A sit-up action standard detection method, device and storage medium

Calculate the standardized degree score of sit-up movements through video image acquisition and limb detection models, and solves the problem that sit-up movement detection relies on manual judgment in the prior art, realizes automatic, fast and accurate movement normative judgment, and improves detection efficiency and accuracy.

CN118015706BActive Publication Date: 2024-11-26GUANGDONG PROPHET BIG DATA CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410324837.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-03-21
Publication Date
2024-11-26
Estimated Expiration
2044-03-21

AI Technical Summary

Technical Problem

In the prior art, sit-up movement detection relies on manual judgment, which is costly, low efficiency and low accuracy, making it difficult to effectively detect movement normativeness.

Method used

Through video image acquisition and limb detection models, the standardized scores of sit-up movements are calculated, including standardized scores of head hugging, feet and knee touching, and automatically determine whether the movements meet the specifications.

Benefits of technology

It realizes automatic, fast and accurate judgment of the standardization of sit-up movements, saves human resources, and improves detection efficiency and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118015706B_ABST
    Figure CN118015706B_ABST
Patent Text Reader

Abstract

The present application discloses a sit-up action standard detection method, device and storage medium for detecting whether the sit-up action is standard. The sit-up action standard detection method disclosed in the present application comprises: collecting a video image of sit-ups; starting from the i-th frame of the video image, calculating the number of frames from the i-th frame to the i+n-th frame. 1 The standardization score #imgabs0# of the sit-up action of the frame; when the standardization score #imgabs1#>0, the sit-up action is determined to be standard, otherwise the sit-up action is determined to be non-standard. The present application also provides a sit-up action standardization detection device and a storage medium.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computing technology, and in particular to a method, device and storage medium for detecting sit-up action norms. Background Art

[0002] Sit-ups are an important test item in physical examination. The test results of sit-ups can reflect the strength level of the abdominal muscles and core muscles, as well as the cardiopulmonary endurance and physical fitness level. Standardized sit-up postures can not only avoid injuries, but also ensure the exercise effect and improve body stability and coordination. In the existing technology, only personnel can be relied on to detect the action specifications, which is too costly and inefficient in terms of time and manpower, and the judgment accuracy is not high. Summary of the invention

[0003] In response to the above technical problems, the embodiments of the present application provide a sit-up action standard detection method, device and storage medium for determining whether the sit-up action is standard.

[0004] In a first aspect, an embodiment of the present application provides a sit-up action standard detection method, comprising:

[0005] Collect video images of sit-ups;

[0006] Starting from the i-th frame of the video image, calculate the standardization score g of the sit-up action from the i-th frame to the i+n1-th frame f ;

[0007] When the standardization score g f When >0, the sit-up action is judged to be standard, otherwise it is judged to be non-standard;

[0008] The i-th frame is the image frame where sit-ups are started, n1 is a positive integer, and the standardization score g is f Indicates the matching degree between the sit-up action from the i-th frame to the i+n1-th frame and the preset action standard;

[0009] i is an integer greater than or equal to 0.

[0010] In the present invention, the sit-up process is captured by an image capture device, and then the standardization score of the sit-up process is automatically calculated, so as to judge whether it meets the standard according to the score, thereby saving human resources and improving judgment efficiency and accuracy.

[0011] Preferably, collecting video images of sit-ups includes:

[0012] The video image is acquired through the camera, and the head coordinates (hx i ,hy i), the coordinates of the two wrists (sx1 i ,sy1 i ), (sx2 i ,sy2 i ), the coordinates of the two elbows (ex1 i ,eyi1 i ), (ex2 i ,ey2 i ), the coordinates of the center of the hip bone (ux i , uy i ), the coordinates of the two knees (kx1 i ,ky1 i ),(kx2 i ,ky2 i ), the coordinates of the two ankles (fx1 i ,fy1 i ), (fx2 i ,fy2 i ).

[0013] Preferably, the standardization score g f Determined according to the following formula:

[0014] g f =g6g7g8;

[0015] Among them, g6 is the standard score for holding the head, g7 is the standard score for the feet, and g8 is the standard score for touching the knees.

[0016] The head-holding standard score g6 is determined according to the following formula:

[0017]

[0018] g3 j is the head-holding status score, determined by the following formula:

[0019]

[0020] in:

[0021]

[0022] ts2 is the set second judgment threshold, ts5 is the set fifth judgment threshold, and j is an integer from i+1 to i+n1.

[0023] The foot standard score g7 is determined according to the following formula:

[0024]

[0025] Among them, g4 j The score for the suspended state is determined by the following formula:

[0026]

[0027]

[0028] ts3 is the set third judgment threshold, j is an integer from i+1 to i+n1;

[0029]

[0030] The knee-touching norm score g8 is determined according to the following formula:

[0031]

[0032] Among them, g3 j is the head-holding status score, determined by the following formula:

[0033]

[0034] g5 j The contact status score is determined according to the following formula:

[0035]

[0036] ts4 is the set fourth judgment threshold, ts2 is the set second judgment threshold, ts5 is the set fifth judgment threshold, and j is an integer from i+1 to i+n1.

[0037] Preferably, the image frame i at which sit-ups are started is determined according to the following method:

[0038] Calculate the activation score g1 of the i-th frame image i ;

[0039] When g1 i =1, it is determined that sit-ups have begun;

[0040] Among them, the startup score g1 i Determined according to the following formula:

[0041]

[0042] And g10=0, ts1 is the set first judgment threshold;

[0043] in,

[0044]

[0045] Preferably, the positive integer n1 is determined according to the following method:

[0046] Calculate the ending score g2 of the image frame i, and g20=2;

[0047] When the start score g1 of frame i i = 1, it is determined that sit-ups are started, and the end score g2 of each frame starting from frame i is recorded. i , when n1 frames have passed, the score ends The first time it is equal to 1;

[0048] Among them, the ending score g2 i Determined according to the following formula:

[0049]

[0050] In a second aspect, the embodiment of the present application further provides a sit-up action standard detection device, comprising:

[0051] An acquisition module is configured to acquire video images of sit-ups;

[0052] The judgment module is configured to calculate the standardization degree score g of the sit-up action from the i-th frame to the i+n1-th frame starting from the i-th frame of the video image. f , when the standardization score g f When >0, the sit-up action is judged to be standard, otherwise it is judged to be non-standard;

[0053] The i-th frame is the image frame where sit-ups are started, n1 is a preset positive integer, and the standardization degree score g is f Indicates the matching degree between the sit-up action from the i-th frame to the i+n1-th frame and the preset action standard.

[0054] In a third aspect, an embodiment of the present application further provides a sit-up action standard detection device, comprising: a memory, a processor, and a user interface;

[0055] The memory is used to store computer programs;

[0056] The user interface is used to interact with the user;

[0057] The processor is used to read the computer program in the memory, and when the processor executes the computer program, the sit-up action standard detection method provided by the present invention is implemented.

[0058] In a fourth aspect, an embodiment of the present application further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and when the processor executes the computer program, the sit-up action standard detection method provided by the present invention is implemented.

[0059] In the present invention, the standard degree score during the sit-up process is calculated according to the head holding standard score, the footsteps standard score and the knee touching standard score, and the standard score of the entire sit-up is calculated comprehensively through the three scores, so as to automatically, quickly and accurately judge whether the sit-up is standard. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0061] Figure 1 A schematic diagram of a method for detecting sit-up movements in accordance with an embodiment of the present application;

[0062] Figure 2 A schematic diagram of another sit-up action standard detection method provided in an embodiment of the present application;

[0063] Figure 3 A schematic diagram of a method for determining the end of sit-ups provided in an embodiment of the present application;

[0064] Figure 4 A schematic diagram of a sit-up action standard detection device provided in an embodiment of the present application;

[0065] Figure 5 A schematic diagram of the structure of another sit-up action standard detection device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] The following are explanations of some of the terms that appear in the text:

[0068] 1. In the embodiments of the present invention, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0069] 2. In the embodiments of the present application, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0070] In view of the problem that the prior art can only rely on personnel to detect action standards, which has high costs in time, manpower, etc. and low efficiency, and the judgment accuracy is not high, the present invention proposes a sit-up action standard detection method, which automatically, quickly and accurately determines whether the sit-up is standard.

[0071] In the present invention, before the test begins, a camera needs to be set up in the sports field to collect images of the sit-up process, such as in the sit-up test field for students. When the sit-up preparation is completed, the staff starts the detection model, obtains images through the camera, and obtains the head coordinates (hx i ,hy i ), the coordinates of the two wrists (sx1 i ,sy1 i ), (sx2 i ,sy2 i ), the coordinates of the two elbows (ex1 i ,ey1 i ), (ex2 i ,ey2 i ), the coordinates of the center of the hip bone (ux i , uy i ), the coordinates of the two knees (kx1 i ,ky1 i ),(kx2 i ,ky2 i ), the coordinates of the two ankles (fx1 i ,fy1 i ), (fx2 i ,fy2 i ), where i is the frame number corresponding to the image, and i=0 indicates the original state when preparation is done.

[0072] Among them, hx i is the horizontal coordinate of the head, hy i is the vertical coordinate of the head, sx1 i is the horizontal coordinate of the left wrist, sy1 i is the ordinate of the left wrist, sx2 i is the horizontal coordinate of the right wrist, sy2 i is the vertical coordinate of the right wrist, ex1 i is the horizontal coordinate of the left elbow, ey1 i is the ordinate of the left elbow, ex2 i is the horizontal coordinate of the right elbow, ey2 i is the ordinate of the right elbow, ux i is the horizontal coordinate of the hip center, uy i The vertical coordinate of the hip center, kx1i is the horizontal coordinate of the left knee, ky1 i is the ordinate of the left knee, kx2 i is the horizontal coordinate of the right knee, ky2 i is the vertical coordinate of the right knee, fx1 i is the horizontal coordinate of the left ankle, fy1 i is the ordinate of the left ankle, fx2 i is the horizontal coordinate of the right ankle, fy2 i is the vertical coordinate of the right ankle.

[0073] When i=0, it indicates the original state when ready to work. Correspondingly, the coordinates of the head at this moment are (hx0, hy0), the coordinates of the two wrists are (sx10, sy10), (sx20, sy20), the coordinates of the two elbows are (ex10, ey10), (ex20, ey20), the coordinates of the center of the hip are (ux0, uy0), the coordinates of the two knees are (kx10, ky10), (kx20, ky20), and the coordinates of the two ankles are (fx10, fy10), (fx20, fy20).

[0074] Preferably, in the present invention, the origin of the coordinate system can be set to the origin (0,0) of the image screen;

[0075] Preferably, in the present invention, the head coordinate point position may be the center point of the head.

[0076] Preferably, in the present invention, the wrist coordinate point position may be the center point of the wrist.

[0077] Preferably, in the present invention, the coordinate point position of the elbow can be the center point of the elbow.

[0078] Preferably, in the present invention, the knee coordinate point position may be the center point of the knee.

[0079] Preferably, in the present invention, the ankle coordinate point position may be the center point of the ankle.

[0080] Preferably, the limb detection model is obtained by collecting images for limb annotation and training using a YOLO model, or by training using a Posenet model.

[0081] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0082] It should be noted that the order in which the embodiments of the present application are presented only represents the order of precedence of the embodiments, and does not represent the advantages or disadvantages of the technical solutions provided by the embodiments.

[0083] See also Figure 1 , a schematic diagram of a sit-up action standard detection method provided in an embodiment of the present application, such as Figure 1 As shown, the method includes steps S101 to S103:

[0084] S101, collecting video images of sit-ups;

[0085] S102, starting from the i-th frame of the video image, calculating the standardization score g of the sit-up action from the i-th frame to the i+n1-th frame f ;

[0086] S103, when the standardization degree score g f When >0, the sit-up action is judged to be standard, otherwise it is judged to be non-standard;

[0087] The i-th frame is the image frame where sit-ups are started, n1 is a positive integer, and the standardization score g is f Indicates the matching degree between the sit-up action from the i-th frame to the i+n1-th frame and the preset action standard.

[0088] As an optional example, in the present invention, the video images of sit-ups can be images captured by a camera at the sit-up scene, or can be video images of the sit-up scene transmitted via a wired network or a wireless network, that is, they can be captured on-site or remotely.

[0089] Preferably, starting from the original state when preparations are made, it is detected whether sit-ups have begun, and when it is detected that sit-ups have begun, the video image frame at that moment is determined as the i-th frame.

[0090] Preferably, n1 is the number of video image frames during one sit-up, that is, the number of video image frames from the beginning of the sit-up to the end of the sit-up.

[0091] Preferably, in the present invention, the method for determining the i-th frame may be:

[0092] Calculate the activation score g1 of the i-th frame image i ;

[0093] When g1 i =1, it is determined that sit-ups have begun;

[0094] Among them, the startup score g1 i Determined according to the following formula:

[0095]

[0096] And g10=0, ts1 is the set first judgment threshold;

[0097] in,

[0098]

[0099] ts1 is the first judgment threshold set. When the head contact degree score is less than ts1, it means that the student has left the ground.

[0100] Preferably, the number n1 of video image frames during a sit-up can be determined according to the following method:

[0101] Calculate the ending score g2 of the image frame i , and g20=2;

[0102] When the start score g1 of frame i i = 1, it is determined that sit-ups are started, and the end score g2 of each frame starting from frame i is recorded. i , when n1 frames have passed, the score ends The first time it is equal to 1;

[0103] Among them, the ending score g2 i Determined according to the following formula:

[0104]

[0105] That is, when the start score g1 of any frame i i = 1, the student starts to do sit-ups, and the end score of each frame starting from the i-th frame is recorded. When n1 frames are passed, the end score is The sit-up is determined to be completed when it is equal to 1 for the first time. Then, the video image of a sit-up action process from the i-th frame to the i+n1-th frame is analyzed.

[0106] As an alternative example, Figure 3 As shown, the process of judging the end of a sit-up process is as follows:

[0107] S301, starting from the i-th frame, calculating the end score of each frame.

[0108] Calculate the end score g2 for each frame i , the method is the same as the above formula, that is:

[0109]

[0110] S302, determine the end score g2 iIs it equal to 1? If it is equal to 1, execute step S303; otherwise, execute S301 again;

[0111] S303, sit-ups are finished.

[0112] As an optional example, in S101, collecting a video image of sit-ups includes:

[0113] The video image is acquired through the camera, and the head coordinates (hx i ,hy i ), the coordinates of the two wrists (sx1 i ,sy1 i ), (sx2 i ,sy2 i ), the coordinates of the two elbows (ex1 i ,ey1 i ), (ex2 i ,ey2 i ), the coordinates of the center of the hip bone (ux i , uy i ), the coordinates of the two knees (kx1 i ,ky1 i ),(kx2 i ,ky2 i ), the coordinates of the two ankles (fx1 i ,fy1 i ), (fx2 i ,fy2 i ).

[0114] As an optional example, the standardization degree score g in S102 f Determined according to the following formula:

[0115] g f =g6g7g8;

[0116] Among them, g6 is the standard score for holding the head, g7 is the standard score for the feet, and g8 is the standard score for touching the knees.

[0117] In the present invention, the head-holding standard score indicates whether the examinee holds the head with hands as required, the feet standard score indicates whether the examinee's lower limb movements are standard, and the knee-touching standard score indicates whether the examinee completes the sit-up movement as required.

[0118] As a preferred example, the head-holding standard score g6 is determined according to the following formula:

[0119]

[0120] g3 j is the head-holding status score, determined by the following formula:

[0121]

[0122] in:

[0123]

[0124] ts2 is the set second judgment threshold, ts5 is the set fifth judgment threshold, and j is an integer from i+1 to i+n1.

[0125] g31 j Score for headlock distance.

[0126] ts2 is the second judgment threshold set. When the head-holding distance score is less than ts2, it means that the head is held with both hands.

[0127] ts5 is the fifth judgment threshold set, indicating the number of video image frames corresponding to the shortest head-holding duration.

[0128] It should be noted that the shortest duration of holding the head is used to determine the shortest duration of the candidate's head holding action, which is an empirical constant obtained through a lot of training.

[0129] As an optional example, the foot specification score g7 is determined according to the following formula:

[0130]

[0131] Among them, g4 j The score for the suspended state is determined by the following formula:

[0132]

[0133] ts3 is the set third judgment threshold, ts6 is the set sixth judgment threshold, and j is an integer from i+1 to i+n1;

[0134] in,

[0135] Among them g41 j Score the students' foot grounding. is the ankle center coordinate of the jth frame. ts3 is the set third judgment threshold. When the foot contact degree score is less than ts3, it means that the foot leaves the ground.

[0136] As an optional example, the knee-contact norm score g8 is determined according to the following formula:

[0137]

[0138] Among them, g3 j is the head-holding status score, determined by the following formula:

[0139]

[0140] g5 j The contact status score is determined according to the following formula:

[0141]

[0142] ts4 is the set fourth judgment threshold, ts2 is the set second judgment threshold, ts5 is the set fifth judgment threshold, ts7 is the set seventh judgment threshold, and j is an integer from i+1 to i+n1.

[0143] Among them g51 j is the student's contact degree score, ts4 is the fourth judgment threshold set, and when the contact degree score is less than ts4, it means that the knee is in contact.

[0144] Combine the following Figure 2 , an optional embodiment of the sit-up action standard detection method of the present invention is described, such as Figure 2 As shown:

[0145] S201, start collecting video images.

[0146] In this step, the method of acquiring video images is the same as S101, which will not be repeated here.

[0147] S202, determine whether sit-ups have started, if so, execute S203, otherwise continue to execute S202.

[0148] In this step, the startup score g1 is calculated i Determine whether to start sit-ups, and when the start score is equal to 1, it is determined that the sit-ups are started. The method for calculating the start score is the same as S102, which will not be repeated here.

[0149] S203: The frame at which the sit-up starts is taken as the i-th frame.

[0150] That is, when it is determined that the sit-up is started, the frame number at that moment is taken as the i-th frame.

[0151] S204, collecting video images during the sit-up process.

[0152] S205, determine whether the sit-up is finished, if finished, execute S206, otherwise execute S204.

[0153] In this step, the method for determining whether the sit-up is finished is the same as Figure 3 , I will not go into details here.

[0154] S206, starting from the i-th frame of the video image, calculating the standardization score g of the sit-up action from the i-th frame to the i+n1-th framef .

[0155] In this step, the standardization score g is calculated. f The method is the same as S102 and will not be described in detail here.

[0156] S207, when the standardization degree score g f When >0, the sit-up action is judged to be standard, otherwise it is judged to be non-standard.

[0157] According to the method of this embodiment, the body coordinate data of the person doing sit-ups is collected by video acquisition equipment, including the head coordinates, the coordinates of the two wrists, the coordinates of the two elbows, the coordinates of the center of the hip bones, the coordinates of the two knees, and the coordinates of the two ankles. Then, the body coordinate data in all video image frames during a sit-up process are used to calculate the head holding standard score, the foot standard score, and the knee touching standard score, and then the sit-up standard score is calculated based on these three scores, so as to judge whether the sit-up is standard, thereby improving the efficiency and accuracy of the judgment, and also saving labor costs.

[0158] Based on the same inventive concept, the embodiment of the present invention also provides a sit-up action standard detection device, such as Figure 4 As shown, the device comprises:

[0159] The acquisition module 401 is configured to acquire video images of sit-ups;

[0160] The judgment module 402 is configured to calculate the standardization degree score g of the sit-up action from the i-th frame to the i+n1-th frame starting from the i-th frame of the video image. f , when the standardization score g f When >0, the sit-up action is judged to be standard, otherwise it is judged to be non-standard;

[0161] The i-th frame is the image frame where sit-ups are started, n1 is a preset positive integer, and the standardization degree score g is f Indicates the matching degree between the sit-up action from the i-th frame to the i+n1-th frame and the preset action standard.

[0162] As an optional example, the acquisition module 401 is further configured to acquire a video image of sit-ups:

[0163] The video image is acquired through the camera, and the head coordinates (hx i ,hy i ), the coordinates of the two wrists (sx1 i ,sy1 i ), (sx2 i ,sy2i ), the coordinates of the two elbows (ex1 i ,ey1 i ), (ex2 i ,ey2 i ), the coordinates of the center of the hip bone (ux i , uy i ), the coordinates of the two knees (kx1 i ,ky1 i ),(kx2 i ,ky2 i ), the coordinates of the two ankles (fx1 i ,fy1 i ), (fx2 i ,fy2 i ).

[0164] As an optional example, the judgment module 402 is further configured to determine the standardization degree score g f :

[0165] g f =g6g7g8;

[0166] Among them, g6 is the standard score for holding the head, g7 is the standard score for the feet, and g8 is the standard score for touching the knees.

[0167] As an optional example, the judgment module 402 is further configured to determine the head-holding standard score g6:

[0168]

[0169] g3 j is the head-holding status score, determined by the following formula:

[0170]

[0171] in:

[0172]

[0173] ts2 is the set second judgment threshold, ts5 is the set fifth judgment threshold, and j is an integer from i+1 to i+n1.

[0174] As an optional example, the determination module 402 is further configured to determine the foot standard score g7:

[0175]

[0176] Among them, g4 j The score for the suspended state is determined by the following formula:

[0177]

[0178] ts3 is the set third judgment threshold, ts6 is the set sixth judgment threshold, and j is an integer from i+1 to i+n1;

[0179] in,

[0180] As an optional example, the determination module 402 is further configured to determine a knee-contact standard score g8:

[0181]

[0182] Among them, g3 j is the head-holding status score, determined by the following formula:

[0183]

[0184] g5 j The contact status score is determined according to the following formula:

[0185]

[0186] ts4 is the set fourth judgment threshold, ts2 is the set second judgment threshold, ts5 is the set fifth judgment threshold, ts7 is the set seventh judgment threshold, and j is an integer from i+1 to i+n1.

[0187] As an optional example, the determination module 402 is further configured to determine the image frame i at which sit-ups are started:

[0188] Calculate the activation score g1 of the i-th frame image i ;

[0189] When g1 i =1, it is determined that sit-ups have begun;

[0190] Among them, the startup score g1 i Determined according to the following formula:

[0191]

[0192] And g10=0, ts1 is the set first judgment threshold;

[0193] in,

[0194]

[0195] As an optional example, the determination module 402 is further configured to determine a positive integer n1:

[0196] Calculate the ending score g2 of the image frame i , and g20=2;

[0197] When the start score g1 of the i-th frame i = 1, it is determined that sit-ups are started, and the end score g2 of each frame starting from the i-th frame is recorded. i , when n1 frames have passed, the score ends The first time it is equal to 1;

[0198] Among them, the ending score g2 i Determined according to the following formula:

[0199]

[0200] It should be noted that the device provided in this embodiment and the above-mentioned method embodiment belong to the same inventive concept, solve the same technical problems, and achieve the same technical effects. The device provided in this embodiment can implement all the methods of the above-mentioned method embodiment, and the similarities will not be repeated.

[0201] Based on the same inventive concept, the embodiment of the present invention also provides a sit-up action standard detection device, such as Figure 5 As shown, the device comprises:

[0202] It includes a memory 502, a processor 501 and a user interface 503;

[0203] The memory 502 is used to store computer programs;

[0204] The user interface 503 is used to interact with the user;

[0205] The processor 501 is configured to read the computer program in the memory 502. When the processor 501 executes the computer program, the following is achieved:

[0206] Collect video images of sit-ups;

[0207] Starting from the i-th frame of the video image, calculate the standardization score g of the sit-up action from the i-th frame to the i+n1-th frame f ;

[0208] When the standardization score g f When >0, the sit-up action is judged to be standard, otherwise it is judged to be non-standard;

[0209] The i-th frame is the image frame where sit-ups are started, n1 is a positive integer, and the standardization score g is f Indicates the matching degree between the sit-up action from the i-th frame to the i+n1-th frame and the preset action standard.

[0210] Among them, Figure 5In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 501 and memory represented by memory 502. The bus architecture may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The processor 501 is responsible for managing the bus architecture and general processing, and the memory 502 may store data used by the processor 501 when performing operations.

[0211] The processor 501 may be a CPU, an ASIC, an FPGA or a CPLD, and the processor 501 may also adopt a multi-core architecture.

[0212] When the processor 501 executes the computer program stored in the memory 502, any sit-up action standard detection method in the first embodiment is implemented.

[0213] It should be noted that the device of this embodiment and the above-mentioned method embodiment belong to the same inventive concept, solve the same technical problems, and achieve the same technical effects. The device of this embodiment can implement all the methods of the above-mentioned method embodiment, and will not be described again here to avoid repetition.

[0214] The present application also provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, and when the processor executes the computer program, any sit-up action standard detection method in the first embodiment is implemented.

[0215] It should be noted that the division of units in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0216] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0217] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0218] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0219] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A sit-up action standard detection method, characterized in that: include: Collect video images of sit-ups; Starting from the i-th frame of the video image, calculate the standardization score g of the sit-up action from the i-th frame to the i+n1-th frame f ; When the standardization score g f When >0, the sit-up action is judged to be standard, otherwise it is judged to be non-standard; The i-th frame is the image frame where sit-ups are started, n1 is a positive integer, and the standardization score g is f Indicates the matching degree between the sit-up action from the i-th frame to the i+n1-th frame and the preset action standard; i is an integer greater than or equal to 0; The video image acquisition of sit-ups comprises: The video image is acquired through the camera, and the head coordinates (hx i ,hy i ), the coordinates of the two wrists (sx1 i ,sy1 i ), (sx2 i ,sy2 i ), the coordinates of the two elbows (ex1 i ,ey1 i ), (ex2 i ,ey2 i ), the coordinates of the center of the hip bone (ux i , uy i ), the coordinates of the two knees (kx1 i ,ky1 i ),(kx2 i ,ky2 i ), the coordinates of the two ankles (fx1 i ,fy1 i ), (fx2 i ,fy2 i ); The standardization degree score g f Determined according to the following formula: g f =g6g7g8; Among them, g6 is the standard score for holding the head, g7 is the standard score for feet, and g8 is the standard score for touching the knee; The head-holding standard score g6 is determined according to the following formula: g3 j is the head-holding status score, determined by the following formula: in: ts2 is the set second judgment threshold, ts5 is the set fifth judgment threshold, and j is an integer from i+1 to i+n1; The foot standard score g7 is determined according to the following formula: Among them, g4 j The score for the suspended state is determined by the following formula: ts3 is the set third judgment threshold, ts6 is the set sixth judgment threshold, and j is an integer from i+1 to i+n1; in, The knee-touching norm score g8 is determined according to the following formula: Among them, g3 j is the head-holding status score, determined by the following formula: g5 j The contact status score is determined according to the following formula: ts4 is the set fourth judgment threshold, ts2 is the set second judgment threshold, ts5 is the set fifth judgment threshold, ts7 is the set seventh judgment threshold, and j is an integer from i+1 to i+n1.

2. The method according to claim 1, characterized in that The image frame i at which sit-ups are started is determined as follows: Calculate the activation score g1 of the i-th frame image i ; When g1 i =1, it is determined that sit-ups have begun; Among them, the startup score g1 i Determined according to the following formula: And g10=0, ts1 is the set first judgment threshold; in, 3. The method according to claim 2, characterized in that The positive integer n1 is determined according to the following method: Calculate the ending score g2 of the image frame i , and g20=2; When the start score g1 of the i-th frame i = 1, it is determined that sit-ups are started, and the end score g2 of each frame starting from the i-th frame is recorded. i , when n1 frames have passed, the score ends The first time it is equal to 1; Among them, the ending score g2 i Determined according to the following formula:

4. A sit-up action standard detection device, characterized in that: include: An acquisition module is configured to acquire video images of sit-ups; The judgment module is configured to calculate the standardization degree score g of the sit-up action from the i-th frame to the i+n1-th frame starting from the i-th frame of the video image. f , when the standardization score g f When >0, the sit-up action is judged to be standard, otherwise it is judged to be non-standard; The i-th frame is the image frame where sit-ups are started, n1 is a preset positive integer, and the standardization degree score g is f Indicates the matching degree between the sit-up action from the i-th frame to the i+n1-th frame and the preset action standard; The video image acquisition of sit-ups comprises: The video image is acquired through the camera, and the head coordinates (hx i ,hy i ), the coordinates of the two wrists (sx1 i ,sy1 i ), (sx2 i ,sy2 i ), the coordinates of the two elbows (ex1 i ,ey1 i ), (ex2 i ,ey2 i ), the coordinates of the center of the hip bone (ux i , uy i ), the coordinates of the two knees (kx1 i ,ky1 i ),(kx2 i ,ky2 i ), the coordinates of the two ankles (fx1 i ,fy1 i ), (fx2 i ,fy2 i ); The standardization degree score g f Determined according to the following formula: g f =g6g7g8; Among them, g6 is the standard score for holding the head, g7 is the standard score for feet, and g8 is the standard score for touching the knee; The head-holding standard score g6 is determined according to the following formula: g3 j is the head-holding status score, determined by the following formula: in: ts2 is the set second judgment threshold, ts5 is the set fifth judgment threshold, and j is an integer from i+1 to i+n1; The foot standard score g7 is determined according to the following formula: Among them, g4 j The score for the suspended state is determined by the following formula: ts3 is the set third judgment threshold, ts6 is the set sixth judgment threshold, and j is an integer from i+1 to i+n1; in, The knee-touching norm score g8 is determined according to the following formula: Among them, g3 j is the head-holding status score, determined by the following formula: g5 j The contact status score is determined according to the following formula: ts4 is the set fourth judgment threshold, ts2 is the set second judgment threshold, ts5 is the set fifth judgment threshold, ts7 is the set seventh judgment threshold, and j is an integer from i+1 to i+n1.

5. A sit-up action standard detection device, characterized in that: including a memory, a processor and a user interface; The memory is used to store computer programs; The user interface is used to interact with the user; The processor is used to read the computer program in the memory, and when the processor executes the computer program, it implements the sit-up action standard detection method as described in any one of claims 1 to 3.

Citation Information

Patent Citations

  • Sit-up posture evaluation method and device and storage medium

    CN114120204A

  • Motion scoring method and device, motion scoring equipment and storage medium

    CN115661930A

  • Diesel unloading standard detection method and device, electronic equipment and storage medium

    CN117237880A

  • Sit-up standard counting method and system based on image judgment

    CN117612261A

  • Counting method and system for sit-up test

    WO2017193590A1