CN117292288A - Sports test method, system, electronic device, chip and storage medium - Google Patents
Sports test method, system, electronic device, chip and storage medium Download PDFInfo
- Publication number
- CN117292288A CN117292288A CN202311013757.XA CN202311013757A CN117292288A CN 117292288 A CN117292288 A CN 117292288A CN 202311013757 A CN202311013757 A CN 202311013757A CN 117292288 A CN117292288 A CN 117292288A
- Authority
- CN
- China
- Prior art keywords
- test
- pull
- video
- key
- sports
- 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
- 238000010998 test method Methods 0.000 title claims description 6
- 238000012360 testing method Methods 0.000 claims abstract description 132
- 230000033001 locomotion Effects 0.000 claims abstract description 90
- 230000009471 action Effects 0.000 claims abstract description 83
- 238000000034 method Methods 0.000 claims abstract description 80
- 238000009432 framing Methods 0.000 claims abstract description 13
- 230000008569 process Effects 0.000 claims description 33
- 210000000707 wrist Anatomy 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 14
- 230000003993 interaction Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 238000013031 physical testing Methods 0.000 claims 2
- 230000000386 athletic effect Effects 0.000 claims 1
- 238000001514 detection method Methods 0.000 description 17
- 238000004422 calculation algorithm Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 11
- 238000004891 communication Methods 0.000 description 8
- 239000000243 solution Substances 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 230000003321 amplification Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000003199 nucleic acid amplification method Methods 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 4
- 210000003423 ankle Anatomy 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 210000003127 knee Anatomy 0.000 description 3
- 239000000725 suspension Substances 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 210000004247 hand Anatomy 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000036544 posture Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012772 sequence design Methods 0.000 description 1
- 239000012085 test solution Substances 0.000 description 1
- 210000001364 upper extremity Anatomy 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Educational Technology (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Physical Education & Sports Medicine (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The embodiment of the application discloses a sports testing method, a sports testing system, electronic equipment, a chip and a computer readable storage medium, wherein the method comprises the following steps: carrying out framing treatment on the pull-up test video to obtain a plurality of video frames; extracting a plurality of key frames from the plurality of video frames based on the overhang and primer actions in one motion cycle; based on the plurality of key frames, judging whether pull-up actions in each movement period are standard or not, and counting the number of standard actions.
Description
Technical Field
The present application relates to the field of sports testing technologies, and in particular, to a sports testing method, a sports testing system, an electronic device, a chip, and a computer readable storage medium.
Background
Pull-up is a common index reflecting the muscle strength and endurance of the upper limbs of students, and the performance of the pull-up is related to the physical exercise degree, so that the pull-up is the most common sports in the middle and primary school sports teaching and the middle and primary school sports test. In daily gym class, students do not record the score when carrying out pull-up training, and the training condition of the students in daily class cannot be collected. Meanwhile, after a period of training, whether the student performance is improved or not is not supported by data. In the traditional pull-up item test, the results are registered through manual counting and notes and then are input into a system, so that the workload of a sports teacher is greatly increased. In addition, the method has more human factor doping, objective fairness is difficult to ensure, and the action process cannot be judged again in the follow-up process.
Disclosure of Invention
The embodiment of the application provides a sports testing method, a sports testing system, electronic equipment, a chip and a computer readable storage medium.
The technical scheme of the embodiment of the application is realized as follows:
in a first aspect, embodiments of the present application provide a sports testing method, including:
carrying out framing treatment on the pull-up test video to obtain a plurality of video frames;
extracting a plurality of key frames from the plurality of video frames based on the overhang and primer actions in one motion cycle;
based on the plurality of key frames, judging whether pull-up actions in each movement period are standard or not, and counting the number of standard actions.
In a second aspect, embodiments of the present application provide a sports testing system, comprising:
extraction unit: the method comprises the steps of carrying out framing processing on a pull-up test video to obtain a plurality of video frames; extracting a plurality of key frames from the plurality of video frames based on the overhang motion and the primer motion;
a statistics unit: for extracting a plurality of key frames from the plurality of video frames based on the overhang and primer actions in one motion cycle.
In a third aspect, the present application provides an electronic device, comprising: the sports test system comprises a processor and a memory, wherein the memory is used for storing a computer program, and the processor is used for calling and running the computer program stored in the memory to execute any sports test method provided by the embodiment of the application.
In a fourth aspect, the present application provides a chip comprising: and the processor is used for calling and running the computer program from the memory, so that the device provided with the chip executes any sports testing method provided by the embodiment of the application.
In a fifth aspect, the present application provides a computer-readable storage medium storing a computer program that causes a computer to perform any one of the sports testing methods provided by the embodiments of the present application.
The sports test method provided by the embodiment of the application can count the number of the standard actions in pull-up, and can also effectively analyze the action standardization degree of the testers; the method has the advantages that the calculation amount and the storage requirement on a computer can be greatly reduced, the movement process of a tester can be intuitively displayed, a teacher and the tester can find problems in the movement process of the tester conveniently, and further scientific guidance and correction are carried out; finally, the proposal can also carry out discriminant analysis on the action of the single frame of the tester according to the key frame extracted in the movement process, determine whether the action at the movement key moment is standard or not, and provide finer discriminant.
Drawings
Fig. 1 is a schematic diagram of an implementation flow of a sports testing method according to an embodiment of the present application;
FIG. 2 is a schematic illustration of a pendulous keyframe provided in an embodiment of the present application;
FIG. 3 is a schematic diagram of a key frame of a primer according to an embodiment of the present disclosure;
fig. 4 is a second schematic implementation flow chart of the sports testing method provided in the embodiment of the present application;
FIG. 5 is a schematic diagram of a sports testing system 500 according to an embodiment of the present disclosure;
FIG. 6 is a schematic diagram of a sports testing system 600 according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device provided in an embodiment of the present application;
fig. 8 is a schematic structural diagram of a chip provided in an embodiment of the present application.
Detailed Description
The following description of the technical solutions in the embodiments of the present application will be made with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
It should be noted that, in the embodiment of the present application, the term "and/or" is merely an association relationship describing the association object, which means that three relationships may exist, for example, a and/or B may be represented: a exists alone, A and B exist together, and B exists alone. In addition, in the embodiment of the present application, the character "/", generally indicates that the front-rear association object is an or relationship.
In the description of the embodiments of the present application, the term "corresponding" may indicate that there is a direct correspondence or an indirect correspondence between the two, or may indicate that there is an association between the two, or may indicate a relationship between the two and the indicated, configured, or the like.
In order to facilitate understanding of the technical solutions of the embodiments of the present application, the following description is given of related technologies of the embodiments of the present application, and the following related technologies may be optionally combined with the technical solutions of the embodiments of the present application as an alternative, which all belong to the protection scope of the embodiments of the present application.
The related art is mainly divided into two types for detecting pull-up movements: one is to analyze the pull-up actions of a tester by adopting traditional physical equipment, generally, a pressure sensor is used for judging whether the tester is on a pole or not, and then an infrared sensor is used for counting the pull-up actions of the tester; the other mode mainly adopts computer vision, adopts a camera to capture pull-up action videos of the testers, then analyzes the target gestures of the testers through a human body key point detection algorithm, and compares the target gestures with preset parameters, thereby realizing detection and analysis of the pull-up gesture standardization degree of the testers.
The above related art still has the following drawbacks:
traditional physical equipment is complex to build, poor in operation convenience, can only count the standard actions in pull-up, cannot effectively capture the nonstandard condition occurring in the motion process, and lacks effective guiding information.
The existing method adopting computer vision needs to analyze each frame of the video, has huge calculation amount and higher storage cost, and can seriously increase the time for displaying the result. The later stage is difficult to carry out efficient show to the whole motion process that draws on, is difficult to trace back the problem that takes place in the motion process, even can trace back, and the time cost that needs is also relatively great. Moreover, the testers have larger individual differences, the included angle of the corresponding vector of the target key part is not fully applicable as a preset parameter, and larger errors can exist.
The openpore key point detection method based on the related technology is from bottom to top, and shake or drift easily occurs in the motion process to influence the detection result. And the action state sequence can not fully show the details of the actions, the judgment of the nonstandard actions is not fine enough, the types of the nonstandard actions can not be determined, and guidance comments are provided for testers.
Fig. 1 is a schematic diagram of an implementation flow of a sports testing method provided in an embodiment of the present application, as shown in fig. 1, where the method includes the following steps:
step 101: and framing the pull-up test video to obtain a plurality of video frames.
Step 102: a plurality of key frames are extracted from the plurality of video frames based on the overhang and primer actions in one motion cycle.
In some alternative embodiments, the critical actions refer to actions that may characterize the course of a sports test item, which may be, for example, a draping state and a primer state when the sports test item is pull-up; when the sports test item is sit-up, the key actions may be a lying down state and an up state.
In some alternative embodiments, the extracting a plurality of key frames from the plurality of video frames based on the overhang and primer actions in one motion cycle includes:
collecting key points in each video frame of the plurality of video frames; the key points include at least one of: left wrist, right wrist, left elbow, right elbow, left shoulder, right shoulder, left hip, right hip and chin;
And extracting video frames of which the key points meet the first conditions of the overhang action and the first conditions of the primer action as the key frames.
Here, the key point is determined according to the key action, and by analyzing the motion track of the key point during motion, the first condition satisfied by the key point during the key action can be determined, and the video frame of the first condition satisfied by the key point is selected from the plurality of video frames as the key frame. Illustratively, when the sports test item is pull-up, the critical actions are overhang and pull-up, and from an action analysis of overhang and pull-up status, it may be determined that the critical points include at least one of: left wrist, right wrist, left elbow, right elbow, left shoulder, right shoulder, left hip, right hip and chin; the first condition of overhang includes: the average value of the heights of the left shoulder, the right shoulder, the left hip, the right hip and the chin in one movement period is a minimum value; the first conditions of the primer include: the average of the heights of the left shoulder, right shoulder, left hip, right hip and chin during one cycle of motion is the maximum.
In some alternative embodiments, keypoints in a video frame may be acquired by: based on the obtained video frame image sequence, detecting human body key points by taking the specific position of a tester captured by a human body tracking algorithm as a target and Vision Transformer +HrNet as a main network to obtain a position sequence corresponding to each key point. The algorithm introduces a local interesting map mechanism in the Head part on the basis of an open source HR-Former, and improves the output precision by matching with global semantic information. In the aspect of human body key point data amplification, the pixels and the space levels are used for transformation, and meanwhile, in order to cooperate with data amplification, unbiased data are used in a decoding stage, so that the decoding precision of the hematmap is improved. In some optional embodiments, the special data set of the sports test item is introduced to train the human body key point detection algorithm, so that the phenomenon of key point shaking and drifting in the motion process can be remarkably reduced.
Based on this, in an embodiment of the present application, the capturing the keypoints in each of the plurality of video frames includes:
acquiring key points in each of the plurality of video frames using a first model; the first model is a model taking Vision Transformer +HrNet as a main network.
The video consists of continuously-changing frame images, and the key frames are frames which can effectively represent the main content of the video in the continuous frame images. The automatic extraction of the video key frames is mainly used for reflecting the remarkable characteristics of each lens in the video, and a large amount of redundant information can be removed through the extraction of the key frames, so that the time spent on video retrieval is reduced. For a single-shot motion video, key frame extraction is mainly used for capturing key actions which can reflect the whole action process, so that a tester can find problems in the motion process, and effective guiding information is provided for correction and improvement of the actions.
Step 103: based on the plurality of key frames, judging whether pull-up actions in each movement period are standard or not, and counting the number of standard actions.
In some alternative embodiments, the determining whether pull-up motion in each motion cycle is standard based on the plurality of keyframes includes:
Determining that the key points meet the second condition of the overhang action or the key frames of the second condition of the primer action as standard action key frames;
when all key frames in a motion cycle are standard motion key frames, the pull-up motion in the motion cycle is determined to be standard motion.
And determining that the key action is a second condition met by the key points in the standard action, collecting the key point sequence of the testers in the key frame, and judging whether the second condition is met or not, so that whether the key action is the standard action or not can be judged. Illustratively, when the sports test item is pull-up, the critical action includes overhang and pull-up, and the second condition of overhang includes at least one of: the difference between the left wrist distance and the right shoulder distance accords with a preset difference range, and the included angle formed by the wrist, the elbow and the shoulder on the same side accords with a preset angle range; the second condition of the primer includes at least one of: the left and right wrists are as wide as the left and right shoulders and the lower jaw is higher than the cross bar. Here, the preset difference range may be 0, that is, the left and right wrists and the left and right shoulders are equal in width, or a certain range may be set according to actual situations, which is not limited in this application; the preset angle range may be 180 degrees, that is, the arm is straightened, or a certain range may be set according to the actual situation, that is, the elbow is allowed to bend, which is not limited in this application.
Referring to fig. 2 and 3, fig. 2 is a schematic diagram of a hanging key frame, fig. 3 is a schematic diagram of a key frame of a primer, and as shown in fig. 2 and 3, a is a left ankle, B is a left knee, C is a left hip, D is a left shoulder, E is a left elbow, F is a left wrist, G is a left and right ear, H is a right ankle, I is a right knee, J is a right hip, K is a right shoulder, L is a right elbow, M is a right wrist, and N is a chin; the distance 1 is the distance between the wrist and the cross bar, and the distance 2 is the distance between the shoulder and the cross bar in the state of the introduction; the positions of the left ear and the right ear can balance the shaking of the chin N, and the distance between the shoulder and the cross bar can identify whether the tester stretches the neck to pass the bar.
In some of the embodiments of the present invention in the alternative,
the motion period comprises adjacent primary overhang and primary primer;
the first condition of overhang includes: the average value of the heights of the left shoulder, the right shoulder, the left hip, the right hip and the chin in one movement period is a minimum value;
the first condition of the primer includes: the average of the heights of the left shoulder, the right shoulder, the left hip, the right hip and the chin in one movement period is the maximum;
the second condition of overhang includes at least one of: the difference between the left wrist distance and the right shoulder distance accords with a preset difference range, and the included angle formed by the wrist, the elbow and the shoulder on the same side accords with a preset angle range;
The second condition of the primer includes at least one of: the left and right wrists are as wide as the left and right shoulders and the lower jaw is higher than the cross bar.
In some embodiments, before framing the pull-up test video, the method further comprises:
collecting the pull-up test video in a test area;
identifying the identity information of the tester in the process of collecting the pull-up test video; prompting a tester to test in the effective area and/or prompting a non-tester to leave the test area; and broadcasting and/or displaying the number of the standard actions.
Referring to fig. 4, fig. 4 is a second schematic implementation flow chart of a sports testing method according to an embodiment of the present application, as shown in fig. 4, the method includes the following steps:
step 401: an image pickup apparatus is mounted.
The sports test field is selected, and the camera device is installed, wherein the camera device can be a camera, the camera can be a fixed camera or an adjustable camera, and the application is not limited to the sports test field. The visual content of the camera needs to effectively cover the sports test area, so that the situation that objects are blocked between the sports test area and the camera is ensured.
Step 402: the test area is set.
And setting a test area according to the image range of the camera through a mobile phone or a PAD and other terminal man-machine interaction units. According to the actual field situation, a plurality of test areas can be arranged in the effective visible area of one camera, so that a plurality of testers can test simultaneously. Illustratively, when the sports test item is pull-up, the camera mounting height is recorded, the distance between the camera and the rail, and the rail and the reference point at the center of the rail for each test area are set. The partial parameters are used as reference parameters for intelligent recognition and detection algorithm debugging of pull-up motion specifications.
Step 403: and (5) collecting sports test videos. The step of collecting sports test videos comprises the following steps:
step 4031: the test person is identified.
The test person enters the test area and video frames are captured from the time the test person enters the test area. If a plurality of testers enter the test areas at the same time, analyzing the number of the testers in each test area, receiving instructions through a mobile phone or a PAD terminal, and displaying and/or prompting by voice, so that only one tester is in each test area.
Step 4032: the identity of the tester is identified.
And (5) aiming at the testers in each test area, adopting a face recognition algorithm to carry out identity recognition.
In some optional embodiments, after the face recognition is successful, the recognition result is displayed through an image interface of a terminal such as a mobile phone or a PAD, and/or the class and name information of the testers is prompted through a voice interaction module such as a bluetooth sound. After the identification is successful, before the test is not started, if the tester leaves the test area, the performance is invalid.
Step 4033: the tester is notified to begin testing.
After the face recognition is successful, the test personnel can start the test through the mobile phone or the terminal such as PAD or the man-machine interaction unit such as Bluetooth sound.
Step 4034: tracking the specific position of a tester, and collecting sports test videos.
After the test is started, the whole process video of the pull-up action of the tester is collected through the camera.
In some alternative embodiments, a ByteTrack+YOLOX human body tracking algorithm is used to locate the specific position of a tester in the video until the pull-up test is completed, and a sports test video is obtained. The specific positions of the human body of the tester are used for extracting key point information of the human body.
Step 404: and framing the video.
And carrying out framing treatment on the acquired video to obtain a video frame image sequence of the whole pull-up process.
Step 405: and detecting key points of the human body.
Here, the key points may be human body joints such as left and right ankle, left and right knee, left and right hip, left and right shoulder, left and right elbow, left and right wrist, chin, etc.; the key points can also be determined according to the key actions of the sports test item, and the key points are determined to be left and right hips, left and right shoulders, left and right elbows, left and right wrists and lower jaws by hanging and leading bodies when the sports test item is in the pull-up direction.
Based on the obtained video frame image sequence, detecting human body key points by taking the specific position of a tester captured by a human body tracking algorithm as a target and Vision Transformer +HrNet as a main network to obtain a position sequence corresponding to each key point. The algorithm introduces a local interesting map mechanism in the Head part on the basis of an open source HR-Former, and improves the output precision by matching with global semantic information. In the aspect of human body key point data amplification, the pixels and the space levels are used for transformation, and meanwhile, in order to cooperate with data amplification, unbiased data are used in a decoding stage, so that the decoding precision of the hematmap is improved. In some optional embodiments, the special data set of the sports test item is introduced to train the human body key point detection algorithm, so that the phenomenon of key point shaking and drifting in the motion process can be remarkably reduced.
Step 406: and determining the movement process of the sports test item.
And determining the start and end of the sports according to the sports process of the sports test item. Illustratively, when the sports test item is pull-up, the pull-up grip movement process begins with the test person vacating to grasp the bar and ends with releasing the bar to rest. And extracting the pull-up holding rod movement process according to the obtained criterion of reasonable design of the human body key point sequence, automatically judging that a tester gets on the rod according to the distance between the wrist key point and the cross rod as the criterion, and starting to perform key frame analysis.
Step 407: and extracting the key frames.
Key actions in the sports test item motion cycle are determined, and key frames are extracted based on the key actions. For example, when the sports test item is pull-up, the pull-up keyframes are an arm extension limit state and a chin bar limit state during a movement, and are referred to as a hanging state and a pull-up state, respectively, as shown in fig. 2 and 3. And extracting the limiting states of each group of action overhang and pull-up in the pull-up holding rod movement process according to the human body key point sequence by adopting reasonable criteria to form a preselected key frame sequence, and primarily screening the preselected key frame sequence according to the pull-up rule to obtain a final key frame sequence. According to the embodiment of the application, the sequence consisting of the arithmetic average values of Y values of the left shoulder (D point, K point), the right hip (C point, J point) and the chin point (N point) is taken as a basis, the maximum value and the minimum value of the sequence are extracted, the extracted extreme points are ordered and filtered through the threshold value, so that key frames of hanging and leading bodies of all movement rounds are extracted, the method is not influenced by individual differences, and the key state conforming to pull-up rules is extracted. And key frames representing key states are stored, so that subsequent backtracking and research are facilitated.
Step 408: and judging whether a key frame exists or not.
If no key frame exists, the test performance of the tester is invalid, and the step 403 is returned to collect sports test videos again or inform the next tester to enter a test area for testing;
if a key frame exists, step 409 is performed: the detection criteria action is identified.
The method comprises the steps of determining conditions met by key points in standard actions in sports test items, and judging whether the actions in key frames are standard actions or not based on the conditions.
Illustratively, when the sports test item is pull-up, the extracted pull-up key frames are divided into hanging key frames and pull-up key frames, and the rest of the sports processes except for the beginning and ending sports processes are reflected by one hanging key frame and one pull-up key frame. Because the time of a group of actions is short, the human body posture is difficult to obviously change, and therefore, the normalization of the whole action is judged by analyzing the joint points of the suspension frame and the primer frame of the tester and the angles of the connecting lines and the connecting lines. If the distance between the key points X of the left and right wrists (points F and M) and the left and right shoulders (points D and K) is equal to the width of the shoulders, if the arm of the hanging frame is straightened is judged by the angles (such as F, E, D points) formed by the wrists, the elbows and the shoulders, and if the pulling frame reaches the drawing standard is judged by the chin point N. For example, when the left and right wrists are equally wide at the left and right shoulders and the arms are straightened, the suspension motion criteria, when the left and right wrists are equally wide at the left and right shoulders and the chin exceeds the cross bar, the body motion criteria are introduced.
Step 410: and counting the effective times.
When all critical actions in a motion cycle are standard actions, the actions in the motion cycle are standard actions, and the effective count is increased by 1. In some embodiments, after the statistics are completed, the test performance is displayed and/or voice broadcast. Exemplary, pull-up valid action count: according to the motion standard identification and detection of the pull-up holding rod motion process key frame, a pull-up key frame pair (hanging frame and pull-up frame) sequence reaching the standard is obtained, when both hanging and pull-up are standard motions in one motion period, the pull-up standard motions in the period are effectively counted and added by 1, and the last statistical value is used as the last pull-up effective motion times.
According to the sports testing method provided by the embodiment of the application, key frames in the pull-up movement process are extracted, and the calculated amount is greatly reduced. The whole motion process can be traced back only by using the key frames with limited storage quantity, so that the storage space is saved, and the time cost of a teacher or a staff is reduced; according to the method, various criteria are designed for the key points of the human body to analyze the possibly-occurring illegal states, so that the types of nonstandard actions can be effectively determined, and the improvement of testers is facilitated.
According to the sports testing method, the sports video key frames are extracted according to the human body key point sequence design criteria, and then the whole process of sports is analyzed through analysis of the key frames. The thinking adopted by the method can be applied to sports scenes such as pull-up, sit-up, open-close jump, squat, push-up and the like, so that a complete sports exercise test solution is constructed, and a scientific and accurate sports prescription is provided.
According to the sports testing method provided by the embodiment of the application, the positions of the left shoulder, the right hip, the left hip, the right hip and the chin point of the tester are considered, the maximum value and the minimum value of the sequence formed by the arithmetic average value of the positions are extracted to determine the pull-up key frame, and then the positions are counted according to the Y value of the chin point. The method is not affected by individual differences, can effectively extract key frames corresponding to various forms and various postures, and has strong universality. The human body key point detection module in the application adopts Vision Transformer +HrNet, and the combination of the two modes has the capabilities of multi-resolution parallelism and comprehensive capture of local and global information. And determining the interval of the pull-up holding rod movement process by the position of the key point of the wrist of the human body in the full video process. The method extracts the key parts of pull-up movement, reduces the interference of the front and back preparation stages, and improves the accuracy of key frame extraction.
The embodiment of the present application further provides a sports test system 500, referring to fig. 5, the sports test system 500 in this embodiment includes:
extraction unit 510: the method comprises the steps of carrying out framing processing on a pull-up test video to obtain a plurality of video frames; extracting a plurality of key frames from the plurality of video frames based on the overhang motion and the primer motion;
statistics unit 520: for extracting a plurality of key frames from the plurality of video frames based on the overhang and primer actions in one motion cycle.
In this embodiment of the present application, the sports test system 500 further includes: video acquisition unit: for capturing the sports test video; man-machine interaction unit: the method is used for prompting testers to test in the effective area and/or prompting non-testers to leave the test area in the process of collecting the sports test video; the system is also used for broadcasting and/or displaying the number of the standard actions; an identity recognition unit: for identifying the identity information of the test person.
In this embodiment of the present application, the sports test system 500 further includes: a network communication unit: the system is used for connecting the extraction unit 510, the statistics unit 520, the video acquisition unit, the man-machine interaction unit and the identity recognition unit into a communication network to realize the connectivity of the physical network among the units. The priority wired network may also be a WIFI router, a 4G wireless router, a 5G wireless router, and a 4G communication module integrated in the man-machine interaction module, which is not limited in this application.
In this embodiment of the present application, the extracting unit 510: the method comprises the steps of acquiring key points in each video frame of a plurality of video frames; the key points include at least one of: left wrist, right wrist, left elbow, right elbow, left shoulder, right shoulder, left hip, right hip and chin; and extracting video frames of which the key points meet the first conditions of the overhang action and the first conditions of the primer action as the key frames.
In this embodiment of the present application, the extracting unit 510: the method comprises the steps of acquiring key points in each video frame of a plurality of video frames by using a first model; the first model is a model taking Vision Transformer +HrNet as a main network.
In this embodiment, the statistics unit 520: the key frame specifically used for determining that the key point meets the second condition of the overhang motion or the second condition of the primer motion is a standard motion key frame; when all key frames in a motion cycle are standard motion key frames, the pull-up motion in the motion cycle is determined to be standard motion.
In the embodiment of the application, the one movement period comprises adjacent primary suspension and primary primer; the first condition of overhang includes: the average value of the heights of the left shoulder, the right shoulder, the left hip, the right hip and the chin in one movement period is a minimum value; the first condition of the primer includes: the average of the heights of the left shoulder, the right shoulder, the left hip, the right hip and the chin in one movement period is the maximum; the second condition of overhang includes at least one of: the difference between the left wrist distance and the right shoulder distance accords with a preset difference range, and the included angle formed by the wrist, the elbow and the shoulder on the same side accords with a preset angle range; the second condition of the primer includes at least one of: the left and right wrists are as wide as the left and right shoulders and the lower jaw is higher than the cross bar.
Those skilled in the art will appreciate that the implementation of the functions of the units in the sports test system 500 shown in fig. 5 may be understood with reference to the relevant description of the foregoing method. The functions of the units in the sports test system 500 shown in fig. 5 may be implemented by a program running on a processor, or by specific logic circuits.
The embodiment of the application further provides a sports test system 600, referring to fig. 6, the sports test system 600 in this embodiment includes:
video acquisition unit 610: the method is used for collecting sports test videos. The camera takes precedence with the network camera, also can adopt USB camera, WIFI camera, candid photograph camera, this application does not limit to this.
Network communication unit 620: the system is used for connecting the video acquisition unit 610, the man-machine interaction unit 630, the identity recognition unit 640, the human body tracking and human body key point detection unit 650 and the action specification recognition and detection unit 660 into a communication network to realize the connectivity of the physical network among the units. The priority wired network may also be a WIFI router, a 4G wireless router, a 5G wireless router, and a 4G communication module integrated in the man-machine interaction module, which is not limited in this application.
Man-machine interaction unit 630: the method is used for prompting the current state of the tester, informing the tester of the effective accumulated times of the real-time test and informing the tester of the test performance. The android PAD and bluetooth speaker may be any other intelligent terminal with a screen, supporting broadcasting or supporting a camera, which is not limited in this application.
Identity recognizing unit 640: the face recognition identity is preferential and is not limited to the identity information of the recognition tester such as fingerprints, identity cards, card numbers and the like. The identity recognition unit 640 may exist independently or may be integrated into a part of the human interaction unit 630, the human body tracking and human body key point detection unit 650, or the action specification recognition and detection unit 660.
Human body tracking and human body key point detection unit 650: the method is used for carrying out human body tracking on a tester in a test area in the acquired video, carrying out framing processing on the full video, inputting framing pictures into a human body key point detection unit, and obtaining a human body key point sequence of the tester. The unit is an algorithm bottom layer module of the whole system, and provides basic conditions for identifying and detecting action specifications of subsequent sports test projects.
Action specification recognition and detection unit 660: for identifying and detecting the movements of the tester in the sports test. Illustratively, the whole test behavior of pulling up the arms, pulling up the body, pulling down the chin, pulling down the body, pulling up the arms, pulling the hands away from the poles is performed on the hands, and the pull-up performance is automatically calculated and stored. The method can identify the foul behaviors of the testers, such as arm unbending, chin unbending and the like. The unit is a core module of the whole system, is a server for identifying and detecting the action specification and counting the number of the pull-up effective actions, and can be connected with a man-machine interaction module to facilitate backtracking of workers.
Those skilled in the art will appreciate that the implementation of the functions of the units in the sports test system 600 shown in fig. 6 may be understood with reference to the relevant description of the foregoing method. The functions of the units in the sports test system 600 shown in fig. 6 may be implemented by a program running on a processor, or may be implemented by specific logic circuits.
Fig. 7 is a schematic structural diagram of an electronic device 700 provided in an embodiment of the present application. The electronic device 700 shown in fig. 7 comprises a processor 710, from which the processor 710 may call and run a computer program to implement the methods in embodiments of the present application.
Optionally, as shown in fig. 7, the electronic device 700 may further comprise a memory 720. Wherein the processor 710 may call and run a computer program from the memory 720 to implement the methods in embodiments of the present application.
Wherein the memory 720 may be a separate device from the processor 710 or may be integrated into the processor 710.
Optionally, as shown in fig. 7, the electronic device 700 may further include a transceiver 730, and the processor 710 may control the transceiver 730 to communicate with other devices, and in particular, may send information or data to other devices or receive information or data sent by other devices.
Among other things, transceiver 730 may include a transmitter and a receiver. Transceiver 730 may further include antennas, the number of which may be one or more.
The electronic device 700 may be specifically a sports test system according to the embodiments of the present application, and the electronic device 700 may implement a corresponding flow implemented by the sports test system in each method according to the embodiments of the present application, which is not described herein for brevity.
Fig. 8 is a schematic structural diagram of a chip of an embodiment of the present application. The chip 800 shown in fig. 8 includes a processor 810, and the processor 810 may call and run a computer program from a memory to implement the methods in the embodiments of the present application.
Optionally, as shown in fig. 8, chip 800 may also include memory 820. Wherein the processor 810 may call and run a computer program from the memory 820 to implement the methods in embodiments of the present application.
Wherein the memory 820 may be a separate device from the processor 810 or may be integrated into the processor 810.
Optionally, the chip 800 may also include an input interface 830. The processor 810 may control the input interface 830 to communicate with other devices or chips, and in particular, may obtain information or data sent by other devices or chips.
Optionally, the chip 800 may further include an output interface 840. The processor 810 may control the output interface 840 to communicate with other devices or chips, and in particular, may output information or data to other devices or chips.
The chip can be applied to the sports test system in the embodiment of the application, and the chip can realize corresponding processes realized by the sports test system in each method in the embodiment of the application, and for brevity, the description is omitted here.
It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, or the like.
It should be appreciated that the processor of an embodiment of the present application may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method embodiments may be implemented by integrated logic circuits of hardware in a processor or instructions in software form. The processor may be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), an off-the-shelf programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks 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 a method disclosed in connection with the embodiments of the present application may be embodied directly in hardware, in a decoded processor, or in a combination of hardware and software modules in a decoded processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in a memory, and the processor reads the information in the memory and, in combination with its hardware, performs the steps of the above method.
It will be appreciated that the memory in embodiments of the present application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (Double Data Rate SDRAM), enhanced SDRAM (ESDRAM), synchronous DRAM (SLDRAM), and Direct RAM (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to comprise, without being limited to, these and any other suitable types of memory.
It should be understood that the above memory is exemplary but not limiting, and for example, the memory in the embodiments of the present application may be Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous DRAM (SLDRAM), direct RAM (DR RAM), and the like. That is, the memory in embodiments of the present application is intended to comprise, without being limited to, these and any other suitable types of memory.
Embodiments of the present application also provide a computer-readable storage medium for storing a computer program. The computer readable storage medium may be applied to the sports test system in the embodiments of the present application, and the computer program makes the computer execute the corresponding flow implemented by the sports test system in the methods in the embodiments of the present application, which is not described herein for brevity.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown 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 units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a sports test system, etc.) to perform all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present application, and the changes and substitutions are intended to be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (11)
1. A method of physical testing comprising:
carrying out framing treatment on the pull-up test video to obtain a plurality of video frames;
extracting a plurality of key frames from the plurality of video frames based on the overhang and primer actions in one motion cycle;
based on the plurality of key frames, judging whether pull-up actions in each movement period are standard or not, and counting the number of standard actions.
2. The method of claim 1, wherein the extracting a plurality of keyframes from the plurality of video frames based on the overhang and primer motions in one motion cycle comprises:
collecting key points in each video frame of the plurality of video frames; the key points include at least one of: left wrist, right wrist, left elbow, right elbow, left shoulder, right shoulder, left hip, right hip and chin;
And extracting video frames of which the key points meet the first conditions of the overhang action and the first conditions of the primer action as the key frames.
3. The method of claim 2, wherein the capturing keypoints in each of the plurality of video frames comprises:
acquiring key points in each of the plurality of video frames using a first model; the first model is a model taking Vision Transformer +HrNet as a main network.
4. The method of claim 2, wherein determining whether pull-up motion is standard in each exercise cycle based on the plurality of keyframes comprises:
determining that the key points meet the second condition of the overhang action or the key frames of the second condition of the primer action as standard action key frames;
when all key frames in a motion cycle are standard motion key frames, the pull-up motion in the motion cycle is determined to be standard motion.
5. The method for physical testing according to claim 4, wherein,
the motion period comprises adjacent primary overhang and primary primer;
the first condition of overhang includes: the average value of the heights of the left shoulder, the right shoulder, the left hip, the right hip and the chin in one movement period is a minimum value;
The first condition of the primer includes: the average of the heights of the left shoulder, the right shoulder, the left hip, the right hip and the chin in one movement period is the maximum;
the second condition of overhang includes at least one of: the difference between the left wrist distance and the right shoulder distance accords with a preset difference range, and the included angle formed by the wrist, the elbow and the shoulder on the same side accords with a preset angle range;
the second condition of the primer includes at least one of: the left and right wrists are as wide as the left and right shoulders and the lower jaw is higher than the cross bar.
6. The sports testing method according to any one of claims 1 to 5, further comprising, prior to framing the pull-up test video:
collecting the pull-up test video in a test area;
identifying the identity information of the tester in the process of collecting the pull-up test video; prompting a tester to test in the effective area and/or prompting a non-tester to leave the test area; and broadcasting and/or displaying the number of the standard actions.
7. A sports testing system, comprising:
extraction unit: the method comprises the steps of carrying out framing processing on a pull-up test video to obtain a plurality of video frames; extracting a plurality of key frames from the plurality of video frames based on the overhang motion and the primer motion;
A statistics unit: for extracting a plurality of key frames from the plurality of video frames based on the overhang and primer actions in one motion cycle.
8. The athletic testing system of claim 7, further comprising:
video acquisition unit: for capturing the pull-up test video;
man-machine interaction unit: the system is used for prompting a tester to test in the effective area and/or prompting a non-tester to leave the test area in the process of collecting the pull-up test video; broadcasting and/or displaying the number of the standard actions;
an identity recognition unit: for identifying the identity information of the test person.
9. An electronic device, comprising: a processor and a memory for storing a computer program, the processor being adapted to invoke and run the computer program stored in the memory to perform the sports test method according to any of claims 1-6.
10. A chip, comprising: processor for calling and running a computer program from a memory, causing a device on which the chip is mounted to perform the sports test method according to any one of claims 1-6.
11. A computer-readable storage medium storing a computer program for causing a computer to perform the sports testing method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311013757.XA CN117292288A (en) | 2023-08-11 | 2023-08-11 | Sports test method, system, electronic device, chip and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311013757.XA CN117292288A (en) | 2023-08-11 | 2023-08-11 | Sports test method, system, electronic device, chip and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117292288A true CN117292288A (en) | 2023-12-26 |
Family
ID=89247012
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311013757.XA Pending CN117292288A (en) | 2023-08-11 | 2023-08-11 | Sports test method, system, electronic device, chip and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117292288A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117636698A (en) * | 2023-12-28 | 2024-03-01 | 北京奥康达体育科技有限公司 | Digital pull-up auxiliary training system for student examination |
-
2023
- 2023-08-11 CN CN202311013757.XA patent/CN117292288A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117636698A (en) * | 2023-12-28 | 2024-03-01 | 北京奥康达体育科技有限公司 | Digital pull-up auxiliary training system for student examination |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021051579A1 (en) | Body pose recognition method, system, and apparatus, and storage medium | |
| CN110090424B (en) | A referee system for football winding rod examination | |
| US20150092981A1 (en) | Apparatus and method for providing activity recognition based application service | |
| CN111437583A (en) | Badminton basic action auxiliary training system based on Kinect | |
| CN110738154A (en) | pedestrian falling detection method based on human body posture estimation | |
| CN112364785B (en) | Exercise training guiding method, device, equipment and computer storage medium | |
| CN110633004B (en) | Interaction method, device and system based on human body posture estimation | |
| CN108958482B (en) | Similarity action recognition device and method based on convolutional neural network | |
| CN114100103B (en) | Rope skipping counting detection system and method based on key point identification | |
| CN113856186B (en) | Pull-up action judging and counting method, system and device | |
| CN117292288A (en) | Sports test method, system, electronic device, chip and storage medium | |
| CN110478862A (en) | A kind of exercise guide system and its guidance method | |
| CN105105757B (en) | A kind of wearable human motion posture track record and assessment device | |
| CN111223549A (en) | Mobile end system and method for disease prevention based on posture correction | |
| CN105844204A (en) | Method and device for recognizing behavior of human body | |
| CN210933642U (en) | Body-building guidance system | |
| CN111563443A (en) | Continuous motion action accuracy evaluation method | |
| CN117133057A (en) | Physical exercise counting and illegal action distinguishing method based on human body gesture recognition | |
| CN114639168B (en) | Method and system for recognizing running gesture | |
| CN114550071B (en) | Method, device and medium for automatically identifying and capturing track and field video action key frames | |
| CN115690895A (en) | Human skeleton point detection-based multi-person motion detection method and device | |
| CN113837112A (en) | Video data processing method and electronic equipment | |
| CN113469113A (en) | Action counting method and device, electronic equipment and storage medium | |
| CN112241674A (en) | Face recognition method and system | |
| CN115273243B (en) | Fall detection method, device, electronic equipment and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |