CN115331776A - Static motion data statistical method, device, equipment and medium - Google Patents
Static motion data statistical method, device, equipment and medium Download PDFInfo
- Publication number
- CN115331776A CN115331776A CN202210951399.6A CN202210951399A CN115331776A CN 115331776 A CN115331776 A CN 115331776A CN 202210951399 A CN202210951399 A CN 202210951399A CN 115331776 A CN115331776 A CN 115331776A
- Authority
- CN
- China
- Prior art keywords
- action
- detection period
- preset
- detection
- 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
- 230000033001 locomotion Effects 0.000 title claims abstract description 82
- 230000003068 static effect Effects 0.000 title claims abstract description 41
- 238000007619 statistical method Methods 0.000 title abstract description 4
- 238000001514 detection method Methods 0.000 claims abstract description 183
- 230000009471 action Effects 0.000 claims abstract description 119
- 238000000034 method Methods 0.000 claims abstract description 74
- 210000000323 shoulder joint Anatomy 0.000 claims description 34
- 210000000988 bone and bone Anatomy 0.000 claims description 22
- 210000004394 hip joint Anatomy 0.000 claims description 21
- 210000002310 elbow joint Anatomy 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 17
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 210000000544 articulatio talocruralis Anatomy 0.000 claims description 12
- 210000001624 hip Anatomy 0.000 claims description 12
- 210000000629 knee joint Anatomy 0.000 claims description 11
- 238000005452 bending Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 7
- 238000002360 preparation method Methods 0.000 claims description 6
- 210000003857 wrist joint Anatomy 0.000 claims description 6
- 241001125929 Trisopterus luscus Species 0.000 claims description 4
- 210000001217 buttock Anatomy 0.000 claims description 4
- 230000007257 malfunction Effects 0.000 claims description 2
- 206010000117 Abnormal behaviour Diseases 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 11
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 19
- 238000004590 computer program Methods 0.000 description 11
- 238000012545 processing Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 230000036544 posture Effects 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 5
- 235000019577 caloric intake Nutrition 0.000 description 4
- 230000006378 damage Effects 0.000 description 4
- 230000008093 supporting effect Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000968 medical method and process Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 210000002784 stomach Anatomy 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/30—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- 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
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Physical Education & Sports Medicine (AREA)
- Epidemiology (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Public Health (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses a static motion data statistical method, a device, equipment and a medium, wherein the method comprises the following steps: acquiring a video stream of a target to be detected; determining a plurality of skeleton nodes of the target to be detected in each frame of image in the video stream based on a MoveNet model, and connecting the skeleton nodes according to a preset mode to obtain a detection heat map; determining the effectiveness of each detection period in the video stream according to a preset action judgment strategy based on the detection heat map; and carrying out data statistics on the static motion. According to the method, the key point information of the human skeleton in motion can be automatically identified through an intelligent detection technology, the automatic statistics of static motion data is realized, the identification accuracy is higher, the counting is not missed or mistaken in the counting process, and the role of a coach can be replaced to a certain extent; each action has feedback, so that the movement is more interesting, and a user can be prompted to complete the action more standard; the use experience of the user is obviously improved.
Description
Technical Field
The application relates to the technical field of digital medical treatment, in particular to a static motion data statistical method, a device, equipment and a medium.
Background
People pay more and more attention to health, and some static exercises are favored by many people, such as flat supports, yoga and the like. But scientific timing of static motion lacks an effective tool. At present, a plurality of fitness applications exist on the network, such as front-end APP (application), and the applications can explain and demonstrate action key points in forms of characters, videos and the like, so that a user can exercise at home, and the time and money for going to a gymnasium are saved. However, for many novices, although learning the standard actions, the novices cannot know whether the actions are standard or not, and a coach does not correct the errors nearby, so that the exercise effect is greatly reduced, and even the exercise injury is generated.
In addition, when the training counter is applied to execution, a user is defaulted to move synchronously, but whether the user really does not know whether the user really does move or not is unknown, after the training counter is over, the exercise score is automatically generated, the calorie is calculated, the exercise ranking and other information are generated, but the user probably does not participate in the exercise at all, the supervision function cannot be achieved, ranking information is not credible due to various cheating means, and the enthusiasm of the user is eliminated.
At present, some applications provide courses for Artificial Intelligence (AI) fitness, movement counting can be performed on certain actions, but the accuracy is poor, the phenomenon of false recognition is easy to occur, sometimes, a user only shakes a little or does other things to count effective times, and the experience is very poor. And if the user's action is not standard, can count, can not remind the user wrong information, the user probably goes to do a wrong action for a long time, causes the motion damage, is particularly not suitable for like the static timing action of flat panel support, and relative to other actions, the nonstandard flat panel support action can cause bigger damage. Therefore, a method for effectively counting the static motion data of the image plate support is needed.
It should be noted that the above description is only a background example and does not necessarily become a prior art.
Disclosure of Invention
In view of the above problems, embodiments of the present application provide a method, an apparatus, a device, and a medium for data statistics of static motion, where the method accurately detects a plurality of bone nodes of an object to be detected in each frame image in a video stream based on a MoveNet model, and detects validity of each detection period in the video stream according to a preset action judgment policy, so as to implement real-time, effective, and high-accuracy data statistics of static motion, thereby overcoming or at least partially overcoming the deficiencies of the prior art.
In a first aspect, an embodiment of the present application provides a data statistics method for static motion, where the method includes:
acquiring a video stream of a target to be detected;
determining a plurality of skeleton nodes of the target to be detected in each frame of image in the video stream based on a MoveNet model, and connecting the skeleton nodes according to a preset mode to obtain a detection heat map;
determining the effectiveness of each detection period in the video stream according to a preset action judgment strategy based on the detection heat map;
and carrying out data statistics on the static motion according to the effectiveness of each detection period.
In a second aspect, an embodiment of the present application further provides a flat plate-supported timing device, including:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a video stream of a target to be detected;
the gesture detection unit is used for determining a plurality of skeleton nodes of the target to be detected in each frame of image in the video stream based on a MoveNet model, and connecting the skeleton nodes according to a preset mode to obtain a detection heat map;
the effectiveness detection unit is used for determining the effectiveness of each detection period in the video stream according to a preset action judgment strategy based on the detection heat map;
and the statistical unit is used for carrying out data statistics on the static motion according to the effectiveness of each detection period.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform any of the methods described above.
In a fourth aspect, this application embodiment also provides a computer-readable storage medium storing one or more programs which, when executed by an electronic device including a plurality of application programs, cause the electronic device to perform any of the methods described above.
The embodiment of the application adopts at least one technical scheme which can achieve the following beneficial effects:
according to the method, through flexible application of the MoveNet model, a plurality of skeleton nodes of the target to be detected in each frame image in the video stream of the target to be detected are accurately detected, the skeleton nodes are connected according to a preset mode to obtain a detection heat map, the effectiveness of each detection period in the video stream is determined according to a preset action judgment strategy based on the detection heat map, and finally, the data of static motion are counted according to the effectiveness of each detection period. According to the method, the key point information of the human skeleton in motion can be automatically identified through an intelligent detection technology, the automatic statistics of the data of static motion is realized, the identification accuracy is higher, the counting is not missed or mistaken in the counting process, and the role of a coach can be replaced to a certain extent; each action has feedback, so that the movement is more interesting, and the user can be prompted to complete the action more normally; the use experience of the user is obviously improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 shows a schematic diagram of a flow of a static motion data statistics method according to an embodiment of the present application;
FIG. 2 shows a schematic diagram of an interface of a client according to an embodiment of the present application;
FIG. 3 shows a flow diagram of a method for data statistics of static motion according to another embodiment of the present application;
figure 4 shows a schematic structural diagram of a static motion statistics apparatus according to another embodiment of the present application,
fig. 5 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. 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 application.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Digital medical treatment refers to the whole medical process of digitization and informatization by using an information technology, generally comprises informatization of a hospital diagnosis and treatment process, also comprises informatization of regional medical coordination, public health, medical and health supervision and medical insurance management, and relates to comprehensive application of technologies such as electronic equipment, computer software, internet and the like. Digital and intelligent fitness also belongs to a branch of digital medical treatment, and with the arrival of the intelligent era, the intelligent transformation of various fitness equipment and fitness equipment becomes the current hot topic.
For this reason, the present application provides a data statistics method for static motion, and fig. 1 shows a flowchart of the data statistics method for static motion according to an embodiment of the present application, and as can be seen from fig. 1, the present application at least includes steps S110 to S140:
step S110: and acquiring a video stream of the target to be detected.
The method can logically form an application program APP of the client, a small degree and the like, and is loaded on electronic equipment of the client, such as a mobile phone, a tablet personal computer and the like. It should be noted that, for convenience of description, the following description will be made by taking static motion as the flat plate support, but the present application is not limited to the flat plate support, and the present application is applicable to all static motion.
In some embodiments of the present application, the method of the present application may be performed directly at the client; in other embodiments, the client may collect a video stream of the target to be detected, upload the video stream to the server, perform tablet-supported timing by the server, and return a result to the client.
After the user opens the corresponding interface, the flat plate can be supported and moved according to the prompt information of the interface. In an actual scenario, a camera right may be applied through a method provided by a client, and after the right is successfully obtained, a video stream may be acquired, in some embodiments, a video stream may be monitored through a navigator, media devices, etc., the navigator, media devices, etc. serve to prompt a user to give permission to use a media input, and the media input may generate a media stream, which includes a track of a requested media type, and the stream may include a video track (from a hardware or virtual video source, such as a camera, a video acquisition device, a screen sharing service, etc.), an audio track (also from a hardware or virtual audio source, such as a microphone, an a/D converter, etc.), and possibly other track types.
After obtaining the video stream, imaging may be performed according to a preset interval, and each imaging may form one frame of image in the video stream, specifically, in some embodiments, in order to further improve the detection accuracy, imaging may be drawn once every 25 milliseconds by a canvas (an imaging tool), that is, 400 frames of image are included in each second of video stream.
The acquisition of the video stream is usually real-time, i.e. the method is performed in synchronization with the movements of the user. As shown in fig. 2, fig. 2 is a schematic diagram of an interface of a client according to an embodiment of the present application, and it can be seen from the diagram that, in this embodiment, a user can perform a sideways motion relative to a mobile phone, that is, perform a tablet supporting motion in a parallel posture with the mobile phone.
In addition, in some embodiments of the application, before the mobile phone is placed horizontally, the mobile phone can be placed vertically, and ready detection is performed on a target to be detected to determine that the user starts to perform ready movement, that is, a ready check is performed before the flat panel support movement starts, at this time, whether the user opens the hands-raising position with the same width as the shoulder and reserved at the top of the head can be checked, and if the ready requirement is not met, voice prompt is performed; if a ready request is reached, the user may be prompted to lay the phone across to begin movement. The method of readiness detection is the same as the validity detection method described below.
Step S120: determining a plurality of skeleton nodes of the target to be detected in each frame image in the video stream based on a MoveNet model, and connecting the plurality of skeleton nodes according to a preset mode to obtain a detection heat map.
The MoveNet model (a human body posture detection model, a unified Chinese name in the industry) is an open source artificial intelligence tool which is introduced by Google and can detect human body postures, and a corresponding Application Program Interface (API) is provided. The model can run on a notebook computer, a tablet personal computer or a mobile phone at the speed of 50+ fps. The MoveNet model can detect at most 17 key bone nodes of a human body, including a wrist joint, a shoulder joint, a hip joint, a knee joint, an ankle joint and the like, quickly and accurately, and the key nodes are referred to as bone nodes in the application.
The method includes processing a video stream frame by frame, or performing downsampling according to a preset interval, for example, sampling every 3 frames, and performing processing, where the downsampling may be selected according to computing power. It should be noted that due to the nature of the plate supporting action, when detecting the bone nodes, 17 bone nodes are not usually detected each time, and only the required bone nodes need to be detected according to the pose of the person.
The bone joints are connected together by a point diagram according to the detection requirement, the points are positioned at the coordinates of each bone node, the connecting lines required by the detection can be represented by straight lines, and the obtained diagram is called a detection heat map. It should be noted that, for some unnecessary connection lines, connection may be connected or not, and connection may be used as a reference; if the detection result is influenced by too many connecting lines, the connecting lines can be disconnected, and the application is not limited to this.
Step S130: and determining the effectiveness of each detection period in the video stream according to a preset action judgment strategy based on the detection heat map.
After the detection heat map is obtained, the effectiveness of the action made by the target to be detected in the video stream can be detected according to a preset action judgment strategy. Specifically, the detection may be performed according to a detection period, for example, 1s is set as one detection period, and the validity of each detection period in the acquired video stream is detected in time sequence with reference to the initial time.
The specific action judgment strategy can be set according to the detection precision and the hardware computing power, if a scoring system can be adopted, a basic score is set for each detection period, for example, 100 scores are set, in the detection period, if one or more frames of images exist, the action of the target to be detected does not meet the set standard, the basic score is deducted, and when the final score is less than a preset threshold value, the detection period can be determined to be invalid; otherwise, the detection period may be determined to be valid.
Taking a detection period as an example, if the detection period starts from the first frame, if the first frame meets the set standard, the backward detection is continued, and if each frame meets the set standard in the detection period, the detection period is determined to be valid; if the first frame does not meet the set standard, the user can directly judge and determine that the detection period is invalid, wait for the next detection period to come, and detect again, and cannot continue to detect from a certain frame in the detection period; if the non-first frame does not meet the set standard and the score of the detection period is less than the preset threshold value due to the deduction in the detection process, the detection period can be determined to be invalid, and the next detection period is waited to come and then the detection is carried out again.
It should be noted that the detection period is not limited to 1s, and other values, such as 2s,3s, etc., may be set according to the detection accuracy.
In some embodiments of the present application, if the validity of a certain detection period is invalid, a voice prompt message is issued, the voice prompt message may inform the user that the current action is not standard, please adjust the posture, and a movement correction suggestion, such as do not collapse waist, may be further included in the voice prompt message.
Step S140: and carrying out data statistics on the static motion according to the effectiveness of each detection period.
Finally, according to the validity of each detection period, performing data statistics on the static motion, such as timing the flat panel support, specifically, if the validity of one detection period is valid, timing the detection period, and accumulating the detection period in the timing result, if the validity of one detection period is invalid, not timing the detection period, that is, not accumulating the detection period in the timing result.
In addition, the whole timing of the flat panel support is performed based on the start and end of the user confirmation, and if one or several detection cycles are invalid, the whole timing is not affected, that is, the timing is not re-timed in the middle. For example, user 12:00 starts the plate supporting movement and enters a timing flow, taking 1s as a detection period, and in 12:05 and 12:07 the detection cycles are all invalid, 12:10, finishing the movement, and the timing result is 8min, during which only 12:05 and 12:07, instead of from 12:05 or 12:07 to count again.
The data statistics is not limited to timing, and the calorie consumed by the user, the exercise completion level and the like can be counted.
As can be seen from the method shown in fig. 1, according to the method, a MoveNet model is flexibly applied, a plurality of bone nodes of the target to be detected in each frame image in the video stream of the target to be detected are accurately detected, the plurality of bone nodes are connected according to a preset mode to obtain a detection heat map, the effectiveness of each detection period in the video stream is determined according to a preset action judgment strategy based on the detection heat map, and finally, the data of the static motion are counted according to the effectiveness of each detection period. According to the method, the key point information of the human skeleton in motion can be automatically identified through an intelligent detection technology, the automatic statistics of static motion data is realized, the identification accuracy is higher, the counting is not missed or missed in the counting process, and the role of a coach can be replaced to a certain extent; each action has feedback, so that the movement is more interesting, and a user can be prompted to complete the action more standard; the use experience of the user is obviously improved.
In some embodiments of the present application, before performing timing, it is further detected whether a user is ready for a tablet support operation, and specifically, before the step of determining validity of each detection period in the video stream according to a preset operation judgment policy based on the detection heatmap, the method further includes: according to the detection heat map, if the bending degree of a first connecting line formed by shoulder joints, hip joints, knee joints and ankle joints on the same side in the plurality of skeleton nodes is smaller than a first threshold value, the included angle between a second connecting line formed by the shoulder joints and the hip joints and a horizontal line is smaller than a first angle threshold value, and the included angle between a third connecting line formed by elbow joints and the shoulder joints in the plurality of skeleton nodes and the included angle between the second connecting line and the second connecting line is within a first angle threshold value range, determining that the to-be-detected target is successfully prepared, and starting to execute the step of determining the effectiveness of each detection period in the video stream according to a preset action judgment strategy based on the detection heat map; otherwise, determining that the preparation of the target to be detected fails, and sending voice prompt information, wherein the voice prompt information comprises action correction opinions.
When the flat plate supports the action standard, the shoulder joint, the hip joint, the knee joint and the ankle joint of a person are almost on the same straight line, so that a bending threshold value can be set, which is denoted as a first threshold value, and whether the trunk of the target to be detected is straight or not is determined by detecting whether the bending of a first connecting line formed by the shoulder joint, the hip joint, the knee joint and the ankle joint is smaller than the first threshold value. The bending degree can be understood as the bending degree of the target to be detected on the length when the target to be detected is lying on the stomach (taking the target to lie on the ground as an example), and when the bending degree of the first connecting line is smaller than a first threshold value, the shoulder joint, the hip joint, the knee joint and the ankle joint of the target to be detected can be determined to be almost on the same straight line, namely, the trunk of the target to be detected is straight.
Meanwhile, whether the trunk is approximately parallel to the ground or not can be detected, namely whether an included angle between a second connecting line formed by the shoulder joint and the hip joint and a horizontal line (a Y axis of the mobile phone) is smaller than a first angle threshold or not is detected, if the first angle threshold is set to be 10 degrees, when the included angle between the first connecting line and the horizontal line is smaller than the first angle threshold, the trunk is considered to be approximately parallel to the ground.
Meanwhile, whether an included angle between the upper arm and the trunk is kept close to 90 degrees or not can be detected, that is, whether an included angle between a third connecting line formed by the elbow joint and the shoulder joint in the plurality of bone nodes and the second connecting line is in a first angle threshold range or not is detected, for example, the first angle threshold range is 85-95 degrees, preferably 89-91 degrees, and more preferably 90 degrees. When the included angle between the third connecting line and the second connecting line is within the range of the first angle threshold, whether the upper arm and the trunk keep a proper included angle or not can be determined.
When the trunk of the target to be detected is detected to be nearly straight, the trunk is detected to be approximately parallel to the ground, and the upper arm and the trunk are detected to keep an included angle close to 90 degrees, the target to be detected can be determined to be successfully prepared, and at the moment, a user can be reminded to start exercise timing; if the action of the user does not meet one or more of the conditions, determining that the preparation of the target to be detected fails, and sending voice prompt information at the moment, wherein the voice prompt information comprises action correction opinions, namely reminding the user of unsuccessful preparation and asking for action adjustment, and specifically indicating where the target to be detected has problems.
In some embodiments of the application, in the method, the determining, according to a preset action judgment policy, the validity of each detection period in the video stream based on the detection heatmap includes: according to time sequence, dividing the video stream into a plurality of detection periods, wherein each detection period comprises a plurality of frames of continuous images; if the first frame image in a detection period meets the action effectiveness requirement according to a preset action judgment strategy, giving a basic score to the detection period as an initial score; determining the action score of the detection period according to the detected nonstandard action in other frame images in the detection period; updating the initial score according to the action score to obtain an actual score of the detection period; wherein the non-standard action comprises: pout, collapse waist and make mistakes; if the actual score is larger than or equal to a preset score threshold value, determining the validity of the detection period as valid; otherwise, the validity of the detection period is determined to be invalid.
When detecting the effectiveness of each detection period in a video stream, firstly, the video stream is divided into a plurality of detection periods according to a time sequence, each detection period comprises a plurality of continuous images, it needs to be noted that the process is real-time, the division can be performed according to the current time length, for example, each detection period is 1s by taking the detection starting time as a reference, when the distance from the detection starting time reaches 1s, a detection period is formed, and under the condition that the imaging frequency is not changed, each detection period has the same number of continuous multi-image images.
Because the flat support is a static timing action, the user keeps the same posture (in an ideal state) in the whole movement process, and whether the user does the flat support movement or not and whether the movement is standard or not need to be continuously detected. In the application, the detection can be performed according to one detection period, taking one detection period as an example, firstly determining whether a first frame image in the detection period meets an action validity requirement in an action judgment strategy, and if none of the first frame images meets the action validity requirement in the action judgment strategy, directly determining that the validity of the detection period is invalid; if yes, giving a basic score, such as 100 scores, to the detection period, and continuing the subsequent detection steps; specifically, it is continuously detected whether the other frame images except the first frame include non-standard motion in the detection period, and if not, no motion score is generated, where the motion score is usually negative, and the actual score (final score) of the detection period is the basic score, for example, 100 points; and if the rest frame images contain one or more times of nonstandard actions, generating action scores, namely deduction items, according to the specific content of the nonstandard actions, calculating the actual score of the detection period, and adding the action score (negative) to the basic score to obtain the actual score of the detection period, wherein the actual score is lower than the basic score, and the smaller the actual score is, the larger the difference between the action of the target to be detected and the standard action is. If the actual score of one detection period is greater than or equal to a preset score threshold, if so, 60 points are used, and the validity of the detection period is determined to be valid; otherwise, the validity of the detection period is determined to be invalid.
For whether the first frame image meets the action validity requirement in the action judgment strategy, reference may be made to the above-mentioned standard for detecting whether the preparation of the target to be detected is successful, which is not described in detail herein.
Such non-standard actions include, but are not limited to: the small irregular movements of pounding buttocks, collapsing waist and the like are collectively referred to as the miss movements in the present application.
If a pout of buttocks is detected, the action is divided into-20 points; if the waist collapse is detected, the action score is-100, because the waist collapse is a serious error in the flat plate supporting movement and is more likely to cause movement damage than other actions, the absolute value of the action score generated by the item is larger; if a faulty action is detected, an action score of-10 is generated. The abnormal operation and the operation score may be set according to the detection accuracy and the standard, and the present application is not limited thereto.
In order to facilitate the user to know whether the user action is standard or not, when the user action is standard, the identified key points can be connected by a green broken line, when the user action is not standard, the nonstandard parts can be connected by a red broken line, and meanwhile, the user is prompted by voice to correct the nonstandard action, so that the user can know the own motion state at a glance through a visual interface through the division of different color lines, and the experience and the feeling of the user are further improved.
In some embodiments of the present application, in the above method, it may be referred to that, taking a direction perpendicular to a horizontal line as positive, if it is determined that an opening direction of a first obtuse included angle formed by a fourth connecting line formed by a hip joint and a knee joint located on the same side among the plurality of bone nodes and a fifth connecting line formed by the hip joint and the shoulder joint located on the same side is negative, and the first obtuse included angle is smaller than a second preset angle threshold, it is determined that the abnormal motion is a false operation; and if the opening direction of the first obtuse included angle is determined to be positive and the first obtuse included angle is smaller than a third preset angle threshold value, determining that the nonstandard action is a false action.
If the motion standard of the flat plate support is in an ideal state, the shoulder joint, the hip joint and the knee joint which are positioned on the same side are positioned on the same straight line (the formed angle is 180 degrees), so that when the hip-up motion is detected, the opening direction and the size of a first obtuse included angle formed by taking the hip joint as a vertex, a fourth connecting line formed by the shoulder joint and the hip joint and a fifth connecting line formed by the hip joint and the shoulder joint as sides can be judged, if the opening direction of the first obtuse included angle is negative (vertical downward), and the first obtuse included angle is smaller than a second preset angle threshold value, if 140 degrees, the object to be detected has slight hip-up motion, and the slight hip-up motion is marked as a wrong motion.
Similarly, if the opening direction of the first obtuse included angle is positive (vertical upward), and the first obtuse included angle is smaller than a third preset angle threshold, if 155 °, it indicates that a slight waist-collapsing action occurs on the target to be detected, and the slight waist-collapsing action is recorded as a false action.
In some embodiments of the present application, when detecting whether the target to be detected has a waist-collapsing or a hip-pursing, reference may also be made to the above method, but the standard setting for the waist-collapsing or the hip-pursing is more strict, specifically, if the opening direction of the first obtuse included angle is negative, and the first obtuse included angle is smaller than a fourth preset angle threshold, where the fourth preset angle threshold is smaller than the second preset angle threshold, the nonstandard movement is determined as the hip-pursing; and if the opening direction of the first obtuse included angle is positive, and the first obtuse included angle is smaller than a fifth preset angle threshold value, wherein the fifth preset angle threshold value is larger than the third preset angle threshold value, determining the nonstandard movement as waist collapse.
If the opening direction of the first obtuse included angle is negative (towards the vertical downward direction), and the first obtuse included angle is smaller than a fourth preset angle threshold value, if the opening direction of the first obtuse included angle is negative, and if the opening direction of the first obtuse included angle is smaller than the fourth preset angle threshold value, the condition that the pounding action occurs on the hip of the target to be detected is indicated as 145 degrees.
Similarly, if the opening direction of the first obtuse included angle is positive (towards the direction vertical to the upward direction), and the first obtuse included angle is smaller than a fifth preset angle threshold, if 165 °, it indicates that the waist collapse action occurs on the target to be detected.
In some embodiments of the present application, in the above method, when detecting whether an abnormal motion exists in the target to be detected, it may be determined whether the position between the arm and the trunk is standard by obtaining coordinate points of the ankle joint, the shoulder joint, and the elbow joint, and calculating an included angle between the ankle joint, the shoulder joint, and the elbow joint, that is, an included angle in a downward opening direction formed by a sixth connecting line formed by the ankle joint and the shoulder joint located on the same side among the plurality of bone nodes and a seventh connecting line formed by the shoulder joint and the elbow joint, where if the included angle is greater than a sixth preset angle threshold, for example, 140 ° (a maximum error between an included angle between the trunk and the arm and 90 °) or less than a seventh preset angle threshold, for example, if the included angle is greater than the sixth preset angle threshold, it is determined that the abnormal motion is an abnormal motion (a maximum error between an included angle between the trunk and the arm and 90 °).
In some embodiments of the present application, in the above method, when detecting whether an abnormal motion exists in the target to be detected, an included angle formed by the elbow joint, the wrist joint and the shoulder joint may be further calculated by obtaining coordinates of the elbow joint, the wrist joint and the shoulder joint, that is, an included angle (an included angle smaller than 180 °) formed by an eighth connecting line formed by the elbow joint and the wrist joint located on the same side among the plurality of bone nodes and a ninth connecting line formed by the elbow joint and the shoulder joint, and if the included angle is greater than a sixth preset angle threshold value, for example, 140 ° (a maximum error between an included angle of a trunk and an arm and 90 °) or smaller than a seventh preset angle threshold value, for example, 40 ° (a maximum error between an included angle of the trunk and the arm and 90 °), it is determined that the abnormal motion is an abnormal operation failure.
In some embodiments of the present application, in the above method, the grade classification and the calorie consumption of each flat panel support may be further performed, such as determining a composite score, grade and calorie consumption of the flat panel supports according to the timing result and the final scores of the detection periods in the video stream.
Specifically, the comprehensive score of the current flat plate support is determined according to the actual score of each detection period, further, the corresponding difficulty coefficient is determined according to the scoring result, and then the information such as the grade and calorie consumption of the current flat plate support is determined according to the comprehensive score and the difficulty system of the current flat plate support.
If the timing result is 1-20 seconds, the current comprehensive score (100-10) is 1.0 of the difficulty coefficient, and therefore the grade is determined as follows: GT (rating in percent); the timing result is 21-50 seconds, the current comprehensive score (100-10) is the difficulty coefficient is 1.6, and the rating is as follows: GT (rating in percent); the timing result is 51-100 seconds, and the current comprehensive score is (100-10) × difficulty coefficient 2, so that the grade is determined as follows: GT (rating in percent); the timing result is more than 100 seconds, and the current score is (100-10) and the difficulty coefficient is 3, so that the grade is determined as follows: GT (rating in percent). The calculation of the comprehensive score, the grade and the calorie consumption of the flat plate support can be set by self, the application is not limited, the above example is only an exemplary illustration, the evaluation mode not only takes the number of actions or the exercise duration as a scoring standard, but also can obtain higher scores only when the actions are more standard and more in number, and the actual exercise effect can be better reflected according to the score ranking, so that the exercise is more interesting, and the enthusiasm of the user is invoked.
Fig. 3 shows a flow chart of a method for timing a plate support according to another embodiment of the present application, and as can be seen from fig. 3, the present embodiment includes:
acquiring a video stream of a target to be detected; and determining a plurality of skeleton nodes of the target to be detected in each frame image in the video stream based on a MoveNet model, and connecting the skeleton nodes according to a preset mode to obtain a detection heat map.
Determining whether the first frame image of a detection period meets the action validity requirement, and if not, determining that the validity of the detection period is invalid; if yes, giving a basic score to the detection period; determining whether other frame images of the detection period have nonstandard actions, and if not, determining that the validity of the detection period is valid; if yes, determining the action score of the detection period according to the detected nonstandard action, and adding the basic score and the action score to obtain the actual score of the detection period; determining whether the actual score of the detection period is greater than or equal to a preset score threshold value, and if so, determining that the validity of the detection period is valid; if not, determining that the validity of the detection period is invalid.
And determining the timing result of the flat plate support according to the effectiveness of each detection period.
Fig. 4 is a schematic structural diagram of a static motion statistics device according to another embodiment of the present application, and as can be seen from fig. 4, the static motion statistics device 400 includes:
an obtaining unit 410, configured to obtain a video stream of a target to be detected;
the posture detection unit 420 is configured to determine a plurality of bone nodes of the target to be detected in each frame image in the video stream based on a MoveNet model, and connect the plurality of bone nodes according to a preset mode to obtain a detection heat map;
an effectiveness detection unit 430, configured to determine, based on the detection heatmap, effectiveness of each detection period in the video stream according to a preset action judgment policy;
and a timing unit 440, configured to perform data statistics on the static motion according to the validity of each detection period.
In some embodiments of the present application, in the above apparatus, the timing unit 440 is further configured to issue a voice prompt message if the validity of a certain detection period is invalid, where the voice prompt message includes the action correction suggestion.
In some embodiments of the present application, in the above apparatus, the static motion is a flat plate support; a validity detecting unit 430, configured to, before the step of determining validity of each detection period in the video stream according to a preset action judgment policy based on the detection heatmap, further determine, according to the detection heatmap, that if it is determined that a curvature of a first connecting line formed by a shoulder joint, a hip joint, a knee joint, and an ankle joint on the same side in the plurality of bone nodes is smaller than a first preset threshold, an included angle between a horizontal line and a second connecting line formed by the shoulder joint and the hip joint is smaller than a first angle threshold, and an included angle between a third connecting line formed by an elbow joint and the shoulder joint in the plurality of bone nodes and the second connecting line is within a first angle threshold range, then determine that the object to be detected is successfully prepared, and start to execute the step of determining validity of each detection period in the video stream according to a preset action judgment policy based on the detection heatmap; otherwise, determining that the preparation of the target to be detected fails, and sending voice prompt information, wherein the voice prompt information comprises action correction opinions.
In some embodiments of the present application, in the above apparatus, the static motion is a plate support; a validity detection unit 430, configured to divide the video stream into a plurality of detection periods according to a time sequence, where each detection period includes multiple frames of consecutive images; if the first frame image in a detection period meets the action effectiveness requirement according to a preset action judgment strategy, giving a basic score to the detection period as an initial score; determining the action score of the detection period according to the detected nonstandard action in other frame images in the detection period; updating the initial score according to the action score to obtain an actual score of the detection period; wherein the nonstandard action comprises: pout, collapse waist and make mistakes; if the actual score is larger than or equal to a preset score threshold value, determining the validity of the detection period as valid; otherwise, determining the validity of the detection period as invalid; and if the first frame image in a detection period is determined not to meet the action validity requirement according to a preset action judgment strategy, directly determining that the validity of the detection period is invalid.
In some embodiments of the present application, in the above apparatus, the validity detecting unit 430 is configured to determine that the non-standard action is a false action if it is determined that an opening direction of a first obtuse included angle formed by a fourth connecting line formed by a hip joint and a knee joint located on the same side and a fifth connecting line formed by the hip joint and the shoulder joint located on the same side in the plurality of bone nodes is negative, and the first obtuse included angle is smaller than a second preset angle threshold; and if the opening direction of the first obtuse included angle is determined to be positive and the first obtuse included angle is smaller than a third preset angle threshold value, determining that the nonstandard action is a false action.
In some embodiments of the present application, in the above-mentioned apparatus, the validity detecting unit 430 is configured to determine the substandard action as a pursy of the buttocks if the opening direction of the first obtuse included angle is negative and the first obtuse included angle is smaller than a fourth preset angle threshold, wherein the fourth preset angle threshold is smaller than the second preset angle threshold; and if the opening direction of the first obtuse included angle is positive, and the first obtuse included angle is smaller than a fifth preset angle threshold value, wherein the fifth preset angle threshold value is larger than the third preset angle threshold value, determining the nonstandard movement as waist collapse.
In some embodiments of the present application, in the above apparatus, the validity detecting unit 430 is configured to determine that the abnormal action is a malfunction if an angle formed by a sixth connecting line formed by the ankle joint and the shoulder joint and a seventh connecting line formed by the shoulder joint and the elbow joint, which are located on the same side in the plurality of bone nodes, in a downward opening direction is greater than a sixth preset angle threshold value or smaller than a seventh preset angle threshold value; or if an included angle formed by an eighth connecting line formed by the wrist joints and the elbow joints and a ninth connecting line formed by the elbow joints and the shoulder joints which are positioned on the same side in the plurality of bone nodes is larger than a sixth preset angle threshold value or smaller than a seventh preset angle threshold value, determining that the abnormal action is a false failure action.
It should be noted that the above-mentioned timing device for panel support can implement the above-mentioned timing method for panel support one by one, and is not described herein again.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Referring to fig. 5, at a hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 5, but this does not indicate only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
The processor reads the corresponding computer program from the non-volatile memory into the memory and runs the computer program to form the flat panel supported timing device on the logic level. And the processor is used for executing the program stored in the memory and is specifically used for executing the method.
The method performed by the above-described flat panel-supported timing device as disclosed in the embodiment of fig. 4 of the present application may be implemented in or by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
The electronic device may further execute the method executed by the timing device supported by the tablet shown in fig. 4, and implement the functions of the timing device supported by the tablet in the embodiment shown in fig. 4, which are not described herein again in this embodiment of the present application.
Embodiments of the present application also provide a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which when executed by an electronic device including a plurality of application programs, enable the electronic device to perform the method performed by the tablet-supported timing apparatus in the embodiment shown in fig. 4, and are specifically configured to perform the foregoing method.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises that element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art to which the present application pertains. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A method for statistics of static motion, the method comprising:
acquiring a video stream of a target to be detected;
determining a plurality of skeleton nodes of the target to be detected in each frame of image in the video stream based on a MoveNet model, and connecting the skeleton nodes according to a preset mode to obtain a detection heat map;
determining the effectiveness of each detection period in the video stream according to a preset action judgment strategy based on the detection heat map;
and carrying out data statistics on the static motion according to the effectiveness of each detection period.
2. The method of claim 1, wherein if the validity of a certain detection period is invalid, then sending out a voice prompt message, wherein the voice prompt message comprises an action correction suggestion.
3. The method of claim 1, wherein the static motion is a plate support; before the step of determining the validity of each detection period in the video stream according to a preset action judgment policy based on the detection heatmap, the method further includes:
according to the detection heat map, if the bending degree of a first connecting line formed by a shoulder joint, a hip joint, a knee joint and an ankle joint which are positioned on the same side in the plurality of skeleton nodes is determined to be smaller than a first preset threshold value, an included angle between a second connecting line formed by the shoulder joint and the hip joint and a horizontal line is determined to be smaller than a first angle threshold value, and an included angle between a third connecting line formed by an elbow joint and the shoulder joint in the plurality of skeleton nodes and the second connecting line is determined to be within a first angle threshold value range, the target to be detected is determined to be prepared successfully, the detection heat map is executed, and the effectiveness of each detection period in the video stream is determined according to a preset action judgment strategy;
otherwise, determining that the preparation of the target to be detected fails, and sending voice prompt information, wherein the voice prompt information comprises action correction opinions.
4. The method of claim 1, wherein the static motion is a plate support; the determining the validity of each detection period in the video stream according to a preset action judgment strategy based on the detection heat map comprises the following steps:
according to time sequence, dividing the video stream into a plurality of detection periods, wherein each detection period comprises a plurality of frames of continuous images;
if the first frame image in a detection period meets the action effectiveness requirement according to a preset action judgment strategy, giving a basic score to the detection period as an initial score; determining an action score of the detection period according to the detected nonstandard actions in other frame images in the detection period; updating the initial score according to the action score to obtain an actual score of the detection period; wherein the non-standard action comprises: pounding buttocks, collapsing waist and doing mistakes;
if the actual score is larger than or equal to a preset score threshold value, determining the validity of the detection period to be valid; otherwise, determining the validity of the detection period as invalid;
and if the first frame image in a detection period is determined not to meet the action validity requirement according to a preset action judgment strategy, directly determining that the validity of the detection period is invalid.
5. The method of claim 4, wherein the abnormal behavior in the other frame images in the detection period is monitored according to the following method:
taking the direction vertical to a horizontal line as positive, if the opening direction of a first obtuse included angle formed by a fourth connecting line formed by hip joints and knee joints positioned on the same side in the plurality of skeleton nodes and a fifth connecting line formed by the hip joints and the shoulder joints positioned on the same side is determined to be negative, and the first obtuse included angle is smaller than a second preset angle threshold value, determining the nonstandard action as false action;
and if the opening direction of the first obtuse included angle is determined to be positive and the first obtuse included angle is smaller than a third preset angle threshold value, determining that the nonstandard action is a false action.
6. The method of claim 5, wherein nonstandard motion in other frame images in the detection period is monitored according to the following method: if the opening direction of the first obtuse included angle is negative, and the first obtuse included angle is smaller than a fourth preset angle threshold value, wherein the fourth preset angle threshold value is smaller than the second preset angle threshold value, the nonstandard action is determined as the pout;
and if the opening direction of the first obtuse included angle is positive, and the first obtuse included angle is smaller than a fifth preset angle threshold value, wherein the fifth preset angle threshold value is larger than the third preset angle threshold value, determining the nonstandard movement as waist collapse.
7. The method of claim 4, wherein nonstandard motion in other frame images in the detection period is monitored according to the following method:
if an opening direction downward included angle formed by a sixth connecting line formed by the ankle joints and the shoulder joints and a seventh connecting line formed by the shoulder joints and the elbow joints, which are positioned on the same side in the plurality of bone nodes, is larger than a sixth preset angle threshold value or smaller than a seventh preset angle threshold value, determining that the abnormal action is a malfunction action;
or,
and if an included angle formed by an eighth connecting line formed by the wrist joint and the elbow joint which are positioned on the same side in the plurality of skeleton nodes and a ninth connecting line formed by the elbow joint and the shoulder joint is larger than a sixth preset angle threshold value or smaller than a seventh preset angle threshold value, determining that the abnormal action is a false action.
8. A static motion statistics apparatus, the apparatus comprising:
the acquisition unit is used for acquiring a video stream of a target to be detected;
the gesture detection unit is used for determining a plurality of skeleton nodes of the target to be detected in each frame image in the video stream based on a MoveNet model, and connecting the skeleton nodes according to a preset mode to obtain a detection heat map;
the effectiveness detection unit is used for determining the effectiveness of each detection period in the video stream according to a preset action judgment strategy based on the detection heat map;
and the statistical unit is used for carrying out data statistics on the static motion according to the effectiveness of each detection period.
9. An electronic device, comprising:
a processor; and
a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method of claims 1 to 7.
10. A computer readable storage medium storing one or more programs which, when executed by an electronic device including a plurality of application programs, cause the electronic device to perform the method of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210951399.6A CN115331776A (en) | 2022-08-09 | 2022-08-09 | Static motion data statistical method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210951399.6A CN115331776A (en) | 2022-08-09 | 2022-08-09 | Static motion data statistical method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115331776A true CN115331776A (en) | 2022-11-11 |
Family
ID=83921448
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210951399.6A Pending CN115331776A (en) | 2022-08-09 | 2022-08-09 | Static motion data statistical method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115331776A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116309699A (en) * | 2023-02-01 | 2023-06-23 | 中国科学院自动化研究所 | Method, device and equipment for determining associated reaction degree of target object |
-
2022
- 2022-08-09 CN CN202210951399.6A patent/CN115331776A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116309699A (en) * | 2023-02-01 | 2023-06-23 | 中国科学院自动化研究所 | Method, device and equipment for determining associated reaction degree of target object |
| CN116309699B (en) * | 2023-02-01 | 2023-11-17 | 中国科学院自动化研究所 | Method, device and equipment for determining associated reaction degree of target object |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107551521B (en) | Fitness guidance method and device, intelligent equipment and storage medium | |
| CN105903157B (en) | Electronic coach realization method and system | |
| US20210248356A1 (en) | Method and apparatus for face recognition | |
| CN110472481B (en) | Sleeping gesture detection method, device and equipment | |
| CN111626137A (en) | Video-based motion evaluation method and device, computer equipment and storage medium | |
| CN115331776A (en) | Static motion data statistical method, device, equipment and medium | |
| CN111009297B (en) | Supervision method and device for medicine taking behaviors of user and intelligent robot | |
| CN111008542A (en) | Object concentration analysis method and device, electronic terminal and storage medium | |
| US20180067544A1 (en) | Indicating Method and Device for Correcting Failure of Motion-Sensing Interaction Tracking | |
| CN114220119B (en) | Human body posture detection method, terminal device and computer readable storage medium | |
| CN108289191B (en) | Image recognition method and device | |
| CN108108709B (en) | Identification method and device and computer storage medium | |
| JP2019016254A (en) | Method and system for evaluating user posture | |
| CN110639192B (en) | Step number calculation method and device for sports equipment and step number calculation method and device | |
| CN114513694A (en) | Scoring determination method and device, electronic equipment and storage medium | |
| CN112291480B (en) | Tracking focusing method, tracking focusing device, electronic device and readable storage medium | |
| CN111223549A (en) | Mobile end system and method for disease prevention based on posture correction | |
| CN110493618A (en) | Android method for intelligently controlling televisions and system based on USB3.0 interface | |
| CN113723306A (en) | Push-up detection method, device and computer readable medium | |
| JP2023072148A (en) | Information processing method, device and program | |
| CN111007902A (en) | Mother and infant motion monitoring system and method based on camera and smart home | |
| CN115331305A (en) | Open-close jump counting method, device, equipment and medium based on human body key points | |
| CN110058693B (en) | Data acquisition method and device, electronic equipment and storage medium | |
| US20240189710A1 (en) | Method of using physical movement for virtual gameplay control and associated apparatus | |
| CN109033986A (en) | The autonomous physical efficiency collecting training data method and apparatus of university student |
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 |