A vision-based standing long jump swing detection method, device and medium

Abstract

The present application relates to a kind of vision-based standing long jump arm swing detection method, equipment and medium, belong to arm swing detection technical field, the method includes: when personnel enters standing long jump area preparation, the key information of each frame of personnel is acquired;According to left / right hand coordinates, left / right hand cumulative peak value score and left / right hand cumulative valley value score are calculated respectively, whether there is swing cycle is judged;When the judgment result is that there is swing cycle, the frame number of each peak value of left / right hand, the frame number of each valley value of left / right hand, the swing amplitude of each valley value of left / right hand and the swing direction of each valley value of left / right hand are determined respectively;The foot off ground degree score and knee joint stretch score of each frame are calculated, whether personnel is in take-off state is judged, the frame number corresponding to the first time that personnel is in take-off state is acquired;The arm swing action of personnel from preparation to take-off process is evaluated;According to the key information of the frame number corresponding to the first time that personnel is in take-off state, take-off posture is evaluated.

Description

Technical Field

[0001] This invention belongs to the field of motion specification detection technology, and in particular relates to a vision-based method, device and medium for detecting the arm swing in standing long jump. Background Technology

[0002] In physical education teaching and training, the standing long jump is an important basic physical fitness test. Its performance depends not only on lower limb strength, but also directly on the standardization of the arm swing motion, which affects the jump distance and quality. A standard standing long jump requires a standardized arm swing trajectory, maintaining the correct movement path. Traditional manual observation methods rely on the coach's subjective judgment, making it difficult to accurately and objectively assess the standardization of the arm swing trajectory, and also failing to provide quantitative feedback data. Summary of the Invention

[0003] In view of the shortcomings of the existing technology, the purpose of the invention is to provide a vision-based method, device and medium for detecting the arm swing in standing long jump. It uses visual detection technology to automatically analyze the arm swing action in standing long jump, which can objectively and accurately determine whether the arm swing trajectory meets the standard requirements, provide scientific technical feedback to personnel, help coaches guide training more effectively, and improve teaching quality and training efficiency.

[0004] In a first aspect, the present invention proposes a vision-based method for detecting the arm swing in a standing long jump, comprising six steps S1 to S6: S1: When personnel enter the standing long jump area to prepare, acquire key information about the personnel in each frame; S2: Calculate the cumulative peak score and cumulative valley score of the left and right hands based on the left and right hand coordinates in the key information of each frame of the personnel, and determine whether there is an oscillation cycle based on the cumulative peak score and cumulative valley score of the left and right hands; S3: When the judgment result is that there is an oscillation period, determine the number of frames for each peak value, the number of frames for each valley value, the oscillation amplitude of each valley value, and the oscillation direction of each valley value on the left and right sides respectively; S4: Calculate the foot lift-off score and knee extension score for each frame based on the key information of each frame. Determine whether the person is in the take-off state based on the foot lift-off score and knee extension score for each frame. If the determination result is that the person is in the take-off state, obtain the frame number corresponding to the first time the person is in the take-off state. S5: Evaluate the arm swing action of the personnel from preparation to takeoff based on the cumulative peak score of the left hand, cumulative peak score of the right hand, cumulative trough score of the left hand, cumulative trough score of the right hand, number of frames for each peak in the left hand, number of frames for each peak in the right hand, number of frames for each trough in the left hand, number of frames for each trough in the right hand, swing amplitude of each trough in the left hand, swing amplitude of each trough in the right hand, swing direction of each trough in the left hand, and swing direction of each trough in the right hand. S6: Evaluate the attitude during take-off based on key information from the frame number corresponding to the jumper's take-off state.

[0005] Furthermore, in the above-mentioned vision-based standing long jump arm swing detection method, step S1 involves acquiring key information for each frame of the person, including: acquiring the coordinates of the left shoulder, right shoulder, left elbow, right elbow, left hand, right hand, left hip, right hip, left knee, right knee, left foot, and right foot through a camera.

[0006] Furthermore, the aforementioned vision-based standing long jump arm swing detection method also includes: If the result indicates that there is no oscillation period, the analysis is stopped.

[0007] Furthermore, in the aforementioned vision-based standing long jump arm swing detection method, step S2 specifically includes: Calculate the foundation height based on the left / right hand coordinates; Calculate the left / right peak score and left / right valley score for each frame based on the base height and left / right coordinates; The cumulative peak score for the left and right hands is obtained by accumulating the peak scores for the left and right hands, and the cumulative trough score for the left and right hands is obtained by accumulating the trough scores for the left and right hands. Determine the magnitude of the cumulative peak score of the left / right hand and the preset peak score threshold, and the magnitude of the cumulative trough score of the left / right hand and the preset trough score threshold; If the judgment result is that the cumulative peak score of the left / right hand is greater than the preset peak score threshold and the cumulative trough score of the left / right hand is greater than the preset trough score threshold, then the judgment result is that there is an oscillation cycle.

[0008] Furthermore, in the aforementioned vision-based standing long jump arm swing detection method, step S3 specifically includes: When the judgment result is that there is a swing period, the peak interval score of each frame of the left and right hands is determined according to the cumulative peak score of the left and right hands, and the valley interval score of each frame of the left and right hands is determined according to the cumulative valley score of the left and right hands. The number of frames for each peak and the number of frames for each valley in the left and right hands are determined based on the peak interval score and valley interval score for each frame in the left and right hands. The swing amplitude of each valley value of the left / right hand is determined based on the left / right hand coordinates and the left / right shoulder coordinates; The swing direction of each valley value on the left / right hand is determined based on the left / right hand coordinates and the left / right shoulder coordinates.

[0009] Furthermore, in the aforementioned vision-based standing long jump arm swing detection method, step S4 specifically includes: The score for the degree of foot lift-off in each frame is calculated based on the left and right foot coordinates of the person in each frame. The knee extension score is determined based on the coordinates of the left foot, right foot, left hip, right hip, left knee, and right knee of the person in each frame. Determine whether the foot lift-off score is equal to the preset foot lift-off score threshold and whether the knee extension score is less than the preset knee extension score threshold. If the judgment result is that the foot lift-off score is equal to the preset foot lift-off score threshold and the knee extension score is less than the preset knee extension score threshold, then the judgment result is that the person is in the take-off state, and the number of frames corresponding to the time when the person first enters the take-off state is obtained.

[0010] Furthermore, in the aforementioned vision-based standing long jump arm swing detection method, step S5 specifically includes: The frequency synchronization score of the two arms is determined based on the cumulative peak score of the left hand, the cumulative peak score of the right hand, the cumulative trough score of the left hand, the cumulative trough score of the right hand, the number of frames for each peak in the left hand, the number of frames for each peak in the right hand, the number of frames for each trough in the left hand, and the number of frames for each trough in the right hand. The arm swing degree of both arms is scored synchronously based on the cumulative trough score of the left hand, the cumulative trough score of the right hand, the swing amplitude of each trough value of the left hand, and the swing amplitude of each trough value of the right hand. The degree and direction of arm swing are determined by the cumulative valley value of the left hand, the cumulative valley value of the right hand, the swing direction of each valley value of the left hand, and the swing direction of each valley value of the right hand. The system determines the relative magnitudes of the frequency synchronization scores of the two arms, the relative magnitudes of the arm swing degree synchronization scores, and the relative magnitudes of the arm swing direction scores. When the judgment result is that the frequency synchronization score of both arms is greater than the preset frequency synchronization score threshold, the swing degree synchronization score of both arms is greater than the preset swing degree synchronization score threshold, and the swing degree direction score of both arms is greater than the preset swing degree direction score threshold, the judge will swing his arms in a regular periodic manner before taking off.

[0011] Furthermore, in the aforementioned vision-based standing long jump arm swing detection method, step S6 specifically includes: The left-side posture score of the person is determined based on the left shoulder coordinate, left elbow coordinate, left hand coordinate, and left knee coordinate of the frame corresponding to the person's take-off state. The right-side posture score of the person is determined based on the right shoulder coordinate, right elbow coordinate, right hand coordinate, and right knee coordinate of the frame corresponding to the person's take-off state. The person's posture coordination score is determined based on the person's left-side posture score and the person's right-side posture score; The score of a person's posture coordination is compared with the preset swing threshold. When the judgment result is that the person's posture coordination score is less than the preset swing threshold, it is determined that the person's arm swing posture at the time of take-off is in accordance with the standard.

[0012] A second aspect of the present invention also provides an electronic device comprising: a processor and a memory; The processor executes any of the above vision-based standing long jump arm detection methods by calling programs or instructions stored in memory.

[0013] In a third aspect, the present invention also provides a computer-readable storage medium storing a program or instructions that cause a computer to execute a vision-based standing long jump arm swing detection method as described above.

[0014] The beneficial effects of this invention are as follows: This invention acquires key information of the person in each frame when they enter the standing long jump area to prepare; calculates the cumulative peak score and cumulative trough score for the left and right hands based on the left / right hand coordinates in each frame; determines whether a swing cycle exists based on the cumulative peak and trough scores; when a swing cycle is determined, the number of frames for each peak, the number of frames for each trough, the swing amplitude, and the swing direction for each trough are determined; and calculates the foot-off-ground score for each frame based on the key information of the person in each frame. The knee extension score is used to determine whether the person is in the take-off state based on the foot lift-off score and knee extension score in each frame, and to obtain the frame number corresponding to the first time the person is in the take-off state. The arm swing action of the person from preparation to take-off is evaluated based on the cumulative peak score of the left hand, the cumulative peak score of the right hand, the cumulative trough score of the left hand, the cumulative trough score of the right hand, the number of frames for each peak in the left hand, the number of frames for each peak in the right hand, the number of frames for each trough in the left hand, the number of frames for each trough in the right hand, the swing amplitude of each trough in the left hand, the swing amplitude of each trough in the right hand, the swing direction of each trough in the left hand, and the swing direction of each trough in the right hand. This invention evaluates the take-off posture based on key information from the frame number corresponding to the jumper's take-off state. It employs visual detection technology to automatically analyze the arm swing motion in the standing long jump, objectively and accurately determining whether the arm swing trajectory meets the specifications. This provides scientific technical feedback to personnel, helping coaches to more effectively guide training and improve teaching quality and training efficiency. Attached Figure Description

[0015] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts. It is obvious that the drawings described below are merely some embodiments of the present invention, and those skilled in the art can obtain other drawings based on these drawings.

[0016] Figure 1 A schematic diagram of a vision-based standing long jump arm detection method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a method for determining whether an oscillation period exists, provided by an embodiment of the present invention; Figure 3 A schematic diagram illustrating a method for determining the number of frames for each peak, the number of frames for each valley, the swing amplitude of each valley, and the swing direction of each valley, provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of a method for determining whether a person is in a jumping state, provided by an embodiment of the present invention; Figure 5 A schematic diagram illustrating a method for evaluating arm swing movements of a person from preparation to takeoff, provided by an embodiment of the present invention; Figure 6 This is a schematic diagram of a method for evaluating take-off posture provided by an embodiment of the present invention; Figure 7 This is a schematic block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0017] To enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0018] Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts disclosed in this invention.

[0019] In the description of this invention, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The terms "installed," "connected," and "linked" should be interpreted broadly; for example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0020] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of methods and systems consistent with some aspects of the invention as detailed in the appended claims.

[0021] This invention proposes a vision-based method, device, and medium for detecting the arm swing in standing long jump. By employing visual detection technology to automatically analyze the arm swing motion in standing long jump, it can objectively and accurately determine whether the arm swing trajectory meets the standard requirements, providing scientific technical feedback to personnel, helping coaches to guide training more effectively, and improving teaching quality and training efficiency.

[0022] Method Implementation Examples In a first aspect, the present invention proposes a vision-based method for detecting the arm swing in a standing long jump, combined with... Figure 1 It includes six steps, S1 to S6: S1: When personnel enter the standing long jump area to prepare, acquire key information about the personnel in each frame.

[0023] Specifically, in this embodiment of the invention, when a person enters the camera preparation area for the standing long jump, key information of the person for each frame is acquired, including: acquiring the coordinates of the left shoulder, right shoulder, left elbow, right elbow, left hand, right hand, left hip, right hip, left knee, right knee, left foot, and right foot through the camera.

[0024] S2: Calculate the cumulative peak score and cumulative valley score of the left and right hands based on the left and right hand coordinates in the key information of each frame of the personnel. Determine whether there is an oscillation cycle based on the cumulative peak score and cumulative valley score of the left and right hands.

[0025] Specifically, in this embodiment of the invention, the arm swing process in the standing long jump exhibits periodic fluctuations in the vertical direction. The highest point of the forward or backward swing corresponds to the trough value in the period, and the lowest point (when the arm is perpendicular to the ground) corresponds to the peak value in the period. The inflection points are used to determine the peak and trough values ​​in the periodic fluctuation data. Here, since the positive direction of the y-axis in the video image is downward, the downward coordinate is larger. The method for calculating the swing pattern of the left / right hand based on the left / right hand coordinates is described in detail below.

[0026] S3: When the judgment result is that there is an oscillation period, determine the number of frames for each peak value, the number of frames for each valley value, the oscillation amplitude of each valley value, and the oscillation direction of each valley value on the left and right sides respectively.

[0027] Specifically, in this embodiment of the invention, when the determination result is that there is an oscillation period, the method for determining the number of frames of each peak value, the number of frames of each valley value, the oscillation amplitude of each valley value, and the oscillation direction of each valley value of the left / right hand is described in detail below.

[0028] S4: Calculate the foot lift-off score and knee extension score for each frame based on the key information of each frame. Determine whether the person is in the take-off state based on the foot lift-off score and knee extension score for each frame. If the determination result is that the person is in the take-off state, obtain the frame number corresponding to the first time the person is in the take-off state.

[0029] Specifically, in this embodiment of the invention, the score of the degree of foot lift-off and the score of knee extension of each frame are calculated based on the key information of the person in each frame. The person is determined to be in the take-off state based on the score of the degree of foot lift-off and the score of knee extension of each frame. When the determination result is that the person is in the take-off state, the method for obtaining the frame number corresponding to the time when the person is in the take-off state for the first time is described in detail below.

[0030] S5: Evaluate the arm swing action of the personnel from preparation to takeoff based on the cumulative peak score of the left hand, cumulative peak score of the right hand, cumulative trough score of the left hand, cumulative trough score of the right hand, number of frames for each peak in the left hand, number of frames for each peak in the right hand, number of frames for each trough in the left hand, number of frames for each trough in the right hand, swing amplitude of each trough in the left hand, swing amplitude of each trough in the right hand, swing direction of each trough in the left hand, and swing direction of each trough in the right hand.

[0031] Specifically, in this embodiment of the invention, the method for evaluating the arm swinging motion of a person from preparation to takeoff is described in detail below based on the cumulative peak score of the left hand, the cumulative peak score of the right hand, the cumulative trough score of the left hand, the cumulative trough score of the right hand, the number of frames for each peak of the left hand, the number of frames for each peak of the right hand, the number of frames for each trough of the left hand, the number of frames for each trough of the right hand, the swing amplitude of each trough of the left hand, the swing amplitude of each trough of the right hand, the swing direction of each trough of the left hand, and the swing direction of each trough of the right hand.

[0032] S6: Evaluate the attitude during take-off based on key information from the frame number corresponding to the jumper's take-off state.

[0033] Furthermore, in the above-mentioned vision-based standing long jump arm swing detection method, step S1 involves acquiring key information for each frame of the person, including: acquiring the coordinates of the left shoulder, right shoulder, left elbow, right elbow, left hand, right hand, left hip, right hip, left knee, right knee, left foot, and right foot through a camera.

[0034] Specifically, in the embodiments of the present invention, This represents the coordinates of the left shoulder in the i-th frame. This represents the coordinates of the right shoulder in the i-th frame. This represents the coordinates of the left elbow in the i-th frame. This represents the right elbow coordinate of the i-th frame. This represents the left-hand coordinates of the i-th frame. This represents the right-hand coordinate of the i-th frame. This represents the coordinates of the left hip in the i-th frame. This represents the coordinates of the right hip in the i-th frame. This represents the coordinates of the left knee in the i-th frame. This represents the coordinate of the right knee in the i-th frame. This represents the coordinates of the left foot in the i-th frame. This represents the coordinates of the right foot in the i-th frame.

[0035] Furthermore, the aforementioned vision-based standing long jump arm swing detection method also includes: If the result indicates that there is no oscillation period, the analysis is stopped.

[0036] Furthermore, in the aforementioned vision-based standing long jump arm swing detection method, combined with... Figure 2 Step S2 specifically includes five steps from S21 to S25: S21: Calculate the foundation height based on the left / right hand coordinates.

[0037] Specifically, in this embodiment of the invention, taking the left hand as an example, the base height is calculated using the following formula when frame number i > 3: in, This represents the left-hand ordinate of the m-th frame, where m is the frame number, the same as i. This represents the base height of the i-th frame.

[0038] S22: Calculate the left / right peak score and left / right valley score for each frame based on the base height and left / right coordinates.

[0039] Specifically, in this embodiment of the invention, taking the left hand as an example, the left-hand peak score and left-hand valley score for each frame are calculated using the following formula: in, This represents the left-hand peak score in the m-th frame. The left-hand valley value is shown in the m-th frame. This indicates the set fluctuation height threshold, which defaults to 30 pixels.

[0040] S23: Accumulate the peak scores of the left and right hands to obtain the cumulative peak scores of the left and right hands, and accumulate the valley scores of the left and right hands to obtain the cumulative valley scores of the left and right hands.

[0041] Specifically, in this embodiment of the invention, taking the left hand as an example, the cumulative peak score and the cumulative valley score of the left hand are obtained through the following formula: in, This indicates the cumulative peak score for the left hand. This represents the cumulative valley value in the left hand.

[0042] S24: Determine the difference between the cumulative peak score of the left / right hand and the preset peak score threshold, and the difference between the cumulative valley score of the left / right hand and the preset valley score threshold.

[0043] Specifically, in this embodiment of the invention, taking the left hand as an example, the magnitude of the cumulative peak score of the left hand and the preset peak score threshold 2 are determined, as well as the magnitude of the cumulative valley score of the left hand and the preset valley score threshold 2.

[0044] S25: When the judgment result is that the cumulative peak score of the left / right hand is greater than the preset peak score threshold and the cumulative valley score of the left / right hand is greater than the preset valley score threshold, the judgment result is that there is an oscillation cycle.

[0045] Specifically, in this embodiment of the invention, taking the left hand as an example, when the judgment result is that the cumulative peak score of the left hand is greater than the preset peak score threshold 2 and the cumulative valley score of the left hand is greater than the preset valley score threshold 2, the judgment result is that there is an oscillation cycle.

[0046] It should be understood that steps S21 to S25 involve: calculating the base height based on the left-hand coordinates; calculating the left-hand peak score and left-hand valley score for each frame based on the base height and left-hand coordinates; accumulating the left-hand peak scores to obtain the left-hand cumulative peak score, and accumulating the left-hand valley scores to obtain the left-hand cumulative valley score; comparing the left-hand cumulative peak score with a preset peak score threshold, and the left-hand cumulative valley score with a preset valley score threshold; and determining the result when the left-hand cumulative peak score is greater than the preset peak score threshold and the left-hand cumulative valley score is greater than the preset valley score threshold, then the result is... There is a swing period; and, the base height is calculated based on the right-hand coordinates; the right-hand peak score and right-hand valley score of each frame are calculated based on the base height and the right-hand coordinates; the right-hand peak score is accumulated to obtain the right-hand cumulative peak score, and the right-hand valley score is accumulated to obtain the right-hand cumulative valley score; the right-hand cumulative peak score is compared with a preset peak score threshold, and the right-hand cumulative valley score is compared with a preset valley score threshold; when the judgment result is that the right-hand cumulative peak score is greater than the preset peak score threshold and the right-hand cumulative valley score is greater than the preset valley score threshold, the judgment result is that there is a swing period.

[0047] Furthermore, in the aforementioned vision-based standing long jump arm swing detection method, combined with... Figure 3 Step S3 specifically includes four steps: S31 to S34. S31: When the judgment result is that there is a swing period, determine the peak interval score of each frame of the left and right hands based on the cumulative peak scores of the left and right hands, and determine the valley interval score of each frame of the left and right hands based on the cumulative valley scores of the left and right hands.

[0048] Specifically, in this embodiment of the invention, taking the left hand as an example, the peak interval score and the valley interval score of each frame of the left hand are determined by the following formula: Where j is the index of the peak interval and k is the index of the valley interval. This represents the interval score of the j-th peak in the m-th frame. This shows the valley interval score for the kth frame in the m-th frame.

[0049] S32: Determine the number of frames for each peak and each valley in the left and right hands based on the peak interval score and valley interval score for each frame in the left and right hands.

[0050] Specifically, in this embodiment of the invention, taking the left hand as an example, the number of frames for each peak and the number of frames for each valley in the left hand are determined by the following formula: in, This indicates the frame number of the j-th peak in the left-hand side. This represents the frame number of the k-th valley value on the left.

[0051] S33: Determine the swing amplitude of each valley value of the left / right hand based on the left / right hand coordinates and the left / right shoulder coordinates.

[0052] Specifically, in this embodiment of the invention, taking the left hand as an example, the swing amplitude of each valley value of the left hand is determined by the following formula: Here, the amplitude of the swing is determined by calculating the cosine value formed by the arm and torso when the arm swings forward or backward to its highest point. The larger the swing amplitude, the larger the corresponding angle and the smaller the cosine value. This represents the swing amplitude of the kth valley value on the left hand.

[0053] S34: Determine the swing direction of each valley value of the left / right hand based on the left / right hand coordinates and the left / right shoulder coordinates.

[0054] Specifically, in this embodiment of the invention, taking the left hand as an example, the swing direction of each valley value of the left hand is determined by the following formula: here, This indicates the swing direction of the kth valley value on the left hand.

[0055] Using the same method as above, obtain the cumulative peak score of the right hand. The cumulative valley value of the right hand The number of frames for the j-th peak on the right side The number of frames for the kth valley value on the right side The swing amplitude of the kth valley value on the right side And the swing direction of the kth valley value on the right side .

[0056] It should be understood that steps S31 to S34 are as follows: when the judgment result indicates the existence of a swing cycle, determine the peak interval score of each frame of the left hand based on the cumulative peak score of the left hand, and determine the valley interval score of each frame of the left hand based on the cumulative valley score of the left hand; determine the number of frames for each peak and each valley value of the left hand based on the peak interval score and valley interval score of each frame of the left hand; determine the swing amplitude of each valley value of the left hand based on the left hand coordinates and left shoulder coordinates; determine the swing direction of each valley value of the left hand based on the left hand coordinates and left shoulder coordinates; and when the judgment result indicates the existence of a swing cycle, determine the peak interval score of each frame of the right hand based on the cumulative peak score of the right hand, and determine the valley interval score of each frame of the right hand based on the cumulative valley score of the right hand; determine the number of frames for each peak and each valley value of the right hand based on the peak interval score and valley interval score of each frame of the right hand; determine the swing amplitude of each valley value of the right hand based on the right hand coordinates and right shoulder coordinates; determine the swing direction of each valley value of the right hand based on the right hand coordinates and right shoulder coordinates.

[0057] Furthermore, in the aforementioned vision-based standing long jump arm swing detection method, combined with... Figure 4 Step S4 specifically includes four steps from S41 to S44: S41: Calculate the score for the degree of foot lift-off in each frame based on the left and right foot coordinates of the person in each frame.

[0058] Specifically, in this embodiment of the invention, the score for the degree of foot lift-off in each frame is calculated using the following formula: in, This represents the score for the degree to which the foot is off the ground in the i-th frame. The set ground clearance threshold, with a default value of 20.

[0059] S42: Determine the knee extension score based on the coordinates of the left foot, right foot, left hip, right hip, left knee, and right knee of the person in each frame.

[0060] in, This represents the knee extension score in the i-th frame.

[0061] S43: Determine whether the foot lift-off score is equal to the preset foot lift-off score threshold and whether the knee extension score is less than the preset knee extension score threshold.

[0062] Specifically, in this embodiment of the invention, it is determined whether the foot lift-off score is equal to a preset foot lift-off score threshold 1 and whether the knee extension score is less than a preset knee extension score threshold. .

[0063] S44: When the judgment result is that the foot lift-off score is equal to the preset foot lift-off score threshold and the knee extension score is less than the preset knee extension score threshold, the judgment result is that the person is in the jumping state, and the number of frames corresponding to the time when the person is in the jumping state for the first time is obtained.

[0064] Specifically, in this embodiment of the invention, when the judgment result is that the foot lift-off score is equal to a preset foot lift-off score threshold of 1 and the knee extension score is less than a preset knee extension score threshold, the determination is made based on whether the knee extension score is equal to a preset knee extension score threshold. If the result indicates that the person is in the jumping state, then the frame number corresponding to the time when the person first entered the jumping state is obtained. .

[0065] Furthermore, in the aforementioned vision-based standing long jump arm swing detection method, combined with... Figure 5 Step S5 specifically includes five steps from S51 to S55: S51: Determine the frequency synchronization score of the two arms based on the cumulative peak score of the left hand, the cumulative peak score of the right hand, the cumulative valley score of the left hand, the cumulative valley score of the right hand, the number of frames for each peak in the left hand, the number of frames for each peak in the right hand, the number of frames for each valley in the left hand, and the number of frames for each valley in the right hand.

[0066] Specifically, in this embodiment of the invention, the formula for determining the frequency synchronization score of the two arms is expressed as follows: in, This represents the frequency synchronization score of the two arms, which is used to analyze whether the frequencies of the two arms are synchronized.

[0067] S52: The arm swing degree of both arms is scored synchronously based on the cumulative trough score of the left hand, the cumulative trough score of the right hand, the swing amplitude of each trough value of the left hand, and the swing amplitude of each trough value of the right hand.

[0068] Specifically, in this embodiment of the invention, the formula for determining the synchronous score of the arm swing degrees of both arms is expressed as follows: in, The score indicates the synchronization of the arm swing. The synchronization score of the arm swing is used to analyze whether the arm swing is synchronized.

[0069] S53: Determine the arm swing direction score based on the cumulative trough score of the left hand, the cumulative trough score of the right hand, the swing direction of each trough value of the left hand, and the swing direction of each trough value of the right hand.

[0070] Specifically, in this embodiment of the invention, the formula for determining the direction score of the arm swing degree is expressed as follows: in, The score represents the degree and direction of the arm swing, which is used to analyze whether the two arms swing in the same direction.

[0071] S54: Determine the magnitude of the frequency synchronization score of the two arms compared to the preset frequency synchronization score threshold, the magnitude of the arm swing degree synchronization score of the two arms compared to the preset arm swing degree synchronization score threshold, and the magnitude of the arm swing degree direction score of the two arms compared to the preset arm swing degree direction score threshold.

[0072] Specifically, in this embodiment of the invention, the frequency synchronization score of the two arms is compared with a preset frequency synchronization score threshold of 0.8, the arm swing degree synchronization score of the two arms is compared with a preset arm swing degree synchronization score threshold of 0.9, and the arm swing degree direction score of the two arms is compared with a preset arm swing degree direction score threshold of 0.9.

[0073] S55: When the judgment result is that the frequency synchronization score of both arms is greater than the preset frequency synchronization score threshold, the swing degree synchronization score of both arms is greater than the preset swing degree synchronization score threshold, and the swing degree direction score of both arms is greater than the preset swing degree direction score threshold, the judge's arms swing in a regular periodic manner before take-off.

[0074] Specifically, in this embodiment of the invention, when the judgment result is that the frequency synchronization score of the two arms is greater than the preset frequency synchronization score threshold of 0.8, the arm swing degree synchronization score of the two arms is greater than the preset arm swing degree synchronization score threshold of 0.9, and the arm swing degree direction score of the two arms is greater than the preset arm swing degree direction score threshold of 0.9, the judge determines that the person swings their arms in a regular periodic manner before taking off.

[0075] It should be understood that when the judgment result is that the frequency synchronization score of the two arms is less than or equal to the preset frequency synchronization score threshold of 0.8, it means that the swing frequency of the two arms is not synchronized. When the swing degree synchronization score of the two arms is less than or equal to the preset swing degree synchronization score threshold of 0.9, it means that the amplitude of the two arms swing is significantly different. In particular, when it is 0, it means that the person hardly swings their arms. When the swing degree direction score of the two arms is less than or equal to the preset swing degree direction score threshold of 0.9, it means that the swing direction is different. These are all non-standard behaviors.

[0076] Furthermore, in the aforementioned vision-based standing long jump arm swing detection method, combined with... Figure 6 Step S6 specifically includes five steps from S61 to S65: S61: Determine the left-side posture score of the person based on the left shoulder coordinate, left elbow coordinate, left hand coordinate, and left knee coordinate of the frame corresponding to the person's take-off state.

[0077] Specifically, in this embodiment of the invention, it refers to the frame number corresponding to the person being in the jumping state. The left pose score is determined by the following formula: in, This indicates the score for the left-side posture.

[0078] S62: Determine the right-side posture score of the person based on the right shoulder coordinate, right elbow coordinate, right hand coordinate, and right knee coordinate of the frame corresponding to the person's take-off state.

[0079] Specifically, in this embodiment of the invention, it refers to the frame number corresponding to the person being in the jumping state. The right-side pose score is determined using the following formula: in, The score indicates the person's right-side posture.

[0080] S63: Determine the person's posture coordination score based on the person's left-side posture score and the person's right-side posture score.

[0081] Specifically, in this embodiment of the invention, the posture coordination score of a person is determined by the following formula: in, This indicates the score for posture coordination.

[0082] S64: Determine the person's posture coordination score and the value of the preset sway threshold.

[0083] Specifically, in this embodiment of the invention, the score of a person's posture coordination is compared with the preset swing threshold of 0.1.

[0084] S65: When the judgment result is that the person's posture coordination score is less than the preset swing threshold, it is determined that the person's arm swing posture at the time of take-off is in accordance with the standard.

[0085] Specifically, in this embodiment of the invention, when the judgment result is that the person's posture coordination score is less than the preset swing threshold of 0.1, it is determined that the person's arm swing posture meets the standard when jumping.

[0086] A second aspect of the present invention also provides an electronic device comprising: a processor and a memory; The processor executes any of the above vision-based standing long jump arm detection methods by calling programs or instructions stored in memory.

[0087] In a third aspect, the present invention also provides a computer-readable storage medium storing a program or instructions that cause a computer to execute a vision-based standing long jump arm swing detection method as described above.

[0088] Figure 7 This is a schematic block diagram of an electronic device provided in an embodiment of the present invention.

[0089] like Figure 7 As shown, the electronic device includes at least one processor 701, at least one memory 702, and at least one communication interface 703. The various components of the electronic device are coupled together via a bus system 704. The communication interface 703 is used for information transmission with external devices. It is understood that the bus system 704 is used to implement communication between these components. In addition to a data bus, the bus system 704 also includes a power bus, a control bus, and a status signal bus. However, for clarity, ... Figure 7 The general designated all buses as Bus System 704.

[0090] It is understood that the memory 702 in this embodiment can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0091] In some implementations, memory 702 stores elements such as executable units or data structures, or subsets thereof, or extended sets thereof: operating systems and applications.

[0092] The operating system includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. The application programs include various applications, such as media players and browsers, used to implement various application functions. The program implementing any method in the vision-based standing long jump arm detection method provided in this embodiment of the invention can be included in the application programs.

[0093] In this embodiment of the invention, the processor 701 executes the steps of various embodiments of the vision-based standing long jump swing arm detection method provided in this embodiment of the invention by calling the program or instructions stored in the memory 702, specifically, the program or instructions stored in the application program.

[0094] S1: When personnel enter the standing long jump area to prepare, acquire key information about the personnel in each frame; S2: Calculate the cumulative peak score and cumulative valley score of the left and right hands based on the left and right hand coordinates in the key information of each frame of the personnel, and determine whether there is an oscillation cycle based on the cumulative peak score and cumulative valley score of the left and right hands; S3: When the judgment result is that there is an oscillation period, determine the number of frames for each peak value, the number of frames for each valley value, the oscillation amplitude of each valley value, and the oscillation direction of each valley value on the left and right sides respectively; S4: Calculate the foot lift-off score and knee extension score for each frame based on the key information of each frame. Determine whether the person is in the take-off state based on the foot lift-off score and knee extension score for each frame. Obtain the frame number corresponding to the time when the person first enters the take-off state. S5: Evaluate the arm swing action of the personnel from preparation to takeoff based on the cumulative peak score of the left hand, cumulative peak score of the right hand, cumulative trough score of the left hand, cumulative trough score of the right hand, number of frames for each peak in the left hand, number of frames for each peak in the right hand, number of frames for each trough in the left hand, number of frames for each trough in the right hand, swing amplitude of each trough in the left hand, swing amplitude of each trough in the right hand, swing direction of each trough in the left hand, and swing direction of each trough in the right hand. S6: Evaluate the attitude during take-off based on key information from the frame number corresponding to the jumper's take-off state.

[0095] Any method in the vision-based standing long jump arm detection method provided in this embodiment of the invention can be applied to, or implemented by, the processor 701. The processor 701 can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed through integrated logic circuits in the hardware of the processor 701 or through software instructions. The processor 701 can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor.

[0096] The steps of any method in the vision-based standing long jump arm detection method provided in this embodiment of the invention can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software units in the decoding processor. The software units can reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 702, and processor 701 reads the information in memory 702 and combines it with hardware to complete the steps of the method.

[0097] Those skilled in the art will understand that although some embodiments described herein include certain features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention and form different embodiments.

[0098] Those skilled in the art will understand that the descriptions of the various embodiments have different focuses, and for parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0099] Although embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention. All such modifications and variations fall within the scope defined by the appended claims. The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0100] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A vision-based method for detecting the arm swing in a standing long jump, characterized in that, It includes six steps, S1 to S6: S1: When personnel enter the standing long jump area to prepare, acquire key information about the personnel in each frame; S2: Calculate the cumulative peak score and cumulative valley score of the left and right hands based on the left and right hand coordinates in the key information of each frame of the personnel, and determine whether there is an oscillation cycle based on the cumulative peak score and cumulative valley score of the left and right hands; S3: When the judgment result is that there is an oscillation period, determine the number of frames for each peak value, the number of frames for each valley value, the oscillation amplitude of each valley value, and the oscillation direction of each valley value on the left and right sides respectively; S4: Calculate the foot lift-off score and knee extension score for each frame based on the key information of each frame. Determine whether the person is in the take-off state based on the foot lift-off score and knee extension score for each frame. If the determination result is that the person is in the take-off state, obtain the frame number corresponding to the first time the person is in the take-off state. S5: Evaluate the arm swing action of the personnel from preparation to takeoff based on the cumulative peak score of the left hand, cumulative peak score of the right hand, cumulative trough score of the left hand, cumulative trough score of the right hand, number of frames for each peak in the left hand, number of frames for each peak in the right hand, number of frames for each trough in the left hand, number of frames for each trough in the right hand, swing amplitude of each trough in the left hand, swing amplitude of each trough in the right hand, swing direction of each trough in the left hand, and swing direction of each trough in the right hand. S6: Evaluate the attitude during take-off based on key information from the frame number corresponding to the jumper's take-off state.

2. The vision-based standing long jump arm swing detection method according to claim 1, characterized in that, In step S1, key information for each frame of the person is obtained, including: left shoulder coordinates, right shoulder coordinates, left elbow coordinates, right elbow coordinates, left hand coordinates, right hand coordinates, left hip coordinates, right hip coordinates, left knee coordinates, right knee coordinates, left foot coordinates, and right foot coordinates obtained through the camera.

3. The vision-based standing long jump arm swing detection method according to claim 1, characterized in that, The method further includes: If the result indicates that there is no oscillation period, the analysis is stopped.

4. The vision-based standing long jump arm swing detection method according to claim 1, characterized in that, Step S2 specifically includes: Calculate the foundation height based on the left / right hand coordinates; Calculate the left / right peak score and left / right valley score for each frame based on the base height and left / right coordinates; The cumulative peak score for the left and right hands is obtained by accumulating the peak scores for the left and right hands, and the cumulative trough score for the left and right hands is obtained by accumulating the trough scores for the left and right hands. Determine the magnitude of the cumulative peak score of the left / right hand and the preset peak score threshold, and the magnitude of the cumulative trough score of the left / right hand and the preset trough score threshold; If the judgment result is that the cumulative peak score of the left / right hand is greater than the preset peak score threshold and the cumulative trough score of the left / right hand is greater than the preset trough score threshold, then the judgment result is that there is an oscillation cycle.

5. The vision-based standing long jump arm swing detection method according to claim 1, characterized in that, Step S3 specifically includes: When the judgment result is that there is a swing period, the peak interval score of each frame of the left and right hands is determined according to the cumulative peak score of the left and right hands, and the valley interval score of each frame of the left and right hands is determined according to the cumulative valley score of the left and right hands. The number of frames for each peak and the number of frames for each valley in the left and right hands are determined based on the peak interval score and valley interval score for each frame in the left and right hands. The swing amplitude of each valley value of the left / right hand is determined based on the left / right hand coordinates and the left / right shoulder coordinates; The swing direction of each valley value on the left / right hand is determined based on the left / right hand coordinates and the left / right shoulder coordinates.

6. The vision-based standing long jump arm swing detection method according to claim 1, characterized in that, Step S4 specifically includes: The score for the degree of foot lift-off in each frame is calculated based on the left and right foot coordinates of the person in each frame. The knee extension score is determined based on the coordinates of the left foot, right foot, left hip, right hip, left knee, and right knee of the person in each frame. Determine whether the foot lift-off score is equal to the preset foot lift-off score threshold and whether the knee extension score is less than the preset knee extension score threshold. If the judgment result is that the foot lift-off score is equal to the preset foot lift-off score threshold and the knee extension score is less than the preset knee extension score threshold, then the judgment result is that the person is in the take-off state, and the number of frames corresponding to the first time the person is in the take-off state is obtained.

7. The vision-based standing long jump arm swing detection method according to claim 1, characterized in that, Step S5 specifically includes: The frequency synchronization score of the two arms is determined based on the cumulative peak score of the left hand, the cumulative peak score of the right hand, the cumulative trough score of the left hand, the cumulative trough score of the right hand, the number of frames for each peak in the left hand, the number of frames for each peak in the right hand, the number of frames for each trough in the left hand, and the number of frames for each trough in the right hand. The arm swing degree of both arms is scored synchronously based on the cumulative trough score of the left hand, the cumulative trough score of the right hand, the swing amplitude of each trough value of the left hand, and the swing amplitude of each trough value of the right hand. The degree and direction of arm swing are determined by the cumulative valley value of the left hand, the cumulative valley value of the right hand, the swing direction of each valley value of the left hand, and the swing direction of each valley value of the right hand. The system determines the relative magnitudes of the frequency synchronization scores of the two arms, the relative magnitudes of the arm swing degree synchronization scores, and the relative magnitudes of the arm swing direction scores. When the judgment result is that the frequency synchronization score of both arms is greater than the preset frequency synchronization score threshold, the swing degree synchronization score of both arms is greater than the preset swing degree synchronization score threshold, and the swing degree direction score of both arms is greater than the preset swing degree direction score threshold, the judge will swing his arms in a regular periodic manner before taking off.

8. The vision-based standing long jump arm swing detection method according to claim 1, characterized in that, Step S6 specifically includes: The left-side posture score of the person is determined based on the left shoulder coordinate, left elbow coordinate, left hand coordinate, and left knee coordinate of the frame corresponding to the person's take-off state. The right-side posture score of the person is determined based on the right shoulder coordinate, right elbow coordinate, right hand coordinate, and right knee coordinate of the frame corresponding to the person's take-off state. The person's posture coordination score is determined based on the person's left-side posture score and the person's right-side posture score; The score of a person's posture coordination is compared with the preset swing threshold. When the judgment result is that the person's posture coordination score is less than the preset swing threshold, it is determined that the person's arm swing posture at the time of take-off is in accordance with the standard.

9. An electronic device, characterized in that, include: Processor and memory; The processor executes a vision-based standing long jump arm swing detection method as described in any one of claims 1 to 8 by calling the program or instructions stored in the memory.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program or instructions that cause a computer to perform a vision-based standing long jump arm swing detection method as described in any one of claims 1 to 8.

Images