CN115035547A - Sitting posture detection method, device, equipment and computer storage medium - Google Patents
Sitting posture detection method, device, equipment and computer storage medium Download PDFInfo
- Publication number
- CN115035547A CN115035547A CN202210607019.7A CN202210607019A CN115035547A CN 115035547 A CN115035547 A CN 115035547A CN 202210607019 A CN202210607019 A CN 202210607019A CN 115035547 A CN115035547 A CN 115035547A
- Authority
- CN
- China
- Prior art keywords
- sitting posture
- user
- human body
- key points
- determining
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 90
- 238000000034 method Methods 0.000 claims abstract description 37
- 230000005856 abnormality Effects 0.000 claims abstract description 18
- 230000002159 abnormal effect Effects 0.000 claims description 45
- 238000011156 evaluation Methods 0.000 claims description 19
- 238000012937 correction Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 16
- 210000001015 abdomen Anatomy 0.000 claims description 6
- 210000000707 wrist Anatomy 0.000 claims description 5
- 210000003128 head Anatomy 0.000 description 5
- 230000037237 body shape Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 210000000245 forearm Anatomy 0.000 description 4
- 208000028752 abnormal posture Diseases 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000003187 abdominal effect Effects 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003601 intercostal effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 210000002784 stomach Anatomy 0.000 description 1
- 238000006467 substitution reaction 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a sitting posture detection method, a sitting posture detection device, equipment and a computer storage medium, wherein the sitting posture detection method comprises the following steps: carrying out image detection on the acquired target image, and determining human body key points of the user in a sitting posture state in the target image; acquiring human body parameter information of a user; according to the human body parameter information, adjusting the parameter information in the standard sitting posture template to obtain a target sitting posture template corresponding to the user; and determining a sitting posture detection result of the user according to the key points of the human body and the target sitting posture template, wherein the sitting posture detection result comprises sitting posture normality or sitting posture abnormality. According to the method, whether the current sitting posture of the user is normal or not is determined by judging whether the human body key point of the user is located at the position, corresponding to the human body key point, on the target sitting posture template, so that the sitting posture of the student is detected in real time, the habit of the student forming the correct sitting posture is helped, and in the method, the correct sitting posture is used as the target sitting posture template, so that the correct rate of the adjusted sitting posture of the student can be guaranteed.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a sitting posture detection method, a sitting posture detection device, sitting posture detection equipment and a computer storage medium.
Background
The lives of students are generally concerned by parents, teachers and society, and not only the learning habits of the students but also the physique and stature of the students are concerned more and more.
At present, the sitting posture of the students of low ages is generally supervised and corrected by parents or teachers, or forcibly corrected by physical means, such as guardrail sitting posture correctors, braces sitting posture correcting products and the like; however, parents or teachers often cannot supervise and urge at all times, and it is difficult to help students develop correct sitting habits.
How to accompany relevant personnel, parents or teachers is not needed, and the problem that the students need to solve is urgently needed to develop the correct sitting posture habit.
Disclosure of Invention
The invention provides a sitting posture detection method, a sitting posture detection device, sitting posture detection equipment and a computer storage medium, which are used for detecting the sitting posture of a student in real time and giving a prompt.
The invention provides a sitting posture detection method, which comprises the following steps:
carrying out image detection on the acquired target image, and determining human body key points of the user in a sitting posture state in the target image;
acquiring human body parameter information of the user;
according to the human body parameter information, parameter information in a standard sitting posture template is adjusted to obtain a target sitting posture template corresponding to the user;
and determining a sitting posture detection result of the user according to the human body key points and the target sitting posture template, wherein the sitting posture detection result comprises sitting posture normality or sitting posture abnormality.
According to the method provided by the invention, the human body parameter information comprises the ratio of the arm length to the shoulder width of the user arm;
the acquiring of the human body parameter information of the user comprises:
determining the arm length of the arm according to the wrist key point, the elbow key point and the shoulder key point of any side arm in the human body key points;
determining the shoulder width according to two shoulder key points in the human body key points;
determining a ratio of the arm length to the shoulder width based on the arm length and the shoulder width.
According to the method provided by the invention, the human parameter information further comprises the ratio of the length of the upper half of the user to the shoulder width;
the acquiring of the human body parameter information of the user comprises:
determining the length of the upper half body according to a plurality of human key points from a nose tip key point to an abdomen key point in the human key points;
determining the shoulder width according to two shoulder key points in the human body key points;
determining a ratio of the user's upper body length to shoulder width based on the upper body length and the shoulder width.
According to the method provided by the invention, the determining the sitting posture detection result of the user according to the human body key points and the target sitting posture template comprises the following steps:
comparing the plurality of human key points with the corresponding reference key points in the target sitting posture module, and determining that the sitting posture detection result of the user is abnormal in sitting posture under the condition that the distance between at least one first human key point and the corresponding reference key point in the plurality of human key points is larger than a preset value.
According to the method provided by the invention, after determining the sitting posture detection result of the user, the method further comprises the following steps:
and outputting evaluation information, wherein the evaluation information comprises the score and the evaluation content of the user sitting posture.
According to the method provided by the invention, the method further comprises the following steps:
determining an abnormal type corresponding to the abnormal sitting posture under the condition that the sitting posture detection result is determined to be the abnormal sitting posture;
generating sitting posture correction prompt information corresponding to the abnormal type;
and outputting the sitting posture correction prompt information.
The invention provides a sitting posture detecting device, which comprises:
the detection module is used for carrying out image detection on the acquired target image and determining human body key points of the user in a sitting posture state in the target image;
the detection module is also used for acquiring the human body parameter information of the user;
the adjusting module is used for adjusting the parameter information in the standard sitting posture template according to the human body parameter information to obtain a target sitting posture template corresponding to the user;
and the comparison module is used for determining the sitting posture detection result of the user according to the human body key points and the target sitting posture template, wherein the sitting posture detection result comprises sitting posture normality or sitting posture abnormality.
The invention provides an electronic device which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the sitting posture detection method.
The present invention provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a sitting posture detection method as described in any one of the above.
The invention provides a computer program product comprising a computer program which, when executed by a processor, implements a sitting posture detection method as described in any one of the above.
The invention provides a sitting posture detection method, a sitting posture detection device, equipment and a computer storage medium, wherein the sitting posture detection method comprises the following steps: carrying out image detection on the acquired target image, and determining human body key points of the user in a sitting posture state in the target image; acquiring human body parameter information of the user; according to the human body parameter information, parameter information in a standard sitting posture template is adjusted to obtain a target sitting posture template corresponding to the user; and determining a sitting posture detection result of the user according to the human body key points and the target sitting posture template, wherein the sitting posture detection result comprises sitting posture normality or sitting posture abnormality. According to the method, whether the current sitting posture of the user is normal or not is determined by judging whether the human body key point of the user is located at the position, corresponding to the human body key point, on the target sitting posture template, so that the sitting posture of the student is detected in real time, the habit of the student forming the correct sitting posture is helped, and in the method, the correct sitting posture is used as the target sitting posture template, so that the correct rate of the adjusted sitting posture of the student can be guaranteed. On the other hand, the parameter information in the standard sitting posture template can be adjusted according to the human parameter information to obtain a target sitting posture template corresponding to the user, and the corresponding target sitting posture template is determined according to the human parameter information of the user to be detected at present due to the fact that differences among different user body types are considered, so that the accuracy of the determined target sitting posture template is high.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a sitting posture detecting method according to an embodiment of the present invention;
fig. 2 is a second schematic flow chart of a sitting posture detecting method according to an embodiment of the present invention;
fig. 3 is a third schematic flow chart of a sitting posture detecting method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a sitting posture detecting apparatus according to an embodiment of the present invention;
fig. 5 is a schematic physical structure diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a sitting posture detecting method according to an embodiment of the present invention, and as shown in fig. 1, the present invention provides a sitting posture detecting method, including:
s101, carrying out image detection on the acquired target image, and determining human body key points of the user in a sitting posture state in the target image.
The method is suitable for a scene of determining the sitting posture of the user.
In the invention, before the image detection is carried out on the acquired target image, the sitting posture of a user can be acquired through the image acquisition equipment so as to obtain an initial image. The image acquisition device can be a camera or a video camera, and the image acquisition device can be arranged on the robot.
In the invention, the target detection can be carried out on the initial image. The target detection comprises three stages: region selection, feature extraction and sign classification; the region selection can use a sliding window algorithm to select and obtain a plurality of regions to be processed with the same size as the sliding window from the initial image; the reference frames with different sizes and different length-width ratios preset on the image can be screened according to the overlapping degree of the reference frames to obtain the rest reference frames. The feature extraction refers to extracting features of the regions to be processed or the regions framed in the remaining reference frames through an extractor after the regions to be processed or the remaining reference frames are obtained. The sign classification means that after the feature extraction is completed, the extracted features are classified through a classifier, so that the position of a user in an initial image is determined, and a target image is obtained.
In the invention, the image detection of the collected target image may be: denoising a target image to make a user in the target image clearer; and then determining the human body key points of the user in the sitting posture state in the target image, and acquiring the position information of the human body key points.
It can be understood that the current sitting posture of the user can be obtained through simulation by determining the positions of the key points of the human body of the user, and then the current sitting posture of the user is compared with the correct sitting posture to determine whether the current sitting posture of the user is normal or not, so that the sitting posture of the user can be detected, and the correct rate of the adjusted sitting posture of the user can be ensured after the user is reminded of abnormal current sitting posture.
And S102, acquiring human body parameter information of the user.
This step is applicable to the scenario of determining the current body parameters of the user.
In a possible implementation manner, the robot may select a fixed-size object in the target image as a reference object, and determine the human body parameter information of the user according to a ratio between the fixed-size object and a human body parameter corresponding to the user in the target image, or a ratio between a size of the fixed-size object in the target image and a real size. Illustratively, the real dimensions of the fixed-size object correspond to: the height is 40cm, the height of the fixed-size object in the target image is 20cm, and in this case, if the distance between the human body key point at the left shoulder and the human body key point at the right shoulder of the user in the target image is 19cm, that is, the shoulder width of the user in the target image is 19cm, the shoulder width in the human body parameter information of the user should be 38 cm.
In another possible implementation manner, the distance between each human body key point in the image and the camera can be determined by using the 3D information acquired by the 3D camera, and the three-dimensional space coordinates of each human body key point in the image can be obtained based on the distance and the (x, y) coordinates of the human body key point in the 2D image, so that the distance between any two human body key points in the actual space can be calculated.
In the invention, the robot can also output human body parameter acquisition information, the human body parameter acquisition information is used for reminding a user to input own human body parameters, and then the robot receives the human body parameters input by the user and acquires the human body parameter information of the user; in addition, after the robot receives the human body parameter information of the user for the first time, the human body parameter information can be stored in the database, and then the latest human body parameter information of the user can be obtained by combining time conjecture according to the human body parameter information in the database.
It can be understood that the body type of the user can be determined by obtaining the human body parameter information of the user, whether the current sitting posture of the user is normal or not is detected based on the body type of the user, and the accuracy of the sitting posture detection result can be improved.
In some embodiments of the invention, the body parameter information comprises a ratio of an arm length to a shoulder width of the user's arm.
In some embodiments of the present invention, where the body parameter information includes a ratio of an arm length to a shoulder width of the user' S arm, S102 may include S1021-S1023, and S1021-S1023 are as follows:
and S1021, determining the arm length of the arm according to the wrist key point, the elbow key point and the shoulder key point of the arm on any side of the human body key points.
In some embodiments of the present invention, the length of the forearm of the user may be determined according to the distance between the wrist key point and the elbow key point of any one of the arms among the body key points, and then the length of the forearm of the user may be determined according to the distance between the elbow key point and the shoulder key point, and the lengths corresponding to the forearm and the forearm are added to determine the arm length of the entire arm of the user.
And S1022, determining the shoulder width according to two shoulder key points in the human body key points.
In some embodiments of the present invention, the shoulder width of the user is determined according to a distance between key points of left and right shoulders among key points of a human body corresponding to the user.
S1023, based on the arm length and the shoulder width, a ratio of the arm length to the shoulder width is determined.
In some embodiments of the present invention, the arm length to shoulder width ratio may be determined by dividing the arm length by the shoulder width based on the arm length and shoulder width determined in S1021 and S1022. Illustratively, a shoulder width of 39 and an arm length of 55, the ratio of arm length to shoulder width is 1.4.
In some embodiments of the invention, the body parameter information further comprises a ratio of the user's upper body length to shoulder width.
The invention can determine the body shape of the upper half of the user through the ratio of the arm length to the shoulder width, subsequently adjust the upper half of the standard sitting posture template representing the correct sitting posture to be consistent with the body shape of the upper half of the user to obtain the target sitting posture template, and then compare the current sitting posture of the user with the target sitting posture template, so that whether the current sitting posture of the user is normal can be more accurately judged, the accuracy of a sitting posture detection result is improved, and the correct rate of the adjusted sitting posture of the user can be ensured after the user is reminded of the abnormal current sitting posture.
In some embodiments of the present invention, where the body parameter information further includes a ratio of the user' S upper body length to shoulder width, S102 may include S1024-S1026, the S1024-S1026 being as follows:
and S1024, determining the length of the upper half body according to a plurality of human key points from the tip of the nose to the abdomen.
In some embodiments of the present invention, since the upper half of the user (or the upper half of the user exposed from the desktop) should be displayed in the target image when the user is in a sitting posture, and the upper half of the user may be curved due to the bending of the user when the user is in a sitting posture, a plurality of human body key points may be taken from the tip of nose key point to the abdomen key point among the human body key points, and the plurality of human body key points may be fitted to fit the curved upper half of the user. And then, according to the distance between every two adjacent human key points in the plurality of human key points from the middle nose tip key point to the abdomen key point, adding the distances between every two adjacent human key points to determine the length of the upper half of the user.
In some embodiments of the present invention, the abdominal key point may be at the navel of the user or at the intercostal space of the user, corresponding to the stomach of the user. The embodiments of the present invention are not limited.
And S1025, determining the shoulder width according to two shoulder key points in the key points of the human body.
In some embodiments of the present invention, the user' S shoulder width is determined as in S1022.
And S1026, determining the ratio of the upper half length to the shoulder width of the user based on the upper half length and the shoulder width.
In some embodiments of the present invention, the length of the user ' S upper body determined at S1024 is divided by the width of the user ' S shoulder determined at S1025 to determine the ratio of the length of the user ' S upper body to the width of the shoulder, as at S1023.
It can be understood that the body type of the upper half of the user can be determined according to the ratio of the length of the upper half of the body to the shoulder width, and the upper half of the standard sitting posture template representing the correct sitting posture is adjusted to be consistent with the body type of the upper half of the user to obtain a target sitting posture template; then, the current sitting posture of the user is compared with the adjusted target sitting posture template, whether the current sitting posture of the user is normal or not can be judged more accurately, the accuracy of a sitting posture detection result is improved, and the accuracy of the adjusted sitting posture of the user can be ensured after the current sitting posture of the user is reminded to be abnormal.
S103, adjusting the parameter information in the standard sitting posture template according to the human body parameter information to obtain a target sitting posture template corresponding to the user.
According to the invention, parameter information in the standard sitting posture template is adjusted according to the ratio of the upper half length of the user to the shoulder width and/or the ratio of the arm length to the shoulder width, namely the ratio of the upper half length to the shoulder width and/or the ratio of the arm length to the shoulder width in the standard sitting posture template is adjusted to be the same as that of the user, and a target sitting posture template corresponding to the user is obtained.
In the invention, the parameter information in the standard sitting posture template can be adjusted according to the specific numerical value corresponding to any one or more of the length of the upper half of the user, the arm length and the shoulder width, so as to obtain the target sitting posture template corresponding to the user.
It can be understood that the parameter information in the target sitting posture template is adjusted according to the ratio of the length of the upper half of the user to the shoulder width and/or the ratio of the length of the arm to the shoulder width, so that the body shape corresponding to the target coordinate template is similar to the real body shape of the user, the current sitting posture of the user is compared with the target sitting posture template, whether the current sitting posture of the user is normal can be judged more accurately, and the accuracy of a sitting posture detection result is improved.
And S104, determining a sitting posture detection result of the user according to the key points of the human body and the target sitting posture template, wherein the sitting posture detection result comprises sitting posture normality or sitting posture abnormality.
The method is suitable for the scene of judging whether the user sitting posture is normal or not.
In the invention, after the human body key points of the user are determined in S102 and the target sitting posture template is obtained in S103, the sitting posture detection result of the user can be determined by combining the human body key points and the target sitting posture template, and the sitting posture detection result comprises sitting posture normality or sitting posture abnormality. Wherein the sitting posture is normal and the sitting posture is abnormal, wherein the sitting posture is correct and the sitting posture is incorrect.
In the invention, system hardware for executing the sitting posture detection method comprises a deep learning algorithm module, which can detect human body information (human body parameter information) and sitting posture information (human body key point) of a user through a deep learning algorithm and adaptively adjust parameter information in a standard human body sitting posture template (standard sitting posture module) through the human body parameter information; and finally, comparing the detected sitting posture information with the target sitting posture template to obtain a sitting posture detection result.
It can be understood that by the method, the human key points and the target sitting posture template corresponding to the current sitting posture of the user are obtained, the human key points and the target sitting posture template are compared, and whether the sitting posture of the user is normal or not can be determined according to the deviation between the human key points and the target sitting posture template, so that a sitting posture detection result is obtained, and the accuracy of the sitting posture detection result can be ensured.
In some embodiments of the present invention, the plurality of human key points are compared with corresponding reference key points in the target sitting posture module, and when there is at least one first human key point in the plurality of human key points and the distance between the corresponding reference key point is greater than a preset value, it is determined that the sitting posture detection result of the user is a sitting posture abnormality.
In some embodiments of the invention, the plurality of human key points correspond to the reference key points in the target sitting posture module one to one; during the comparison, the distance between each human body key point and the corresponding reference key point, namely the deviation between each human body key point and the corresponding reference key point, can be determined according to the absolute value of the sum of the difference between the x-axis coordinate and the difference between the y-axis coordinate between each human body key point and the corresponding reference key point; the distance between each human body key point and the corresponding reference key point can be determined according to the straight-line distance between each human body key point and the corresponding reference key point. And determining that the sitting posture detection result of the user is abnormal in sitting posture under the condition that the distance between at least one first human body key point and the corresponding reference key point in the plurality of human body key points is larger than a preset value.
It can be understood that the degree of deviation between the current sitting posture of the user and the target sitting posture template can be determined by obtaining the distance or deviation between each human body key point and the corresponding reference key point, so that whether the current sitting posture of the user is normal or not is determined, a sitting posture detection result is obtained, and the accuracy of the sitting posture detection result can be ensured.
In some embodiments of the invention, after the S104 determines the sitting posture detection result of the user, the method further includes: and outputting evaluation information, wherein the evaluation information comprises scores and evaluation contents for the sitting posture of the user.
In some embodiments of the present invention, after determining the sitting posture detection result of the user through S104, evaluation information may be output to score and evaluate the sitting posture of the user.
In some embodiments of the invention, the evaluation information is generated based on the distance or deviation between each human keypoint and the corresponding reference keypoint. For example, in a case that the sitting posture detection result is a sitting posture which is normal, assuming that the distance between the nose tip key point in the user human body key point and the nose tip reference viewpoint in the reference key point is 0, the evaluation information may be generated: "Sitting position 100 points, current sitting position normal, head excellent distance from table, refuel, wish to continue to hold! ". Under the condition that the sitting posture detection result is abnormal sitting posture, assuming that the distance between the nasal tip key point in the human body key point of the user and the nasal tip reference viewpoint in the reference key point is 3 and exceeds a preset threshold, evaluation information can be generated: "Sitting posture 60, current sitting posture is abnormal, head is too close to desktop, please raise head to protect vision, thank you! "
It can be understood that by outputting the evaluation information, the method not only can play a role of prompting the user, but also can indicate an abnormal part for the user when the sitting posture of the user is abnormal, and correctly guide the abnormal part, so that the user can correct the sitting posture according to the guide, the accuracy of the corrected sitting posture is improved, and the efficiency of correcting the sitting posture of the user is improved; the problem that the user can not correct the sitting posture to the standard sitting posture due to the fact that the user corrects the sitting posture subjectively and the sitting posture is delayed is avoided, and therefore efficiency is wasted. When the user sitting posture is abnormal, encouragement and the like can be made for the user, and the time for the user to insist on the correct sitting posture is increased.
Fig. 2 is a second schematic flow chart of a sitting posture detecting method according to an embodiment of the present invention, as shown in fig. 2, the sitting posture detecting method further includes:
and S105, determining the abnormal type corresponding to the abnormal sitting posture under the condition that the sitting posture detection result is determined to be the abnormal sitting posture.
In some embodiments of the present invention, in a case that the sitting posture detection result is determined to be a sitting posture abnormality, the abnormality type corresponding to the abnormal sitting posture may be determined based on the database.
In some embodiments of the present invention, the distance or the deviation between each human body key point determined in S104 and the corresponding reference key point is compared with a plurality of sitting posture templates stored in the database to obtain a sitting posture template corresponding to the current abnormal sitting posture of the user, and an abnormal type corresponding to the abnormal sitting posture is determined according to the type corresponding to the sitting posture template in the database.
In some embodiments of the present invention, for example, when the sitting posture detection result is a sitting posture abnormality and the distance between the nose tip key point in the human body key point and the nose tip reference viewpoint in the reference key point of the abnormal posture of the user is 3 and exceeds a preset threshold, the abnormal posture is compared with a plurality of sitting posture templates stored in the database, and the sitting posture template corresponding to the current abnormal sitting posture of the user is obtained as the distance between the eyes and the desktop; it can be determined that the type of abnormality corresponding to the out-of-position sitting is that the eyes are too close to the tabletop.
And S106, generating sitting posture correction prompt information corresponding to the abnormal type.
In some embodiments of the present invention, based on the abnormality type corresponding to the abnormal posture determined in S105, the sitting posture correction prompting information corresponding to the abnormality type is generated. The sitting posture correction prompt information can be stored in a database and corresponds to a plurality of sitting posture templates in the database; in practical application, one sitting posture template can correspond to a plurality of sitting posture correction prompt messages, and the sitting posture correction prompt messages between the sitting posture templates can be the same. The sitting posture correction prompt information can be generated according to key words stored in the database, the key words correspond to a plurality of sitting posture templates in the database, and each key word can correspond to a plurality of sitting posture templates.
In some embodiments of the present invention, for example, the sitting posture template corresponding to the current abnormal sitting posture of the user is that the eyes are too close to the desktop, and the sitting posture prompt information corresponding to the sitting posture template is: the head is raised, so that the sitting posture correction prompt information is generated under the condition that two eyes are away from the desktop by one ruler: the head is raised, so that the distance between the two eyes and the desktop is one ruler.
And S107, outputting sitting posture correction prompt information.
In some embodiments of the present invention, the generated sitting posture correction prompt information is output S106; the voice output can be realized, and the output can be finished by displaying characters on a screen.
It can be understood that, by determining the abnormal type of the user's abnormal sitting posture and outputting the corresponding sitting posture correction prompt information, not only can the user be prompted, but also the abnormal part can be pointed out for the user when the user's sitting posture is abnormal, and the user can be guided correctly for the abnormal part, so that the user can correct the sitting posture according to the guidance, and the accuracy of the corrected sitting posture is improved.
Fig. 3 is a third schematic flow chart of a sitting posture detecting method according to an embodiment of the present invention, and as shown in fig. 3, the present invention provides a sitting posture detecting method, including:
s201, collecting a human body sitting posture image (target image) by a camera.
S202, detecting human body joint point information (human body key points) by using a human body key point detection algorithm.
And S203, adjusting the human body template (standard sitting posture template) according to the detected human body parameter information.
S204, comparing and evaluating the detected human body sitting posture (human body key points) and the adjusted template (target sitting posture template), and giving evaluation information and a sitting posture improvement scheme (sitting posture correction prompt information).
It can be understood that the current human sitting posture of the user can be obtained through simulation by detecting the human joint point information of the user, and then the current human sitting posture of the user is compared with a template used for representing the correct sitting posture and adjusted according to the body type of the user, so that whether the current human sitting posture of the user is normal or not can be determined, the sitting posture of the user can be detected, and the accuracy of the adjusted sitting posture of the user after reminding the user of the abnormal current sitting posture can be ensured. And after the abnormal type of the abnormal sitting posture of the user is determined, the evaluation information and the sitting posture improvement scheme are output, so that the prompting effect can be realized for the user, the abnormal part can be pointed out for the user when the sitting posture of the user is abnormal, and the correct guidance can be performed aiming at the abnormal part, so that the user can correct the sitting posture according to the guidance, and the accuracy of the corrected sitting posture is improved. On the other hand, parameter information in the standard sitting posture template can be adjusted according to the human body parameter information to obtain a target sitting posture template corresponding to the user, and the corresponding target sitting posture template is determined according to the human body parameter information of the user to be detected at present due to the fact that differences among different user body types are considered, so that the accuracy of the determined target sitting posture template is high.
Fig. 4 is a schematic structural diagram of a sitting posture detecting device according to an embodiment of the present invention, and as shown in fig. 4, the present invention provides a sitting posture detecting device suitable for a sitting posture detecting method according to an embodiment of the present invention, where the sitting posture detecting device 7 includes:
the detection module 71 is configured to perform image detection on the acquired target image, and determine human body key points of the user in a sitting posture state in the target image;
an obtaining module 72, configured to obtain human body parameter information of the user;
the adjusting module 73 is configured to adjust parameter information in a standard sitting posture template according to the human body parameter information to obtain a target sitting posture template corresponding to the user;
and a comparison module 74, configured to determine a sitting posture detection result of the user according to the human body key point and the target sitting posture template, where the sitting posture detection result includes a sitting posture normality or a sitting posture abnormality.
In some embodiments of the invention, the body parameter information comprises a ratio of an arm length to a shoulder width of the user's arm; the obtaining module 72 is further configured to determine the arm length of an arm according to a wrist key point, an elbow key point and a shoulder key point of any one of the human body key points; determining the shoulder width according to two shoulder key points in the human body key points; determining a ratio of the arm length to the shoulder width based on the arm length and the shoulder width.
In some embodiments of the invention, the body parameter information further comprises a ratio of the user's upper body length to shoulder width; the obtaining module 72 is further configured to determine the length of the upper body according to a plurality of human key points from a nose tip key point to an abdomen key point among the human key points; determining the shoulder width according to two shoulder key points in the human body key points; determining a ratio of the user's upper body length to shoulder width based on the upper body length and the shoulder width.
In some embodiments of the present invention, the comparing module 74 is further configured to compare a plurality of human key points with corresponding reference key points in the target sitting posture module, and determine that the sitting posture detection result of the user is a sitting posture abnormality when a distance between at least one first human key point and the corresponding reference key point in the plurality of human key points is greater than a preset value.
In some embodiments of the present invention, the apparatus further comprises an output module 75, wherein:
the output module 75 is configured to output evaluation information, where the evaluation information includes a score and evaluation content for the user sitting posture.
In some embodiments of the invention, the apparatus further comprises a generation module 76, wherein:
the comparison module 74 is further configured to determine an abnormal type corresponding to an abnormal sitting posture when the sitting posture detection result is determined to be the abnormal sitting posture;
the generating module 76 is configured to generate sitting posture correction prompt information corresponding to the abnormality type;
the output module 75 is further configured to output the sitting posture correction prompt information.
Fig. 5 is a schematic entity structure diagram of an electronic device provided in an embodiment of the present application, and as shown in fig. 5, the electronic device provided in the present application may include: a processor (processor)810, a communication Interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication Interface 820 and the memory 830 communicate with each other via the communication bus 840. The processor 810 may call logic instructions in the memory 830 to perform the sitting posture detection methods provided by the methods described above.
In addition, the logic instructions in the memory 830 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solutions of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present application further provides a computer program product comprising a computer program, the computer program being storable on a non-transitory computer readable storage medium, the computer program, when executed by a processor, being capable of executing the sitting posture detecting method provided by the above methods.
In yet another aspect, the present application further provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the sitting posture detecting method provided by the above methods.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A sitting posture detecting method, comprising:
carrying out image detection on the acquired target image, and determining human body key points of the user in a sitting posture state in the target image;
acquiring human body parameter information of the user;
according to the human body parameter information, parameter information in a standard sitting posture template is adjusted to obtain a target sitting posture template corresponding to the user;
and determining a sitting posture detection result of the user according to the human body key points and the target sitting posture template, wherein the sitting posture detection result comprises sitting posture normality or sitting posture abnormality.
2. The sitting posture detection method of claim 1, wherein the human parameter information comprises a ratio of an arm length to a shoulder width of the user's arm;
the acquiring of the human body parameter information of the user comprises:
determining the arm length of the arm according to the wrist key point, the elbow key point and the shoulder key point of any side arm in the human body key points;
determining the shoulder width according to two shoulder key points in the human body key points;
determining a ratio of the arm length to the shoulder width based on the arm length and the shoulder width.
3. The sitting posture detection method of claim 2, wherein the human parameter information further comprises a ratio of the user's upper body length to shoulder width;
the acquiring of the human body parameter information of the user comprises:
determining the length of the upper half body according to a plurality of human key points from a nose tip key point to an abdomen key point in the human key points;
determining the shoulder width according to two shoulder key points in the human body key points;
determining a ratio of the user's upper body length to shoulder width based on the upper body length and the shoulder width.
4. The sitting posture detection method of any one of claims 1-3, wherein determining the sitting posture detection result of the user according to the human body key points and the target sitting posture template comprises:
comparing the plurality of human key points with the corresponding reference key points in the target sitting posture module, and determining that the sitting posture detection result of the user is abnormal in sitting posture under the condition that the distance between at least one first human key point and the corresponding reference key point in the plurality of human key points is larger than a preset value.
5. The sitting posture detection method of any one of claims 1-3, wherein after determining the sitting posture detection result of the user, the method further comprises:
and outputting evaluation information, wherein the evaluation information comprises the score and the evaluation content of the user sitting posture.
6. The sitting posture detecting method as claimed in any one of claims 1 to 3, wherein the method further comprises:
determining an abnormal type corresponding to an abnormal sitting posture under the condition that the sitting posture detection result is determined to be abnormal sitting posture;
generating sitting posture correction prompt information corresponding to the abnormal type;
and outputting the sitting posture correction prompt information.
7. A sitting posture detecting apparatus, comprising:
the detection module is used for carrying out image detection on the acquired target image and determining human body key points of the user in a sitting posture state in the target image;
the acquisition module is used for acquiring the human body parameter information of the user;
the adjusting module is used for adjusting the parameter information in the standard sitting posture template according to the human body parameter information to obtain a target sitting posture template corresponding to the user;
and the comparison module is used for determining the sitting posture detection result of the user according to the human body key points and the target sitting posture template, wherein the sitting posture detection result comprises sitting posture normality or sitting posture abnormality.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the sitting posture detection method according to any one of claims 1 to 6 when executing the program.
9. A non-transitory computer-readable storage medium on which a computer program is stored, wherein the computer program, when executed by a processor, implements the sitting posture detection method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, wherein the computer program, when executed by a processor, implements the sitting posture detection method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210607019.7A CN115035547A (en) | 2022-05-31 | 2022-05-31 | Sitting posture detection method, device, equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210607019.7A CN115035547A (en) | 2022-05-31 | 2022-05-31 | Sitting posture detection method, device, equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115035547A true CN115035547A (en) | 2022-09-09 |
Family
ID=83123654
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210607019.7A Pending CN115035547A (en) | 2022-05-31 | 2022-05-31 | Sitting posture detection method, device, equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115035547A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115240231A (en) * | 2022-09-22 | 2022-10-25 | 珠海翔翼航空技术有限公司 | Image recognition-based sitting posture detection and adjustment method for full-motion simulator |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190251341A1 (en) * | 2017-12-08 | 2019-08-15 | Huawei Technologies Co., Ltd. | Skeleton Posture Determining Method and Apparatus, and Computer Readable Storage Medium |
| CN111414780A (en) * | 2019-01-04 | 2020-07-14 | 卓望数码技术（深圳）有限公司 | Sitting posture real-time intelligent distinguishing method, system, equipment and storage medium |
| CN111967439A (en) * | 2020-09-03 | 2020-11-20 | Tcl通讯（宁波）有限公司 | Sitting posture identification method and device, terminal equipment and storage medium |
| CN114038016A (en) * | 2021-11-16 | 2022-02-11 | 平安普惠企业管理有限公司 | Sitting posture detection method, device, equipment and storage medium |
-
2022
- 2022-05-31 CN CN202210607019.7A patent/CN115035547A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190251341A1 (en) * | 2017-12-08 | 2019-08-15 | Huawei Technologies Co., Ltd. | Skeleton Posture Determining Method and Apparatus, and Computer Readable Storage Medium |
| CN111414780A (en) * | 2019-01-04 | 2020-07-14 | 卓望数码技术（深圳）有限公司 | Sitting posture real-time intelligent distinguishing method, system, equipment and storage medium |
| CN111967439A (en) * | 2020-09-03 | 2020-11-20 | Tcl通讯（宁波）有限公司 | Sitting posture identification method and device, terminal equipment and storage medium |
| CN114038016A (en) * | 2021-11-16 | 2022-02-11 | 平安普惠企业管理有限公司 | Sitting posture detection method, device, equipment and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115240231A (en) * | 2022-09-22 | 2022-10-25 | 珠海翔翼航空技术有限公司 | Image recognition-based sitting posture detection and adjustment method for full-motion simulator |
| CN115240231B (en) * | 2022-09-22 | 2022-12-06 | 珠海翔翼航空技术有限公司 | Image recognition-based sitting posture detection and adjustment method for full-motion simulator |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111832383B (en) | Training method of gesture key point recognition model, gesture recognition method and device | |
| US11423699B2 (en) | Action recognition method and apparatus and electronic equipment | |
| JP5772821B2 (en) | Facial feature point position correction apparatus, face feature point position correction method, and face feature point position correction program | |
| JP7197971B2 (en) | Information processing device, control method and program for information processing device | |
| CN111178280A (en) | Human body sitting posture identification method, device, equipment and storage medium | |
| US9390310B2 (en) | Striped pattern image examination support device, striped pattern image examination support method and program | |
| CN105139000B (en) | A kind of face identification method and device removing glasses trace | |
| CN112651389B (en) | Correction model training, correction and recognition method and device for non-emmetropic iris image | |
| US11176673B2 (en) | Method and device for acquiring figure parameters of a user | |
| CN111523476A (en) | Mask wearing identification method, device, equipment and readable storage medium | |
| CN112712053A (en) | Sitting posture information generation method and device, terminal equipment and storage medium | |
| CN106843141A (en) | Numerical control device | |
| CN110084219B (en) | Interface interaction method and device | |
| CN111160088A (en) | VR (virtual reality) somatosensory data detection method and device, computer equipment and storage medium | |
| CN109740511B (en) | Facial expression matching method, device, equipment and storage medium | |
| CN115035547A (en) | Sitting posture detection method, device, equipment and computer storage medium | |
| CN111108515A (en) | Picture target point correcting method, device and equipment and storage medium | |
| EP4040386A1 (en) | Motion recognition method, motion recognition program, and information processing device | |
| CN114998931A (en) | Bad habit monitoring method, device, equipment and program product in learning state | |
| CN110443147A (en) | A kind of sitting posture recognition methods, system and storage medium | |
| CN114038016A (en) | Sitting posture detection method, device, equipment and storage medium | |
| CN116978127A (en) | Body-building posture correction method, device, equipment and medium based on posture estimation | |
| EP4227894A1 (en) | Posture detection device, posture detection method, and sleeping posture determination method | |
| KR101787255B1 (en) | Facial expression recognition method based on ratio of facial ladnmark's distance | |
| JP7103506B2 (en) | Information presentation method, information presentation device and program |
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 |