the aggregation points as a first preferred parameter of the changed pixel point, analyzing the aggregation degree of the distribution and the overall deviation degree of the gray distribution, and obtaining the first preferred parameter on the position gray distribution characteristic of the changed region, wherein in the embodiment of the invention, the expression of the first preferred parameter is as follows:
In the method, in the process of the invention, Expressed as/>First preferred parameter of each variable pixel,/>Expressed as/>Total number of aggregation points of each changed pixel point,/>Expressed as/>Local number of aggregation points,/>Expressed as/>Within local estimation of the aggregation pointGray value of each variable pixel/>Expressed as current image frame/>High gray level mean value of/>Expressed as hyperbolic tangent function,/>Expressed as an absolute value extraction function,/>It should be noted that, normalization is a technical means well known to those skilled in the art, and the normalization function may be selected by linear normalization or standard normalization, and the specific normalization method is not limited herein.
Wherein,Expressed as/>Within local estimation of the aggregation pointGray level difference of each variable pixel point,/>Expressed as/>Local gray scale distribution index of each aggregation point,Expressed as/>Preferred values for the individual aggregation points. The larger the local gray scale distribution index is, the less likely the change area where the change pixel points are located is to be a light change area, and the larger the local number of the aggregation points is, the larger the main body part of the change area is, the more likely the change area is for a patient, so that the greater the importance degree of the change pixel points is, and the greater the first preferred parameter is.
S3: obtaining a movement index of each change pixel point according to the change difference condition of the corresponding change pixel point and other change pixel points between adjacent historical image frames in the local estimation range of each change pixel point; and obtaining a second preferred parameter of each changed pixel point according to the change quantity and the movement index of each changed pixel point in all the historical image frames.
Meanwhile, considering that a patient with severe respiratory disease needs to be guaranteed to rest in a care unit, the action with faster speed change cannot be performed, so that the change caused by the action such as respiration or turning over generated by the patient activity in an image is continuous and has smaller change movement degree, and the change of other areas is shorter and has higher change degree compared with the patient activity. Therefore, the change condition is further analyzed, namely, the change movement characteristic is firstly analyzed, namely, in the local estimation range of each change pixel point, the movement index of each change pixel point is obtained according to the change difference condition of the corresponding change pixel point and other change pixel points between adjacent historical image frames.
Preferably, after frame difference method calculation is performed on each historical image frame and the previous historical image frame in time sequence, a difference point in each historical image frame is obtained, and the change pixel point is divided into difference points generated in different time to perform time sequence change analysis. It should be noted that, for an image frame without a previous history image frame, that is, the first history image frame, the case in which the pixel point changes cannot be analyzed, and therefore, the difference point thereof is not calculated.
Further, each of the changed pixel points is sequentially used as a reference point, and the same analysis is performed on each of the changed pixel points. When the positions of the difference points in the historical image frames are the same as the reference points, the corresponding historical image frames are used as the reference frames of the reference points, and as the change pixel points are the pixel points generating the change, each change pixel point is always provided with the difference points with the same positions, and when the positions of the change pixel points are changed in the adjacent historical image frames, the corresponding historical image frames are used as the reference frames of the reference points for analysis.
Since the reference frames are image frames with changed reference points, the average value of the distances between the difference points of each reference frame in the local estimation range of the reference points and the reference points is calculated, the movement change value of the reference points under each reference frame is obtained, the distance between the reference points and each changed difference point at the moment can be reflected by calculating the distance between the reference points and the changed points, and the smaller the distance is, the closer the whole movement distance at the moment is to the changed region of the patient. In other embodiments of the present invention, an average distance of pixel point changes between a reference frame and a previous historical image frame within a local estimation range of the reference point may also be calculated by using an optical flow method, as a movement change value of the reference point under the reference frame, and an overall change form of a change area of the reference point may also be reflected by an overall change distance of an adjacent frame, where the optical flow method is a technical means well known to those skilled in the art, and will not be described herein.
Since the reference point may change in a plurality of historical image frames, an average value of movement change values of the reference point under all corresponding reference frames is calculated, and negative correlation mapping and normalization processing are performed to obtain a movement index of the reference point, and in the embodiment of the invention, the expression of the movement index is:
In the method, in the process of the invention, Expressed as/>Moving index of each changed pixel point,/>Expressed as/>Total number of reference frames for each changed pixel,/>Expressed as/>The reference frame is at the/>Total number of difference points within the local estimation range of the individual change pixel points,/>Expressed as/>The reference frame is at the/>First/>, within the local estimation range of the individual varying pixelsDifference points and/>Distance between each of the changed pixels,/>Represented as an exponential function with a base of natural constant.
Wherein,Expressed as/>The variable pixel point is at the/>The smaller the motion change value is, the closer the local change motion condition of the changed pixel point is to the patient change area, so that the motion index is larger.
Since the respiratory rate of a critically ill patient is high, the duration of the change is long for the patient to produce a changing area, i.e., continuously changing. And further combining the changing quantity of the changing pixel points in all the historical image frames, namely combining the continuity of the changing pixel points, and further obtaining a second preferred parameter, namely obtaining the second preferred parameter of each changing pixel point according to the changing quantity and the moving index of each changing pixel point in all the historical image frames.
Preferably, for any one of the change pixels, the number of changes of the change pixel is obtained by counting the number of times that the position of the change point between the current image frame and each of the history image frames is the same as that of the change pixel, and in step S1, the change point where the change occurs between the current image frame and each of the history image frames is obtained, and at the position of the change pixel, when the number of occurrences of the change point is greater, the change pixel is indicated as being changed all the time, and therefore, the number of changes of the change pixel is indicated by counting the number of times that the position of the change point obtained between each of the image frames is the same as that of the change pixel. For example, when the gray value is changed (10,11,12,13,15) from the historical image frame to the current image frame at the position corresponding to the changed pixel point, 15 is the gray value of the changed pixel point in the current image frame, and each historical image frame can correspond to a changed point at the changed pixel point, the change number is 4, and the change duration is longer. When the gray value of the position corresponding to the changed pixel point is changed to 10,11,11,11,11, the last 11 is the gray value of the changed pixel point in the current image frame, and at the moment, only one change point is correspondingly generated at the first historical image frame, the change quantity is 1, and the change duration is short.
And further carrying out normalization processing on the product of the change quantity of the change pixel points and the movement index to obtain a second preferred parameter of the change pixel points, analyzing from the change degree, and obtaining the second preferred parameter on the change movement characteristics of the change region. In the embodiment of the present invention, the expression of the second preferred parameter is:
In the method, in the process of the invention, Expressed as/>Second preferred parameter of each variable pixel,/>Expressed as/>Moving index of each changed pixel point,/>Expressed as/>Number of changes in each changed pixel,/>Represented as a normalization function. When the change continuity degree corresponding to the change pixel point is higher and the change movement degree is closer to the movement characteristic of the change region of the patient, the second preferred parameter of the change pixel point is larger, and the corresponding gray level needs to be higher in priority degree.
S4: obtaining priority parameters of each gray level according to the first preferred parameters and the second preferred parameters of the gray level corresponding to all the changed pixel points and the gray level distribution probability; and obtaining the image code of the current image frame for transmission monitoring according to the priority parameter of each gray level in the current image frame and the gray level distribution probability.
Combining the distribution characteristics of each changed pixel point under each gray level and the change characteristics, namely the first preferred parameter and the second preferred parameter, and adding the gray level distribution frequency to obtain the priority parameter of each gray level, namely giving higher coding importance to the gray level of the pixel point in the change area possibly occurring for the patient.
Preferably, the sum of the first preferred parameter and the second preferred parameter of each change pixel point is taken as the total preferred parameter of each change pixel point, the average value of the total preferred parameters of all change pixel points corresponding to each gray level is taken as the preferred index of each gray level, the first preferred parameter and the second preferred parameter are integrated to obtain the preferred degree of each change pixel point, namely the importance degree of the change pixel point, the overall importance degree of all change pixel points corresponding to each gray level is represented, and the obtained preferred degree of each gray level influenced by the importance degree of the pixel point is represented. When the gray level does not correspond to the pixel point, the calculated preference index is zero.
The probability of occurrence of each gray level in the current image frame is used as the gray level distribution probability of each gray level, the gray level distribution probability is the importance degree of reflecting each gray level based on the distribution quantity of the gray levels, and a certain importance proportion is required to be given to the gray levels with a large distribution quantity. Further, the product of the priority index of each gray level and the gray level distribution probability is taken as the priority parameter of each gray level, and in the embodiment of the present invention, the expression of the priority parameter is:
In the method, in the process of the invention, Expressed as/>Priority parameters of individual grey levels,/>Expressed as/>Total number of corresponding change pixel points under each gray level,/>Expressed as/>Fifth/> under gray levelFirst preferred parameter of each variable pixel,/>Expressed as/>Fifth/> under gray levelSecond preferred parameter of each variable pixel,/>Expressed as/>Gray level class distribution probability for each gray level.
Wherein,Expressed as/>Fifth/> under gray levelThe total preferred parameters of the individual varying pixels,Expressed as/>A preferred indicator of the gray level. When the priority index corresponding to the gray level is larger, the gray level distribution frequency is higher, which means that the importance degree of the gray level is larger, the number of corresponding distributed pixel points is larger, and the priority required by the gray level in coding is higher.
Therefore, according to the priority parameter and the gray level distribution probability of each gray level in the current image frame, the image code of the current image frame is obtained for transmission monitoring, preferably, the huffman tree of the gray level in the current image frame is obtained by combining the priority parameter and the gray level distribution probability of each gray level, wherein the left subtree of the huffman tree is constructed according to the priority parameter for the gray level corresponding to each non-zero priority parameter, and the right subtree of the huffman tree is constructed according to the gray level distribution probability for the gray level with zero priority parameter.
In the embodiment of the invention, for each gray level with a non-zero priority parameter, the gray levels are arranged in the order from large to small according to the priority parameter to obtain a priority sequence, a left subtree of the Huffman tree is constructed according to the priority sequence, the gray level with the large priority parameter is preferentially used as a leaf node of the left subtree, and then the construction of the left subtree of the Huffman tree is completed according to the order of the priority parameter. And for the gray level with zero priority parameter, sequencing the gray level distribution probability from large to small to obtain a gray level distribution sequence, constructing a right subtree of the Huffman tree according to the gray level distribution sequence, optimizing the gray level distribution probability as a leaf node of the right subtree, and then completing the construction of the right subtree of the Huffman tree according to the sequencing of the gray level distribution probability. And connecting the left subtree and the right subtree to obtain the Huffman tree of the gray level in the current image frame. It should be noted that, specific construction of the weights in the huffman tree is a technical means well known to those skilled in the art, and further description is omitted herein.
According to the method, the Huffman coding is carried out on the current image frame according to the Huffman tree of the gray level in the current image frame, so that the image coding of the current image frame and the gray level coding of each gray level are obtained.
Finally, the image codes and all gray level codes are transmitted, and the loss probability of important gray levels is reduced and the transmission reliability is improved by adjusting the coding weight of the gray levels in Huffman coding. After transmission, the image code can be decoded through gray level code, so that the current image frame in the monitoring video of the patient suffering from the severe respiratory disease is obtained, and the real-time condition of the patient is conveniently monitored.
In summary, the invention considers the importance degree of the patient change region to the current image frame in continuous monitoring, obtains the change pixel point according to the change condition of the pixel point between the current image frame and the historical image frame, and analyzes the priority degree of gray level coding from the pixel point characteristic in the change region. The first preferred parameter for each changed pixel is derived from the local distribution density of the changed pixel and the overall deviation of the gray scale, giving higher priority to pixels more likely to be patient change areas in terms of location and gray scale characteristics. And obtaining a second preferred parameter of each change pixel point from the change movement condition of the change pixel point between adjacent historical image frames and the change degree of each change pixel point in all the historical image frames, and giving higher priority to the change pixel points of the change area of the patient more likely from the change movement condition of the change pixel point position. Combining the distribution characteristics and the change characteristics of each change pixel point under each gray level, namely a first preferred parameter and a second preferred parameter, and adding the gray level distribution frequency to obtain the priority parameter of each gray level, namely giving higher coding importance to the gray level of the pixel point of the change region of the patient, and finally realizing coding transmission based on the priority parameter of the gray level and the gray level distribution probability. According to the invention, by analyzing the characteristics of the pixel points in the current image frame and the change in the historical image frame, the gray level of the pixel point in the change area possibly occurring for the patient is given a higher coding level, the loss rate of the coding of the important part is reduced, the transmission reliability is improved, the important part in the transmitted monitoring image is reserved, and the important patient can be effectively monitored and managed.
The invention provides a remote monitoring system for a patient suffering from severe respiratory diseases, which comprises a memory and a processor, wherein the processor executes a computing program stored in the memory so as to realize the remote monitoring method for the patient suffering from severe respiratory diseases.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (7)
1. A method of remotely monitoring a patient suffering from a respiratory distress, the method comprising:
Acquiring a historical image frame in a preset time period before a current image frame according to a respiratory critical patient monitoring video; determining a changed pixel point in the current image frame according to the change condition of the pixel point between the current image frame and each historical image frame;
Obtaining a local estimation range of each change pixel point according to the position distribution condition of the change pixel point in the current image frame and the distribution difference condition between each change pixel point and other change pixel points; obtaining a first preferred parameter of each change pixel point according to the position distribution density of other change pixel points and the overall deviation condition of gray distribution in the local estimation range of each change pixel point;
Obtaining a movement index of each change pixel point according to the change difference condition of the corresponding change pixel point and other change pixel points between adjacent historical image frames in the local estimation range of each change pixel point; obtaining a second preferred parameter of each change pixel point according to the change quantity and the movement index of each change pixel point in all historical image frames;
obtaining priority parameters of each gray level according to the first preferred parameters and the second preferred parameters of the gray level corresponding to all the changed pixel points and the gray level distribution probability; acquiring an image code of the current image frame for transmission monitoring according to the priority parameter of each gray level in the current image frame and the gray level distribution probability;
the method for acquiring the changed pixel points comprises the following steps:
Obtaining a change point between the current image frame and each historical image frame by adopting a frame difference method; taking all corresponding change points in the current image frame as change pixel points;
the method for acquiring the local estimation range comprises the following steps:
Calculating the coordinate variance of all the change pixel points in the current image frame, performing negative correlation mapping and normalization processing to obtain a change distribution chaotic value of the current image frame;
For any one of the change pixel points, calculating the distance between the change pixel point and each other change pixel point to obtain the distribution difference of the change pixel points; arranging all distribution differences of the change pixel points in order from small to large to obtain a distribution difference sequence of the change pixel points;
Carrying out negative correlation mapping and normalization processing on the serial number of each distribution difference in the distribution difference sequence of the change pixel point to obtain an adjustment coefficient of each distribution difference; multiplying each distribution difference in the distribution difference sequence by a corresponding adjusting coefficient to obtain a distance sequence of the changed pixel point;
Calculating the difference of every two adjacent element values in the distance sequence to be used as a distance difference value; taking the distribution difference corresponding to the smallest element value as the distance distribution index of the change pixel point in the two element values corresponding to the largest distance difference value;
Calculating the average value of the distance distribution indexes of all the change pixel points in the current image frame, and obtaining the distance threshold value of each change pixel point; taking the product of the distance threshold value of each change pixel point and the change distribution chaotic value as a local range value of each change pixel point; taking each change pixel point as a center, taking a local range value as a radius, and obtaining a circular range corresponding to each change pixel point as a local estimation range of each change pixel point;
The method for acquiring the second preferred parameters comprises the following steps:
for any one change pixel point, counting the same times of the positions of the change points between the current image frame and each historical image frame as the change pixel point to obtain the change quantity of the change pixel point;
And carrying out normalization processing on the product of the change quantity of the change pixel points and the movement index to obtain a second preferred parameter of the change pixel points.
2. The method for remotely monitoring a patient suffering from a severe respiratory disease according to claim 1, wherein the method for obtaining the first preferred parameter comprises:
For any one of the change pixel points, taking other change pixel points in the local estimation range of the change pixel point as local points of the change pixel point; counting the number of the changed pixel points in the local estimation range of each local point, and taking the number as the local number of each local point; taking the corresponding local point with the maximum local quantity as the gathering point of the changed pixel point;
obtaining a high gray level average value of the current image frame according to the distribution condition of pixel points corresponding to gray levels in the current image frame;
calculating the difference between the gray value of each change pixel point and the high gray level mean value in the local estimation range of each aggregation point to obtain the gray difference of each change pixel point; calculating the average value of the gray differences of all the changed pixel points in the local estimation range of each aggregation point, and carrying out normalization processing to obtain a local gray distribution index of each aggregation point;
normalizing the product of the local gray level distribution index and the local quantity of each aggregation point to obtain a preferred value of each aggregation point; the average value of the preferred values of all the aggregation points is taken as the first preferred parameter of the changed pixel point.
3. The method for remotely monitoring a patient suffering from severe respiratory diseases according to claim 1, wherein the method for acquiring the movement index comprises:
Performing frame difference method calculation on each historical image frame and the previous historical image frame in time sequence, and obtaining a difference point in each historical image frame;
Sequentially taking each change pixel point as a reference point; when the position of the difference point in the historical image frame is the same as the reference point, taking the corresponding historical image frame as the reference frame of the reference point; calculating the average value of the distances between the difference points of each reference frame in the local estimation range of the reference point and the reference point, and obtaining the movement change value of the reference point under each reference frame; and calculating the average value of the movement change values of the reference points under all corresponding reference frames, performing negative correlation mapping and normalization processing, and obtaining the movement index of the reference points.
4. The method for remotely monitoring a patient suffering from severe respiratory diseases according to claim 1, wherein the method for acquiring the priority parameter comprises:
taking the sum value of the first preferred parameter and the second preferred parameter of each changed pixel point as the total preferred parameter of each changed pixel point; taking the average value of the total preferred parameters of all the changed pixel points corresponding to each gray level as a preferred index of each gray level; taking the occurrence probability of each gray level in the current image frame as the gray level distribution probability of each gray level;
the product of the preference index and the gray level distribution probability of each gray level is used as the priority parameter of each gray level.
5. The method for remote monitoring of a patient suffering from a severe respiratory disease according to claim 4, wherein the obtaining the image code of the current image frame for transmission monitoring according to the priority parameter and the gray level distribution of each gray level in the current image frame comprises:
Combining the priority parameter of each gray level and the gray level distribution probability to obtain a Huffman tree of the gray level in the current image frame; the left subtree of the Huffman tree is constructed according to the priority parameters for the gray level corresponding to each non-zero priority parameter, and the right subtree of the Huffman tree is constructed according to the gray level distribution probability for the gray level with zero priority parameter;
performing Huffman coding on the current image frame according to the Huffman tree of the gray level in the current image frame to obtain the image coding of the current image frame and the gray level coding of each gray level; the image code and all gray scale codes are transmitted.
6. The method for remotely monitoring a patient suffering from severe respiratory diseases according to claim 2, wherein the method for obtaining the high gray scale mean value comprises:
Arranging all pixel points in the current image frame according to the sequence from big to small of gray level to obtain a gray level distribution sequence; and calculating the average value of the gray levels of the preset number of pixel points in the gray distribution sequence, and obtaining the high gray level average value of the current image frame.
7. A respiratory critical patient remote monitoring system comprising a memory and a processor, wherein the processor executes a computer program stored in the memory to implement a respiratory critical patient remote monitoring method as claimed in any of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410252017.XA CN117831744B (en) | 2024-03-06 | 2024-03-06 | Remote monitoring method and system for critically ill patients |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410252017.XA CN117831744B (en) | 2024-03-06 | 2024-03-06 | Remote monitoring method and system for critically ill patients |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117831744A CN117831744A (en) | 2024-04-05 |
| CN117831744B true CN117831744B (en) | 2024-05-10 |
Family
ID=90506268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410252017.XA Active CN117831744B (en) | 2024-03-06 | 2024-03-06 | Remote monitoring method and system for critically ill patients |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117831744B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015226326A (en) * | 2014-05-26 | 2015-12-14 | 富士通株式会社 | Video analysis method and video analysis device |
| CN113473131A (en) * | 2021-07-01 | 2021-10-01 | 成都国科微电子有限公司 | Video coding code rate dynamic adjustment method and device, electronic equipment and storage medium |
| CN115225897A (en) * | 2022-07-14 | 2022-10-21 | 河南职业技术学院 | Video multi-level encryption transmission method based on Huffman coding |
| CN115456868A (en) * | 2022-11-14 | 2022-12-09 | 南京金易众和信息科技有限公司 | Data management method for fire drill system |
| CN116055722A (en) * | 2023-03-06 | 2023-05-02 | 山东梁山酿酒总厂有限公司 | Data storage method for automatic white spirit production system |
| CN116309579A (en) * | 2023-05-19 | 2023-06-23 | 惠州市宝惠电子科技有限公司 | Transformer welding seam quality detection method using image processing |
| CN116828209A (en) * | 2023-08-30 | 2023-09-29 | 华洋通信科技股份有限公司 | Method and system for transmitting intelligent video monitoring data under mine |
| WO2024001588A1 (en) * | 2022-07-01 | 2024-01-04 | 上海商汤智能科技有限公司 | Breathing state detection method and apparatus, device, storage medium and computer program product |
| CN117409004A (en) * | 2023-12-14 | 2024-01-16 | 自贡市第一人民医院 | Lung rehabilitation intelligent auxiliary system based on medical image analysis |
| CN117499655A (en) * | 2023-11-13 | 2024-02-02 | 上海商汤智能科技有限公司 | Image encoding method, apparatus, device, storage medium, and program product |
| CN117593308A (en) * | 2024-01-19 | 2024-02-23 | 科普云医疗软件(深圳)有限公司 | Respiration monitoring and early warning method for critically ill respiratory patient |
-
2024
- 2024-03-06 CN CN202410252017.XA patent/CN117831744B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015226326A (en) * | 2014-05-26 | 2015-12-14 | 富士通株式会社 | Video analysis method and video analysis device |
| CN113473131A (en) * | 2021-07-01 | 2021-10-01 | 成都国科微电子有限公司 | Video coding code rate dynamic adjustment method and device, electronic equipment and storage medium |
| WO2024001588A1 (en) * | 2022-07-01 | 2024-01-04 | 上海商汤智能科技有限公司 | Breathing state detection method and apparatus, device, storage medium and computer program product |
| CN115225897A (en) * | 2022-07-14 | 2022-10-21 | 河南职业技术学院 | Video multi-level encryption transmission method based on Huffman coding |
| CN115456868A (en) * | 2022-11-14 | 2022-12-09 | 南京金易众和信息科技有限公司 | Data management method for fire drill system |
| CN116055722A (en) * | 2023-03-06 | 2023-05-02 | 山东梁山酿酒总厂有限公司 | Data storage method for automatic white spirit production system |
| CN116309579A (en) * | 2023-05-19 | 2023-06-23 | 惠州市宝惠电子科技有限公司 | Transformer welding seam quality detection method using image processing |
| CN116828209A (en) * | 2023-08-30 | 2023-09-29 | 华洋通信科技股份有限公司 | Method and system for transmitting intelligent video monitoring data under mine |
| CN117499655A (en) * | 2023-11-13 | 2024-02-02 | 上海商汤智能科技有限公司 | Image encoding method, apparatus, device, storage medium, and program product |
| CN117409004A (en) * | 2023-12-14 | 2024-01-16 | 自贡市第一人民医院 | Lung rehabilitation intelligent auxiliary system based on medical image analysis |
| CN117593308A (en) * | 2024-01-19 | 2024-02-23 | 科普云医疗软件(深圳)有限公司 | Respiration monitoring and early warning method for critically ill respiratory patient |
Non-Patent Citations (1)
| Title |
|---|
| Automatic Detection of Obstructive Sleep Apnea B ased on Multimo dal Imaging System a nd Binary Co de Alignment;Ruoshu Yang、Ludan Zhang等;Springer Nature Singapore Pte Ltd. 2022;20221231;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117831744A (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110051324B (en) | Method and system for predicting death rate of acute respiratory distress syndrome | |
| CN115670418A (en) | Data storage method based on smart watch user information | |
| KR20170016778A (en) | Method and program for computing bone age by deep neural network | |
| CN115333678B (en) | Unmanned ship water quality monitoring data transmission method and system | |
| EP3453321A1 (en) | Non-invasive method and system for estimating blood pressure from photoplethysmogram using statistical post-processing | |
| CN113270197A (en) | Health prediction method, system and storage medium based on artificial intelligence | |
| CN112017155B (en) | Method, device, system and storage medium for measuring health sign data | |
| CN111652138B (en) | Face recognition method, device and equipment for wearing mask and storage medium | |
| CN117593308B (en) | Respiration monitoring and early warning method for critically ill respiratory patient | |
| CN112509696A (en) | Health data detection method based on convolution autoencoder Gaussian mixture model | |
| WO2021120007A1 (en) | Infrared image sequence-based sleep quality evaluation system and method | |
| CN117909908B (en) | Intelligent monitoring method for running state of shared massage chair | |
| CN115868941B (en) | Information management method for intelligent ring | |
| US12100508B2 (en) | Method for predicting maximal oxygen uptake in wearable devices | |
| CN117523235A (en) | A patient wound intelligent identification system for surgical nursing | |
| CN117831744B (en) | Remote monitoring method and system for critically ill patients | |
| CN113576472B (en) | Blood oxygen signal segmentation method based on full convolution neural network | |
| CN110811638A (en) | SVM classifier construction method, system and method for monitoring sleep | |
| CN114820652A (en) | Method, device and medium for segmenting local quality abnormal region of mammary X-ray image | |
| CN116631563B (en) | Big data storage and intelligent matching method for pharmaceutical industry | |
| CN117838053A (en) | Multi-mode multi-resolution sleep apnea automatic detection method and system | |
| CN117481628A (en) | Wearable multi-parameter noninvasive hemodynamic monitoring method and system | |
| CN111466877B (en) | LSTM network-based oxygen reduction state prediction method | |
| CN113487611A (en) | Dental film image processing method and system based on artificial intelligence | |
| WO2022222472A1 (en) | Respiratory rate measurement method and apparatus, and electronic device and readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |