CN107330424B - Interaction area and interaction time period identification method, storage device and mobile terminal - Google Patents
Interaction area and interaction time period identification method, storage device and mobile terminal Download PDFInfo
- Publication number
- CN107330424B CN107330424B CN201710655807.2A CN201710655807A CN107330424B CN 107330424 B CN107330424 B CN 107330424B CN 201710655807 A CN201710655807 A CN 201710655807A CN 107330424 B CN107330424 B CN 107330424B
- Authority
- CN
- China
- Prior art keywords
- interaction
- human body
- recording
- image
- area
- 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
- 230000003993 interaction Effects 0.000 title claims abstract description 121
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000001514 detection method Methods 0.000 claims abstract description 21
- 230000002452 interceptive effect Effects 0.000 claims abstract description 21
- 230000001960 triggered effect Effects 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 15
- 230000000694 effects Effects 0.000 claims description 25
- 238000006073 displacement reaction Methods 0.000 claims description 15
- 230000037081 physical activity Effects 0.000 claims description 10
- 238000013179 statistical model Methods 0.000 claims description 5
- 239000003086 colorant Substances 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000009193 crawling Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000035622 drinking Effects 0.000 description 1
- 239000003651 drinking water Substances 0.000 description 1
- 235000020188 drinking water Nutrition 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000012567 pattern recognition method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an interactive region and interactive time period identification method which is suitable for being executed in computing equipment and comprises the following steps: receiving an input video signal, and performing frame splitting processing on the input video signal to generate a single-frame image; carrying out human shape detection on the obtained single-frame image; carrying out full-image difference and recording difference data; judging whether the image pixel differential data of the previous N frames meet a human body interaction characteristic model or not, and recording a triggered interaction region and a time breakpoint and a stopped interaction region and a time breakpoint; and recording the human body interaction area and the time period. The invention also discloses a storage device and a mobile terminal.
Description
Technical Field
The invention belongs to the field of computer vision identification, and particularly relates to a method for identifying an interaction area and an interaction time period of a differential pixel, and further relates to a storage device and a mobile terminal capable of realizing the functions.
Background
With the development of scientific technology and the wide application of modern video technology, image processing and pattern recognition methods based on machine vision are increasingly applied to the fields of pattern recognition, motion analysis, video monitoring, artificial intelligence and the like.
The existing human-related algorithms, most of which are model-based detection algorithms, need to perform matching calculation on the whole image through a specific operator or model, so that the operation consumption is greatly increased, and the operation efficiency and the real-time performance are lost. At present, algorithms for generating prior regions for human activity regions cannot give consideration to real-time and precision requirements, and when regions are judged, two human activity states of human displacement type activities (such as walking, running, crawling and the like) and interactive type activities (activities displayed on images as dynamic and static state conversion, motion stop and interaction with objects in a certain space, such as standing up and sitting down, going out and entering doors, drinking water and the like) are not distinguished obviously, and identification for human interactive type activity regions is not performed. In addition, most of the existing algorithms only pay attention to the calibration in space, but do not record the time corresponding to the activity, and do not completely record the activity area of a human body and the activity time in the area.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides an interaction area and interaction time period identification method, a storage device and a mobile terminal, which can make up the defects of the prior art and improve the application effect of a mathematical model.
The invention provides a method for identifying an interaction region and an interaction time period of a differential pixel, which is suitable for being executed in computing equipment, and comprises the following steps:
receiving an input video signal, and performing frame splitting processing on the input video signal to generate a single-frame image;
carrying out human shape detection on the obtained single-frame image;
carrying out full-image difference and recording difference data;
judging whether the image pixel differential data of the previous N frames meet a human body interaction characteristic model or not, and recording a triggered interaction region and a time breakpoint and a stopped interaction region and a time breakpoint; and
and recording the human body interaction area and the time period.
Wherein the step of 'detecting the human shape of the obtained single frame image' comprises the following steps:
converting the obtained single-frame image from RGB into a gray level image, and performing smooth denoising and filtering processing on the converted gray level image; and
and (5) detecting the portrait by using a portrait HOG operator.
Wherein, the step of detecting the portrait by using the portrait HOG operator comprises the following steps:
performing Gamma correction;
converting the image into gray scale;
calculating the gradient and the direction of the image to obtain the gradient amplitude and the angle of the image;
8 multiplied by 8 grid direction gradient weight histogram statistics; and
the block descriptors are normalized to the feature vectors.
Wherein, the step of 'performing full-map differencing and recording difference data' comprises the following steps:
respectively carrying out two-frame difference, three-frame difference and five-frame difference on the whole image, and recording corresponding difference results; and
the pixel transformation in the region under the general motion condition of the human body is described by applying one-dimensional normal distribution through a human body motion statistical model, and differential data of non-human body activity are filtered.
Wherein, the step of judging whether the image pixel differential data of the previous N frames meet the human body interaction characteristic model and recording the triggered interaction region and time breakpoint and the terminated interaction region and time breakpoint comprises the following steps:
based on the obtained human body movement differential data, judging whether the differential data meets the human body movement type by using a human body movement model;
if the motion is not determined to be the displacement motion, matching the N frames of differential data with the human body interaction triggering model;
if the matching is successful, recording the currently triggered interaction area and the time breakpoint;
matching the N frames of differential data with a human body interaction termination model; and
and if the matching is successful, recording the currently terminated interactive area and the time breakpoint.
Wherein the step of recording the human interaction area and the time period comprises:
calculating the overlapping part of the interaction triggering area and the termination area, and recording the overlapping part as a human body activity area;
calculating the interval time between the interactive triggering and the termination, and corresponding to the recorded activity area; and
and performing multi-group video detection in the same space, recording all interactive trigger areas, performing intersection operation on the interactive trigger areas in all adjacent M pixel ranges, and acquiring an intersection part area, wherein the intersection part area is the area with the highest interaction frequency in the finally acquired space.
Further, the method also comprises the following steps: areas of different interaction frequencies are marked by different colors.
The present invention also provides a memory device having stored therein a plurality of instructions adapted to be loaded and executed by a processor, the instructions comprising:
receiving an input video signal, and performing frame splitting processing on the input video signal to generate a single-frame image;
carrying out human shape detection on the obtained single-frame image;
carrying out full-image difference and recording difference data;
judging whether the image pixel differential data of the previous N frames meet a human body interaction characteristic model or not, and recording a triggered interaction region and a time breakpoint and a stopped interaction region and a time breakpoint; and
and recording the human body interaction area and the time period.
The present invention also provides a mobile terminal, comprising:
a processor adapted to implement instructions; and
a storage device adapted to store a plurality of instructions, the instructions adapted to be loaded and executed by a processor, the instructions comprising:
receiving an input video signal, and performing frame splitting processing on the input video signal to generate a single-frame image;
carrying out human shape detection on the obtained single-frame image;
carrying out full-image difference and recording difference data;
judging whether the image pixel differential data of the previous N frames meet a human body interaction characteristic model or not, and recording a triggered interaction region and a time breakpoint and a stopped interaction region and a time breakpoint; and
and recording the human body interaction area and the time period.
The algorithm of the method for identifying the interaction region and the interaction time period of the differential pixels mainly counts the pixel change of human body activity on an image, and then judges two states of human body common position movement and space interaction by combining a human body activity model, so that the human body interaction region and the interaction time period are finally obtained.
Drawings
Fig. 1 is a flowchart of a method for identifying an interaction region and an interaction time period of a differential pixel according to a preferred embodiment of the present invention.
Fig. 2 is a detailed flowchart of step S2 in fig. 1.
Fig. 3 is a detailed flowchart of step S3 in fig. 1.
Fig. 4 is a detailed flowchart of step S4 in fig. 1.
Fig. 5 is a detailed flowchart of step S5 in fig. 1.
Detailed Description
In order to make the technical means, the creation characteristics, the achievement purposes and the effects of the invention easy to understand, the invention is further explained below by combining the specific drawings.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In the present invention, the human body displacement type activities include behavioral states such as walking, running, crawling and the like, which generate displacements for the human body; interactive activities include small displacement activities such as standing up, doing down, lying down, drinking, interacting with objects (tables, chairs, etc.), which can basically divide human behavior into two categories, facilitating further gesture recognition and behavior analysis.
Fig. 1 is a flowchart illustrating an interaction area and an interaction time period identification method of a differential pixel according to a preferred embodiment of the present invention. The preferred implementation of the method for identifying the interaction region and the interaction time period of the differential pixel comprises the following steps:
step S1: the input video signal is received and subjected to a frame dropping process to generate a single frame image.
The frame rate is the number of still pictures played in the video format per second, so that the video signal can be disassembled into a plurality of still pictures, i.e. frames. Many existing software can implement the function of frame splitting, and details are not described here.
Step S2: human shape detection is performed on the single frame image obtained in step S1.
Human shape detection (HSR) is a technique for finding and identifying and positioning Human-shaped objects in an imaging space by processing a graphic image by using certain characteristics of Human body imaging. Human form detection (HSR) is a fusion of computer vision, pattern recognition, image processing techniques and morphological techniques, and can be widely applied to the fields of intelligent monitoring, intelligent transportation, target tracking, and the like. The realization process of human shape detection can be divided into the processes of target detection, boundary extraction, human shape target matching, human shape target identification and the like.
Specifically, referring to fig. 2, the human shape detection can be performed by:
step S21: the single frame image obtained in step S1 is converted from RGB into a grayscale image, and the converted grayscale image is subjected to smooth denoising filtering processing.
Step S22: and (5) detecting the portrait by using a portrait HOG operator.
The HOG (Histogram of Oriented Gradient) feature is a feature extraction algorithm in object recognition and pattern matching, and is an algorithm for extracting a feature Histogram based on a local pixel block. By HOG feature extraction and SVM (Support Vector Machine) training, a good effect can be obtained. The general flow of HOG feature extraction is as follows: the first step is Gamma correction, which is the inverse conversion output by inverse nonlinear conversion, mainly correcting the input image to compensate the gray scale deviation brought by the display, with a common coefficient of about 2.5. And secondly, converting the image into gray scale. And thirdly, calculating the gradient and the direction of the image to finally obtain the gradient amplitude and the angle of the image. And fourthly, carrying out statistics on the 8 multiplied by 8 grid directional gradient weight histogram. And fifthly, normalizing the gradient histogram in the block. Finally, the human shape detection function can be realized.
Step S3: and carrying out full-image difference and recording difference data.
Specifically, referring to fig. 3, the full graph difference can be performed as follows:
step S31: respectively carrying out two-frame difference, three-frame difference and five-frame difference on the whole image, recording corresponding difference results, and respectively recording as: diff1, diff2, and diff 3.
The two-frame difference means that two adjacent frames of images are subtracted to obtain an absolute value of the brightness difference of the two frames of images, whether the absolute value is greater than a threshold value is judged to analyze the motion characteristic of a video or an image sequence, and whether object motion exists in the image sequence is determined. The three-frame difference refers to selecting any adjacent three frames of images, respectively performing image difference operation on the first two frames of images and the second two frames of images, and then performing AND operation on the thresholded structure of the two frames of images, so as to extract a target image, which can be used for describing the intensity degree of image pixel change. Similarly, the five-frame difference means that adjacent five-frame images are selected, the K-th frame image is used as a current frame, frame difference operation is respectively carried out on the current frame and the previous two frames and the next two frames to obtain four difference frame operation results, binarization processing is carried out on the four difference frame operation results, and operation and then or operation are carried out on the four processed operation results, and then the target contour of the image can be obtained. The purpose of adopting the two-frame difference, the three-frame difference and the five-frame difference in the embodiment is that the calculation amount of the three difference calculation modes is small, and the algorithm real-time requirement can be met. The differential data obtained by the differential data can be used to analyze the types of motion (displacement type and interaction type).
Step S32: the pixel transformation in the region under the general motion condition of the human body is described by using one-dimensional normal distribution through a human body motion statistical model (namely, human body motion normal distribution), and differential data of non-human body activity is filtered. In the present embodiment, the statistics herein are performed based on multiple samples to ensure the accuracy of the statistics.
Step S4: and judging whether the image pixel differential data of the first 20 frames meet the human body interaction characteristic model. In this embodiment, 20 frames of images are selected as the determination criteria, and in other embodiments, images of other frames may be selected as the determination criteria.
Specifically, referring to fig. 4, the determination of whether the human interaction feature model is satisfied can be performed in the following manner:
step S41: and based on the obtained human body movement differential data, judging whether the differential data meets the human body movement type by using a human body movement model. In this embodiment, the human body displacement activity model is a normal distribution model obtained according to statistics of difference data, wherein the data sample is 20 frames of image difference data generating displacement type motion. And when the difference data | x-E | < ═ σ, determining that the data successfully falls in the distribution, namely determining that the data is the human body displacement activity, wherein x represents data obtained by image difference, E represents the average value of human body displacement type activity difference values in the statistical model, and σ represents the difference data variance obtained by calculation in image difference data statistics.
In this embodiment, 20 frames of images are selected as data samples, and in other embodiments, images of other frames may be selected as data samples.
Step S42:if the motion is not determined to be the displacement motion, matching the 20 frames of differential data diff with the human body interaction triggering model (taking the two frames of differential diff1 as an example, diff ∑ diff1i，i∈{[1,20],i∈N})。
Step S43: and if the matching is successful, recording the currently triggered interaction area and the time breakpoint. If the matching is not successful, the process returns to step S42 to continue the matching.
Step S44: and (4) performing cycle detection, and matching the 20 frames of differential data with a human body interaction termination model.
Step S45: and if the matching is successful, recording the currently terminated interactive area and the time breakpoint. If the matching is not successful, the process returns to step S44 to continue the matching.
In this embodiment, the human interaction termination model is a normal distribution model obtained from statistical data of difference data, and the data samples are image difference data of 10s before and after the human stops moving. When the difference data | x-E | < ═ σ, it is determined that the data successfully falls within the distribution, that is, it is determined as a human body interaction trigger model. Wherein x represents data obtained by image difference, E represents an average value of image difference values of human body interaction type activities in the statistical model, and σ represents a variance calculated in image difference data statistics.
Step S5: and recording the human body interaction area and the time period.
Specifically, referring to fig. 5, the step S5 specifically includes the following steps:
step S51: and calculating the overlapped part of the interaction triggering area and the termination area, and recording the overlapped part as a human body activity area. The interactive trigger area and the termination area are obtained in steps S42 and S43.
Step S52: and calculating the interval time between the interaction triggering and the termination, and corresponding to the recorded activity area. The time for the interaction triggering and terminating is obtained in steps S42 and S43.
Step S53: performing multiple groups of video detection in the same space, and recording all interactive trigger areas (area)1，area2，area3，……，arean) And all the interactive triggering areas within the range of 50 adjacent pixels are processedAnd solving intersection operation to obtain an intersection part area, wherein the intersection part area is the area with the highest interaction frequency in the finally obtained space. In this embodiment, the "adjacent 50 pixels" in the intersection calculation of the interactive trigger regions in the range of all adjacent 50 pixels is only an example, and other embodiments may also be selected according to the user's requirements.
Step S54: regions of different interaction frequencies are marked by red, yellow and green. Of course, in other embodiments, the regions with different interaction frequencies may be marked by other different colors or even other marks.
The algorithm of the method for identifying the interaction region and the interaction time period of the differential pixels mainly counts the pixel change of human body activity on an image, and then judges two states of human body common position movement and space interaction by combining a human body activity model, so that the human body interaction region and the interaction time period are finally obtained. The method needs less calculation consumption, can distinguish the human body displacement type activity from the interactive type activity, and can completely record the activity area of a human body and the activity time in the area.
The invention also discloses a storage device and a mobile terminal. The storage device stores a plurality of instructions adapted to be loaded and executed by a processor, the instructions comprising: receiving an input video signal, and performing frame splitting processing on the input video signal to generate a single-frame image; carrying out human shape detection on the obtained single-frame image; carrying out full-image difference and recording difference data; judging whether the image pixel differential data of the previous N frames meet a human body interaction characteristic model or not, and recording a triggered interaction region and a time breakpoint and a stopped interaction region and a time breakpoint; and recording the human body interaction area and the time period.
The mobile terminal comprises a processor and a storage device, wherein the processor is suitable for realizing instructions, the storage device is suitable for storing a plurality of instructions, the instructions are suitable for being loaded and executed by the processor, and the instructions comprise: receiving an input video signal, and performing frame splitting processing on the input video signal to generate a single-frame image; carrying out human shape detection on the obtained single-frame image; carrying out full-image difference and recording difference data; judging whether the image pixel differential data of the previous N frames meet a human body interaction characteristic model or not, and recording a triggered interaction region and a time breakpoint and a stopped interaction region and a time breakpoint; and recording the human body interaction area and the time period.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent structures made by using the contents of the present specification and the drawings can be directly or indirectly applied to other related technical fields, and are within the scope of the present invention.
Claims (8)
1. An interaction region and interaction time period identification method, suitable for being executed in a computing device, the method comprising:
receiving an input video signal, and performing frame splitting processing on the input video signal to generate a single-frame image;
carrying out human shape detection on the obtained single-frame image;
carrying out full-image difference and recording difference data;
judging whether the image pixel differential data of the previous N frames meet a human body interaction characteristic model or not, and recording a triggered interaction region and a time breakpoint and a stopped interaction region and a time breakpoint; and
recording human body interaction areas and time periods;
the step of judging whether the image pixel differential data of the previous N frames meet the human body interaction characteristic model and recording the triggered interaction region and time breakpoint and the stopped interaction region and time breakpoint comprises the following steps:
based on the obtained human body movement differential data, judging whether the differential data meets the human body movement type by using a human body movement model;
if the motion is not determined to be the displacement motion, matching the N frames of differential data with the human body interaction triggering model;
if the matching is successful, recording the currently triggered interaction area and the time breakpoint;
matching the N frames of differential data with a human body interaction termination model; and
and if the matching is successful, recording the currently terminated interactive area and the time breakpoint.
2. The method for identifying an interaction area and an interaction time period as claimed in claim 1, wherein: the step of detecting the human shape of the obtained single-frame image comprises the following steps:
converting the obtained single-frame image from RGB into a gray level image, and performing smooth denoising and filtering processing on the converted gray level image; and
and (5) detecting the portrait by using a portrait HOG operator.
3. The method for identifying an interaction area and an interaction time period as claimed in claim 2, wherein: the step of detecting the portrait by using a portrait HOG operator comprises the following steps:
performing Gamma correction;
converting the image into gray scale;
calculating the gradient and the direction of the image to obtain the gradient amplitude and the angle of the image;
8 multiplied by 8 grid direction gradient weight histogram statistics; and
the block descriptors are normalized to the feature vectors.
4. The method for identifying an interaction area and an interaction time period as claimed in claim 1, wherein: the step of carrying out full-image difference and recording difference data comprises the following steps:
respectively carrying out two-frame difference, three-frame difference and five-frame difference on the whole image, and recording corresponding difference results; and
the pixel transformation in the region under the general motion condition of the human body is described by applying one-dimensional normal distribution through a human body motion statistical model, and differential data of non-human body activity are filtered.
5. The method for identifying an interaction area and an interaction time period as claimed in claim 1, wherein: the step of recording the human body interaction area and the time period comprises the following steps:
calculating the overlapping part of the interaction triggering area and the termination area, and recording the overlapping part as a human body activity area;
calculating the interval time between the interactive triggering and the termination, and corresponding to the recorded activity area; and
and performing multi-group video detection in the same space, recording all interactive trigger areas, performing intersection operation on the interactive trigger areas in all adjacent M pixel ranges, and acquiring an intersection part area, wherein the intersection part area is the area with the highest interaction frequency in the finally acquired space.
6. The method as claimed in claim 5, wherein the method comprises the steps of: further comprising: areas of different interaction frequencies are marked by different colors.
7. A memory device having stored therein a plurality of instructions adapted to be loaded and executed by a processor, the instructions comprising:
receiving an input video signal, and performing frame splitting processing on the input video signal to generate a single-frame image;
carrying out human shape detection on the obtained single-frame image;
carrying out full-image difference and recording difference data;
judging whether the image pixel differential data of the previous N frames meet a human body interaction characteristic model or not, and recording a triggered interaction region and a time breakpoint and a stopped interaction region and a time breakpoint; and
recording human body interaction areas and time periods;
judging whether the image pixel differential data of the previous N frames meet a human body interaction characteristic model, and recording triggered interaction regions and time breakpoints and terminated interaction regions and time breakpoints, wherein the steps comprise:
based on the obtained human body movement differential data, judging whether the differential data meets the human body movement type by using a human body movement model;
if the motion is not determined to be the displacement motion, matching the N frames of differential data with the human body interaction triggering model;
if the matching is successful, recording the currently triggered interaction area and the time breakpoint;
matching the N frames of differential data with a human body interaction termination model; and
and if the matching is successful, recording the currently terminated interactive area and the time breakpoint.
8. A mobile terminal, comprising:
a processor adapted to implement instructions; and
a storage device adapted to store a plurality of instructions, the instructions adapted to be loaded and executed by a processor, the instructions comprising:
receiving an input video signal, and performing frame splitting processing on the input video signal to generate a single-frame image;
carrying out human shape detection on the obtained single-frame image;
carrying out full-image difference and recording difference data;
judging whether the image pixel differential data of the previous N frames meet a human body interaction characteristic model or not, and recording a triggered interaction region and a time breakpoint and a stopped interaction region and a time breakpoint; and
recording human body interaction areas and time periods;
judging whether the image pixel differential data of the previous N frames meet a human body interaction characteristic model, and recording triggered interaction regions and time breakpoints and terminated interaction regions and time breakpoints, wherein the steps comprise:
based on the obtained human body movement differential data, judging whether the differential data meets the human body movement type by using a human body movement model;
if the motion is not determined to be the displacement motion, matching the N frames of differential data with the human body interaction triggering model;
if the matching is successful, recording the currently triggered interaction area and the time breakpoint;
matching the N frames of differential data with a human body interaction termination model; and
and if the matching is successful, recording the currently terminated interactive area and the time breakpoint.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710655807.2A CN107330424B (en) | 2017-08-03 | 2017-08-03 | Interaction area and interaction time period identification method, storage device and mobile terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710655807.2A CN107330424B (en) | 2017-08-03 | 2017-08-03 | Interaction area and interaction time period identification method, storage device and mobile terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107330424A CN107330424A (en) | 2017-11-07 |
| CN107330424B true CN107330424B (en) | 2020-10-16 |
Family
ID=60225613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710655807.2A Active CN107330424B (en) | 2017-08-03 | 2017-08-03 | Interaction area and interaction time period identification method, storage device and mobile terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107330424B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7457007B2 (en) * | 2003-04-07 | 2008-11-25 | Silverbrook Research Pty Ltd | Laser scanning device for printed product identification codes |
| CN102436301A (en) * | 2011-08-20 | 2012-05-02 | Tcl集团股份有限公司 | Human-machine interaction method and system based on reference region and time domain information |
| CN102509088A (en) * | 2011-11-28 | 2012-06-20 | Tcl集团股份有限公司 | Hand motion detecting method, hand motion detecting device and human-computer interaction system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4509917B2 (en) * | 2005-11-21 | 2010-07-21 | 株式会社メガチップス | Image processing apparatus and camera system |
-
2017
- 2017-08-03 CN CN201710655807.2A patent/CN107330424B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7457007B2 (en) * | 2003-04-07 | 2008-11-25 | Silverbrook Research Pty Ltd | Laser scanning device for printed product identification codes |
| CN102436301A (en) * | 2011-08-20 | 2012-05-02 | Tcl集团股份有限公司 | Human-machine interaction method and system based on reference region and time domain information |
| CN102509088A (en) * | 2011-11-28 | 2012-06-20 | Tcl集团股份有限公司 | Hand motion detecting method, hand motion detecting device and human-computer interaction system |
Non-Patent Citations (1)
| Title |
|---|
| "基于HOG特征的人脸识别系统研究";幕春雷;《中国优秀硕士学位论文全文数据库 (电子期刊) 信息科技辑》;20140115;期刊第4.2节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107330424A (en) | 2017-11-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kruthiventi et al. | Saliency unified: A deep architecture for simultaneous eye fixation prediction and salient object segmentation | |
| US20200167554A1 (en) | Gesture Recognition Method, Apparatus, And Device | |
| US9536147B2 (en) | Optical flow tracking method and apparatus | |
| CN110427905A (en) | Pedestrian tracting method, device and terminal | |
| US9615039B2 (en) | Systems and methods for reducing noise in video streams | |
| US9014467B2 (en) | Image processing method and image processing device | |
| CN111539273A (en) | Traffic video background modeling method and system | |
| CN112308095A (en) | Picture preprocessing and model training method and device, server and storage medium | |
| WO2019074601A1 (en) | Object tracking for neural network systems | |
| US8548247B2 (en) | Image processing apparatus and method, and program | |
| CN109101897A (en) | Object detection method, system and the relevant device of underwater robot | |
| US20100296701A1 (en) | Person tracking method, person tracking apparatus, and person tracking program storage medium | |
| CN104867111B (en) | A kind of blind deblurring method of non-homogeneous video based on piecemeal fuzzy core collection | |
| CN105989367A (en) | Target acquisition method and equipment | |
| US8577137B2 (en) | Image processing apparatus and method, and program | |
| Huynh-The et al. | NIC: A robust background extraction algorithm for foreground detection in dynamic scenes | |
| US8094971B2 (en) | Method and system for automatically determining the orientation of a digital image | |
| CN109886195B (en) | Skin identification method based on near-infrared monochromatic gray-scale image of depth camera | |
| CN111553915A (en) | Article identification detection method, device, equipment and readable storage medium | |
| CN111784624A (en) | Target detection method, device, equipment and computer readable storage medium | |
| CN105405138A (en) | Water surface target tracking method based on saliency detection | |
| CN113542868A (en) | Video key frame selection method and device, electronic equipment and storage medium | |
| CN110827320A (en) | Target tracking method and device based on time sequence prediction | |
| Yanulevskaya et al. | Salient object detection: from pixels to segments | |
| CN115482523A (en) | Small object target detection method and system of lightweight multi-scale attention mechanism |
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 |