Method and apparatus for evaluating a vertical jump action in place
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- NANJING INST OF TECH
- Filing Date
- 2024-07-22
- Publication Date
- 2026-07-24
AI Technical Summary
Existing technologies for evaluating vertical jump in place require high computing power, involve complex human skeletal point recognition, and have a single evaluation dimension, which can easily lead to incorrect evaluations and lacks reference value.
By acquiring motion image sequences of test subjects, identifying skeletal point positions, judging whether the posture of the arms and legs, trunk swing, and hip and knee joint rotation meet the standards, establishing a three-dimensional coordinate system, evaluating vertical jump movements from multiple dimensions, and calculating quality scores.
It enables real-time evaluation with low computing power requirements, provides accurate multi-dimensional evaluation results with reference value, and reduces equipment costs and evaluation errors.
Smart Images
Figure CN118976232B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of athletic ability assessment technology, and in particular to a method and apparatus for assessing standing vertical jump. Background Technology
[0002] Vertical jumps in place are a common aerobic exercise and a frequently used training movement in many fitness programs. They effectively strengthen lower limb muscles, improve cardiovascular function, and enhance physical fitness and endurance. They require no equipment and can be performed anytime, anywhere, making them a very convenient and effective form of exercise. However, proper vertical jump technique hinges on the jump height, stability, and the presence or absence of compensatory movements. Improper vertical jumps or overexertion can lead to strain on the bones and joints. In particular, imbalances and excessive compensatory movements during the exercise can cause serious damage to leg muscles and ankles. Therefore, standardized monitoring of vertical jump technique is crucial.
[0003] In existing technologies, most evaluation schemes for standing vertical jumps rely on neural network models for recognition. However, these methods suffer from several problems. The processing of human skeletal points requires preprocessing, making it impractical for users. Furthermore, using neural networks to process video input and obtain coordinate information of human skeletal points places extremely high demands on the computing power of the equipment and is complex. The recognition and classification of human features are also limited by the features contained in the training parameters of the neural network model, which can easily lead to incorrect evaluations. In addition, there is a lack of evaluation of categorized postures (vertical jump stability, motion compensation, etc.) during the vertical jump, resulting in a single evaluation dimension and a lack of reference value in the evaluation results. Summary of the Invention
[0004] Purpose of the invention: This invention provides a method and device for evaluating vertical jump in place, aiming to solve the technical problems in the prior art, such as extremely high requirements for equipment computing power, the need for preprocessing to identify human skeletal points, the limitations of the features contained in the training parameters of the neural network model, the susceptibility to erroneous evaluation, and the lack of reference for the single evaluation dimension of vertical jump.
[0005] Technical Solution: This invention provides a method for evaluating standing vertical jump, comprising: a tester performing a standing vertical jump and acquiring a sequence of motion images during the tester's movement; selecting feature motion images from the sequence of motion images and determining the skeletal points of the tester in the motion images; determining whether the posture and position of the tester's arms and legs conform to the take-off specifications based on the skeletal points in the feature motion images during the tester's take-off movement; if they conform to the take-off specifications, the tester's standing vertical jump is deemed valid; determining whether the tester's torso swing amplitude conforms to the vertical jump specifications based on the skeletal points in the jump movements of the tester in the feature motion images; determining whether the rotation amplitude of the tester's hip and knee joints and feet conforms to the no-compensation specification based on the skeletal points in the tester's take-off and landing movements of the tester in the feature motion images; and providing the evaluation results of the tester's movement.
[0006] Specifically, the locations of the skeletal points include: the central lumbar vertebra, left shoulder, right shoulder, left heel, right heel, left toe, right toe, left elbow joint, right elbow joint, left knee joint, right knee joint, left hip joint, right hip joint, throat, and groin.
[0007] Specifically, from the motion image sequence, the motion image with the highest height of the test subject above the ground is selected, and the shooting time of the motion image with the highest height above the ground is used as the first reference time. Jump motion images before and after the first reference time are selected according to a predetermined time interval. From the motion image sequence, the motion image with the lowest squatting position of the test subject is selected, and the shooting time of the motion image with the lowest squatting position is used as the second reference time. Jump motion images before and after the second reference time are selected according to a predetermined time interval. From the motion image sequence, the motion image of the test subject landing and contacting the ground is selected, and the shooting time of the motion image of landing and contacting the ground is used as the third reference time. Landing motion images after the third reference time are selected according to a predetermined time interval. The selected jump motion images, jump motion images, and landing motion images are used as feature motion images.
[0008] Specifically, the take-off specifications include: the distances from the left heel to the central lumbar spine and the right heel to the central lumbar spine, with the distance deviation less than a first distance threshold; the distance from the left heel to the right heel being greater than the distance from the left shoulder to the right shoulder, and the distance difference being less than a second distance threshold; the distances from the left shoulder to the left elbow joint and the right shoulder to the right elbow joint being greater than the swing distance threshold; the angles of the left elbow joint and the right elbow joint being less than a first angle threshold; and the angles of the left knee joint and the right knee joint being less than a second angle threshold.
[0009] Specifically, the vertical jump height of the tester is determined to meet the jumping standard by the position of the skeletal points in the jump action of the tester in the feature motion image; the knee flexion action of the tester is determined to meet the landing standard by the position of the skeletal points in the landing action of the tester in the feature motion image; the landing standard includes: the angle of the left knee joint and the angle of the right knee joint are both less than the third angle threshold; if the take-off standard, the jump standard and the landing standard are met at the same time, the tester's standing vertical jump is considered valid.
[0010] Specifically, the vertical jump specifications include: the x-axis distance from the left shoulder to the vertical line containing the central lumbar spine, and the x-axis distance from the right shoulder to the vertical line containing the central lumbar spine, with the x-axis distance deviation being less than a third distance threshold; the y-axis distance from the left shoulder to the vertical line containing the central lumbar spine, and the y-axis distance from the right shoulder to the vertical line containing the central lumbar spine, with the y-axis distance deviation being less than a fourth distance threshold; the vertical swing angle formed by the lines connecting the throat to the groin and the central lumbar spine, with the vertical swing angle variation being less than a fourth angle threshold; and establishing a three-dimensional coordinate system with the central lumbar spine as the origin, the direction of the tester's shoulders as the x-axis, the direction from the heel to the toe as the y-axis, and the height direction as the z-axis.
[0011] Specifically, the non-compensation motion standard includes: a first hip-knee rotation angle formed by connecting the left hip joint with the left knee joint and the central lumbar vertebra, a second hip-knee rotation angle formed by connecting the right hip joint with the right knee joint and the central lumbar vertebra, the variation of the first hip-knee rotation angle and the second hip-knee rotation angle being less than a fifth angle threshold; a first y-axis distance between the left heel and the left toe, a second y-axis distance between the right heel and the right toe, the variation of the first y-axis distance and the second y-axis distance being less than a fifth distance threshold.
[0012] Specifically, provided that the tester's vertical jump in place is valid, if it meets both the vertical jump standard and the no-compensation standard, then the tester's action is judged to be a standard vertical jump in place.
[0013] Specifically, the height score is calculated based on the vertical jump height, the stability score is calculated based on the trunk swing amplitude, and the non-compensation score is calculated based on the rotation amplitude of the hip, knee and foot joints. The height score, stability score and non-compensation score are weighted and added together to obtain the quality score of the standing vertical jump.
[0014] This invention provides a standing vertical jump assessment device, comprising: an image acquisition unit, a skeletal point location determination unit, a take-off action assessment unit, a jump action assessment unit, a motion compensation assessment unit, and a comprehensive assessment unit, wherein: the image acquisition unit is used to acquire a sequence of motion images of the test subject performing a standing vertical jump; the skeletal point location determination unit is used to select feature motion images from the motion image sequence and determine the skeletal point locations of the test subject in the motion images; the take-off action assessment unit is used to determine the skeletal point locations of the test subject based on the skeletal point locations of the test subject's take-off action in the feature motion images. The test unit assesses whether the posture and position of the tester's arms and legs conform to the take-off specifications. If they do, the tester's vertical jump is considered valid. The jump action evaluation unit determines whether the tester's torso swing amplitude conforms to the vertical jump specifications by analyzing the skeletal points in the jump action of the tester in the feature action image. The motion compensation evaluation unit determines whether the rotation amplitude of the tester's hip, knee, and foot joints conforms to the non-motor compensation specifications by analyzing the skeletal points in the tester's take-off and landing actions of the tester in the feature action image. The comprehensive evaluation unit provides the judgment results of the tester's action evaluation.
[0015] Beneficial effects: Compared with the prior art, the present invention has the following significant advantages: it is real-time, allowing testers to conduct tests at any time; it does not require high computing power from the equipment; and by setting universal standards for vertical jump body posture and position, it evaluates vertical jump movements from multiple dimensions, resulting in more accurate evaluation results with reference value. Attached Figure Description
[0016] Figure 1 A schematic diagram of the vertical jump assessment device provided by the present invention;
[0017] Figure 2 This is a flowchart illustrating the vertical jump assessment method provided by the present invention. Detailed Implementation
[0018] The technical solution of the present invention will be further described below with reference to the accompanying drawings.
[0019] See Figure 1 This is a schematic diagram of the vertical jump assessment device provided by the present invention.
[0020] In practice, it includes a Microsoft Xbox 360 motion camera 1 on the front, a Microsoft Xbox 360 motion camera 2 on the other side, and a computer device 3 connected to the camera.
[0021] In its specific implementation, it should be noted that the Microsoft Xbox 360 Kinect used in this invention is a 3D motion-sensing camera peripheral with color and depth lenses, a voice microphone array, and a motorized base for automatically adjusting the Kinect's angle. The field of view is 57 degrees horizontally and 43 degrees vertically, with a physical tilt range of ±27 degrees. The depth-sensing distance is 1.2 meters to 3.5 meters. It also features a skeletal tracking system capable of simultaneously capturing the motion of two people. It relies on the camera to capture the user's movement in three-dimensional space and supports multilingual voice recognition, meeting the usage requirements of this invention.
[0022] In this specific implementation, the computer device 3 connected to the camera is a Lenovo Legion Y9000P 2023 (32GB / 2TB) with an Intel i9-13900HX CPU. It has 8 performance cores (P-Cores) and 16 energy efficiency cores (E-Cores), providing a total of 24 threads. Its computing speed and storage space can meet the requirements of video analysis and modeling for two high-definition cameras. It can generate human skeleton point coordinate system in real time as needed, and perform data analysis and data storage.
[0023] See Figure 2 This is a flowchart illustrating the vertical jump assessment method provided by the present invention.
[0024] In this embodiment of the invention, as described in step 1, the tester performs a vertical jump in place, and the image acquisition unit acquires the sequence of motion images of the tester during the motion process.
[0025] In practice, before entering the designated area, the Kinect motion cameras are positioned at an appropriate distance directly in front of and to the left of the user to ensure the human body is within the camera's field of view. It should be noted that the angles at which the two cameras used in this invention are positioned in front of and to the left of the user can be adjusted according to specific circumstances and the camera's detection capabilities.
[0026] In practice, after identity verification or login is completed, the Kinect body camera begins to identify the skeletal coordinates and key data of the tester, including shoulder width, upper arm length, forearm length, shoulder-vertebral distance, hip length, thigh length, calf length, and foot distance.
[0027] In practice, it should be noted that after the user stands in the designated area, they should prepare by standing with their feet slightly wider than shoulder-width apart, bending their knees and lowering their arms in a take-off position (refer to the specific requirements of the take-off standard). At the same time, the computer analyzes the data transmitted by the body camera to check whether the user's preparation posture is correct, and will issue a reminder if the preparation is incorrect.
[0028] In this embodiment of the invention, as described in step 2, feature motion images are selected from the motion image sequence, and the skeletal point position determination unit determines the skeletal point position of the tester in the motion image.
[0029] In this embodiment of the invention, the skeletal points include: the central lumbar vertebra, left shoulder, right shoulder, left heel, right heel, left toe, right toe, left elbow joint, right elbow joint, left knee joint, right knee joint, left hip joint, right hip joint, throat, and groin.
[0030] In practice, the coordinate position of the left shoulder is A(X). a ,Y a Z a The coordinates of the right shoulder are B(X). b ,Y b Z b The coordinate position of the left elbow joint is C(X). c ,Y c Z c The coordinates of the right elbow joint are D(X). d ,Y d Z d The coordinates of the central lumbar vertebra (the center point of the lumbar vertebrae) are E(X). e ,Y e Z e The coordinates of the left hip joint are F(X). f ,Y f Z f The coordinates of the right hip joint are G(X). g ,Y g Z g The coordinates of the left knee are H(X). h ,Y h Z h The coordinates of the right knee are I(X) i ,Y i Z i The coordinates of the left heel are J(X). j ,Y j Z j The coordinates of the right heel are K(X). k ,Y k Z k The coordinates of the throat point are M(X). m ,Y m Z m The coordinates of the groin point are N(X). n ,Y n Z n The coordinates of the left toe point are O(X). o ,Y o Zo The coordinates of the right toe point are P(X). p ,Y p Z p ).
[0031] In this embodiment of the invention, the action image with the highest height of the tester off the ground is selected from the action image sequence. The shooting time of the action image with the highest height off the ground is used as the first reference time. Jumping action images before and after the first reference time are selected according to a predetermined time interval (which can be set according to the actual application scenario). The action image with the lowest squatting position of the tester is selected from the action image sequence. The shooting time of the action image with the lowest squatting position is used as the second reference time. Jumping action images before and after the second reference time are selected according to a predetermined time interval. The action image of the tester landing (just touching the ground) is selected from the action image sequence. The shooting time of the action image of landing and touching the ground is used as the third reference time. Landing action images after the third reference time are selected according to a predetermined time interval. The selected jumping action images, jumping action images, and landing action images are used as feature action images.
[0032] In practice, by selecting multiple images of jumping, take-off, and landing, the body posture and the range of change of posture of the test personnel can be analyzed to determine whether the vertical jump conforms to the corresponding standards.
[0033] In practice, multiple images representing the tester's posture during the vertical jump are selected. Compared to video processing, image processing can significantly reduce the computing power requirements of the equipment.
[0034] In practice, the camera captures motion images of the test subject. The computer analyzes these images, selecting those showing jumping ability. Real-time data processing is then performed on the acquired images of human activity. Based on the Kinect motion camera, key skeletal coordinates are acquired. Connected to a host computer equipped with the Kinect SDK and a monitor, the coordinate position information is used to read skeletal node data via interface functions provided by the SDK, and then transmitted to the host computer's database. Finally, a Python program completes the calculations.
[0035] In this embodiment of the invention, as described in step 3, the take-off action evaluation unit determines whether the posture and position of the tester's arms and legs conform to the take-off specifications by using the skeletal point positions in the tester's take-off action in the feature action image. If they conform to the take-off specifications, the tester's vertical jump in place is deemed valid.
[0036] In practice, the jumping exercise requires the test subject to jump from a standing position, swinging their upper arms upwards and extending their abdomen in the air. Upon landing, they should consciously contract their abdomen and bend their knees. Compensation should include assessing whether the hip and knee joints rotate during takeoff and landing, as well as whether the feet rotate during takeoff and landing. The key points of the movement can be summarized as follows: Start in a straddle stance, bend your knees while swinging your arms downwards to prepare for the jump, jump from a standing position, swing your upper arms upwards, extend your abdomen in the air, and upon landing, consciously contract your abdomen, bend your knees to cushion the impact, and swing your arms downwards to return to the takeoff position.
[0037] In this embodiment of the invention, the take-off specifications include: the distance from the left heel to the central lumbar vertebra and the distance from the right heel to the central lumbar vertebra are less than a first distance threshold; the distance from the left heel to the right heel is greater than the distance from the left shoulder to the right shoulder, and the distance difference is less than a second distance threshold; the distance from the left shoulder to the left elbow joint and the distance from the right shoulder to the right elbow joint are both greater than the swing distance threshold; the angle between the left elbow joint and the right elbow joint are both less than a first angle threshold; and the angle between the left knee joint and the right knee joint are both less than a second angle threshold.
[0038] In practice, the deviation between the distance from the left heel to the central lumbar vertebra and the distance from the right heel to the central lumbar vertebra reflects the relative symmetry of the legs with respect to the body's centerline.
[0039] In practice, the distance from the left heel to the right heel is greater than the distance from the left shoulder to the right shoulder, and the distance between the feet should be slightly greater than the distance between the shoulders.
[0040] In practice, the distance from the left shoulder to the left elbow joint and the distance from the right shoulder to the right elbow joint indicate whether the arms swing down and the extent of the swing.
[0041] In practice, the angles between the left and right elbow joints reflect whether the arms are in a bent position and the degree of bending. The angles between the left and right elbow joints refer to the angles formed between the forearm and upper arm.
[0042] In practice, the angle between the left and right knee joints reflects whether both legs are in a flexed position and the degree of flexion. The angle between the left and right knee joints refers to the angle formed between the lower leg and the thigh.
[0043] In practice, the position, distance, and angle of the aforementioned skeletal nodes can be used to accurately determine the test subject's posture. If the vertical jump conforms to the specifications, it is considered valid, allowing for very quick and precise determination of the vertical jump.
[0044] In this embodiment of the invention, determining the validity of a tester's standing vertical jump further includes: judging whether the tester's vertical jump height conforms to the jumping specifications by using the skeletal point positions in the tester's jumping action in the feature motion image; judging whether the tester's knee flexion action conforms to the landing specifications by using the skeletal point positions in the tester's landing action in the feature motion image; the landing specifications include: the angle between the left knee joint and the right knee joint are both less than a third angle threshold; if the take-off specifications, jumping specifications, and landing specifications are all met simultaneously, then the tester's standing vertical jump is deemed valid.
[0045] In practice, to determine whether a tester's vertical jump height meets the jumping standards, one can judge whether the distance between the left or right toe and the ground meets the height requirements.
[0046] In practice, the abdominal contraction action can also be tested during the landing action. The angle formed by the lines connecting the central lumbar spine point with the shoulder and hip during the landing abdominal contraction action is between 0 and 180 degrees.
[0047] In practice, when analyzing the take-off criteria of the characteristic motion images of the vertical jump of the test personnel, it is possible to require that the human posture in all characteristic motion images meets the take-off criteria, or to require that the human posture in some (e.g., one-quarter to three-quarters) of the characteristic motion images meets the take-off criteria, or to require that the human posture in only one of the characteristic motion images meets the take-off criteria. The specific requirements can be set according to the actual situation.
[0048] In this embodiment of the invention, as described in step 4, the jumping action evaluation unit determines whether the tester's torso swing amplitude conforms to the vertical jump standard by using the skeletal point positions in the tester's jumping action in the feature action image.
[0049] In this embodiment of the invention, the vertical jump standard (used to determine vertical jump stability) includes: when determining the left-right swing of the torso, the x-axis distance from the left shoulder to the vertical line (a line perpendicular to the ground, the same below) and the x-axis distance from the right shoulder to the vertical line are both less than a third distance threshold; when determining the forward-backward swing of the torso, the y-axis distance from the left shoulder to the vertical line and the y-axis distance from the right shoulder to the vertical line are both less than a fourth distance threshold; when determining the vertical axis swing of the torso, the vertical swing angle formed by the lines connecting the throat to the groin and the central lumbar spine is less than a fourth angle threshold; a three-dimensional coordinate system is established with the central lumbar spine as the origin, the direction of the tester's shoulders as the x-axis, the direction from the heel to the toe as the y-axis, and the height direction as the z-axis.
[0050] In specific implementation, as described in step 4, the evaluation of the tester's jump stability should be based on the left-right / forward-backward / vertical swing angles of the two shoulder joint centers to determine whether the squatting torso swings left-right, forward-backward, or vertically, whether the squatting torso swings forward-backward, or vertically, whether the torso swings left-right, forward-backward, or vertically during takeoff, and whether the torso swings forward-backward or vertically during takeoff, and whether the torso swings backward-backward or vertically during takeoff.
[0051] In practice, the left-right sway of the torso is determined by the aforementioned x-axis distance deviation, i.e., |X a –X e |and|X b –X e The deviation between |
[0052] In practice, the forward and backward swing of the torso is determined by the aforementioned y-axis distance deviation, i.e., |Y a –Y e | and |Y b –Y e The deviation between the two distances can also be used to determine the distance. The y-axis distance between the left hip joint and the central lumbar vertebra is measured on the vertical line, and the y-axis distance between the right hip joint and the central lumbar vertebra is measured on the vertical line. If the deviation between these two y-axis distances is less than the fourth distance threshold, a judgment can be made.
[0053] In practice, the vertical axis sway of the torso is judged by the changes in the vertical sway angles mentioned above. The angles formed between the lines connecting the throat and groin, and the lines connecting the throat and the central lumbar vertebra, are used to determine the vertical sway angles. Alternatively, the angles formed by the lines connecting the central lumbar vertebra to the left (right) shoulder and left (right) hip joints, as detected by the left-side posture camera, are assessed to determine if the change in these angles exceeds a corresponding threshold.
[0054] In this embodiment of the invention, as described in step 5, the compensation assessment unit determines whether the rotation amplitude of the tester's hip and knee joints and feet conforms to the no-motor-compensation standard by using the skeletal point positions in the tester's jump and landing actions in the feature motion image, thereby determining whether the tester's hip and knee joints and feet have motor compensation.
[0055] In this embodiment of the invention, the non-compensation motion specification includes: a first hip-knee rotation angle formed by connecting the left hip joint with the left knee joint and the central lumbar vertebra, a second hip-knee rotation angle formed by connecting the right hip joint with the right knee joint and the central lumbar vertebra, the variation of the first hip-knee rotation angle and the second hip-knee rotation angle being less than a fifth angle threshold; a first y-axis distance between the left heel and the left toe, a second y-axis distance between the right heel and the right toe, the variation of the first y-axis distance and the second y-axis distance being less than a fifth distance threshold.
[0056] In practice, the change in the first hip-knee rotation angle is less than the fifth angle threshold, and the change in the second hip-knee rotation angle is less than the fifth angle threshold, reflecting whether the hip and knee joints rotate and the range of rotation during take-off and landing.
[0057] In practice, the change in the first y-axis distance is less than the fifth distance threshold, and the change in the second y-axis distance is less than the fifth distance threshold, which reflects whether the feet rotate and the magnitude of rotation during take-off and landing.
[0058] In practice, motor compensation reflects whether the tester uses the wrong muscle groups and joints to generate and bear force when performing a vertical jump, indicating whether the tester may cause serious damage to the leg muscles and ankles due to excessive motor compensation.
[0059] In practice, the aforementioned distance difference (deviation) and angle changes can be obtained by comparing the human body posture and skeletal positions in multiple feature motion images.
[0060] In practice, the first distance threshold, the second distance threshold, the hem distance threshold, the third distance threshold, the fourth distance threshold, the fifth distance threshold, the first included angle threshold, the second included angle threshold, the third included angle threshold, the fourth included angle threshold, and the fifth included angle threshold can be set according to the actual application scenario, which reflects the strictness of the vertical jump specification.
[0061] In this embodiment of the invention, as described in step 6, the comprehensive evaluation unit provides the judgment result of the tester's action evaluation.
[0062] In this embodiment of the invention, if the tester's vertical jump in place is valid and simultaneously meets the vertical jump standard and the no-compensation standard, then the tester's action is judged to be a standard vertical jump in place.
[0063] In this embodiment of the invention, the judgment result in step 6 mainly includes the following scoring points: a height score calculated based on the vertical jump height; a stability score calculated based on the trunk swing amplitude; and a non-compensation score calculated based on the rotation amplitude of the hip, knee, and foot joints. The height score, stability score, and non-compensation score are weighted and summed to calculate the quality score of the standing vertical jump.
[0064] In its implementation, this invention evaluates the importance and quality of movements during a standing vertical jump, categorizing them into three main categories and 12 subcategories. The three main categories include jump height, jump stability, and the absence of compensatory movements. Jump height accounts for n1 / N of the total score. Jump stability assessment includes evaluations of the following aspects of jump height: left-right trunk sway during squatting, forward-backward trunk sway during squatting, vertical axis sway during squatting, left-right trunk sway during takeoff, forward-backward trunk sway during takeoff, vertical axis sway during takeoff, and cushioned left-right trunk sway, forward-backward trunk sway, and cushioned vertical axis sway, each accounting for n2 / 9N of the total score, totaling n2 / N. The absence of compensatory movements includes hip and knee joint rotation during takeoff and landing, and foot rotation during takeoff and landing, each accounting for n3 / 2N of the total score, totaling n3 / N. The total score is calculated as: jump height score * 5 / 12 + jump stability score * 1 / 3 + compensatory movement score * 1 / 4.
[0065] This invention also provides a standing vertical jump assessment device, comprising: an image acquisition unit, a skeletal point position determination unit, a take-off action assessment unit, a jump action assessment unit, a motion compensation assessment unit, and a comprehensive assessment unit, wherein: the image acquisition unit is used to acquire a sequence of motion images of the test subject performing a standing vertical jump; the skeletal point position determination unit is used to select feature motion images from the motion image sequence and determine the skeletal point positions of the test subject in the motion images; the take-off action assessment unit is used to determine the skeletal point positions of the test subject in the take-off action based on the skeletal point positions of the test subject in the feature motion images. The tester assesses whether the posture and position of the tester's arms and legs conform to the take-off specifications. If they do, the tester's vertical jump is deemed valid. The jump action evaluation unit determines whether the tester's torso swing amplitude conforms to the vertical jump specifications by analyzing the skeletal point positions in the characteristic action image. The motion compensation evaluation unit determines whether the tester's hip, knee, and foot rotation amplitudes conform to the non-motor compensation specifications by analyzing the skeletal point positions in the tester's take-off and landing actions in the characteristic action image. The comprehensive evaluation unit provides the tester's action evaluation results.
[0066] In the embodiments of the present invention, the methods, steps or functions of the units in the standing vertical jump action evaluation device provided by the present invention can refer to the methods, steps or functions in the standing vertical jump action evaluation method provided by the present invention. Those skilled in the art can make various changes based on the spirit of this patent without changing its core purpose.
Claims
1. A method for evaluating standing vertical jump, characterized in that, include: The tester performs a vertical jump in place, and the sequence of motion images during the tester's action is obtained. Featured motion images are selected from the motion image sequence, and the skeletal points of the test subject are determined in the motion images; By analyzing the skeletal points in the tester's take-off motion in the feature motion image, we can determine whether the posture and position of the tester's arms and legs conform to the take-off specifications. If they conform to the take-off specifications, the tester's vertical jump in place is considered valid. By analyzing the skeletal points in the jump motion of the tester in the feature motion image, it can be determined whether the amplitude of the tester's torso swing conforms to the vertical jump standard. By analyzing the skeletal points in the tester's take-off and landing movements in the feature motion images, we can determine whether the rotation range of the tester's hip, knee, and foot joints conforms to the non-compensation motion standard. Provides the judgment results of the testers' actions.
2. The method for evaluating standing vertical jump according to claim 1, characterized in that, The locations of the skeletal points include: the central lumbar vertebra, left shoulder, right shoulder, left heel, right heel, left toe, right toe, left elbow joint, right elbow joint, left knee joint, right knee joint, left hip joint, right hip joint, throat, and groin.
3. The method for evaluating standing vertical jump according to claim 2, characterized in that, The step of selecting feature action images from the action image sequence includes: From the motion image sequence, select the motion image of the test subject at the highest altitude above the ground. Use the shooting time of the motion image at the highest altitude above the ground as the first reference time. Select jumping motion images before and after the first reference time according to a predetermined time interval. From the motion image sequence, select the motion image of the test subject at the lowest squatting position. Use the shooting time of the motion image at the lowest squatting position as the second reference time. Select take-off motion images before and after the second reference time according to a predetermined time interval. From the motion image sequence, select the motion image of the test subject landing and touching the ground. Use the shooting time of the motion image of landing and touching the ground as the third reference time. Select landing motion images after the third reference time according to a predetermined time interval. The selected jumping motion images, take-off motion images, and landing motion images are used as feature motion images.
4. The method for evaluating standing vertical jump according to claim 2, characterized in that, The determination of whether the posture and position of the test subject's arms and legs conform to the take-off specifications includes: The take-off criteria include: the distances from the left heel to the central lumbar spine and the right heel to the central lumbar spine, with the distance deviation less than a first distance threshold; the distance from the left heel to the right heel being greater than the distance from the left shoulder to the right shoulder, and the distance difference being less than a second distance threshold; the distances from the left shoulder to the left elbow joint and the right shoulder to the right elbow joint being greater than the swing distance threshold; the angles of the left elbow joint and the right elbow joint being less than a first angle threshold; and the angles of the left knee joint and the right knee joint being less than a second angle threshold.
5. The method for evaluating standing vertical jump according to claim 2, characterized in that, The statement that a tester's vertical jump is valid if it meets the take-off specifications also includes: By analyzing the skeletal positions in the jump motion of the tester in the feature motion image, it is determined whether the vertical jump height of the tester meets the jump specifications; by analyzing the skeletal positions in the landing motion of the tester in the feature motion image, it is determined whether the knee flexion motion of the tester meets the landing specifications; the landing specifications include: the angles of the left knee joint and the right knee joint are both less than a third angle threshold; if the take-off specifications, jump specifications and landing specifications are met simultaneously, the tester's standing vertical jump is considered valid.
6. The method for evaluating standing vertical jump according to claim 2, characterized in that, The determination of whether the test subject's torso swing amplitude conforms to the vertical jump standard includes: The vertical jump specifications include: the x-axis distance from the left shoulder to the vertical line containing the central lumbar vertebra, and the x-axis distance from the right shoulder to the vertical line containing the central lumbar vertebra, with the x-axis distance deviation less than a third distance threshold; the y-axis distance from the left shoulder to the vertical line containing the central lumbar vertebra, and the y-axis distance from the right shoulder to the vertical line containing the central lumbar vertebra, with the y-axis distance deviation less than a fourth distance threshold; the vertical swing angle formed by the lines connecting the throat to the groin and the central lumbar vertebra, with the vertical swing angle variation less than a fourth angle threshold; and establishing a three-dimensional coordinate system with the central lumbar vertebra as the origin, the direction of the tester's shoulders as the x-axis, the direction from the heel to the toe as the y-axis, and the height direction as the z-axis.
7. The method for evaluating standing vertical jump according to claim 6, characterized in that, The determination of whether the range of motion of the test subject's hip, knee, and foot joints conforms to the non-compensatory motion standard includes: The non-motor compensation standard includes: a first hip-knee rotation angle formed by connecting the left hip joint with the left knee joint and the central lumbar vertebra, a second hip-knee rotation angle formed by connecting the right hip joint with the right knee joint and the central lumbar vertebra, the variation of the first hip-knee rotation angle and the second hip-knee rotation angle being less than a fifth angle threshold; a first y-axis distance between the left heel and the left toe, a second y-axis distance between the right heel and the right toe, the variation of the first y-axis distance and the second y-axis distance being less than a fifth distance threshold.
8. The method for evaluating standing vertical jump according to claim 2, characterized in that, The judgment results provided for evaluating the tester's actions include: Provided that the tester's vertical jump in place is valid, if it meets both the vertical jump standard and the no-compensation standard, then the tester's action is judged to be a standard vertical jump in place.
9. The method for evaluating standing vertical jump according to claim 8, characterized in that, The judgment result of providing the tester's action evaluation then includes: The height score is calculated based on the vertical jump height, the stability score is calculated based on the trunk swing amplitude, and the non-compensation score is calculated based on the rotation amplitude of the hip, knee and foot joints. The height score, stability score and non-compensation score are weighted and added together to obtain the quality score of the standing vertical jump.
10. A device for evaluating standing vertical jump, characterized in that, include: The system comprises an image acquisition unit, a skeletal point location determination unit, a take-off action evaluation unit, a jump action evaluation unit, a motor compensation evaluation unit, and a comprehensive evaluation unit, wherein: The image acquisition unit is used to acquire a sequence of motion images of the tester during the process of performing a vertical jump in place. The skeletal point location determination unit is used to select feature motion images from the motion image sequence and determine the skeletal point locations of the tester in the motion images. The take-off action evaluation unit is used to determine whether the posture and position of the tester's arms and legs conform to the take-off specifications by using the position of the skeletal points in the tester's take-off action in the feature action image. If they conform to the take-off specifications, the tester's vertical jump in place is deemed valid. The jumping action evaluation unit is used to determine whether the tester's torso swing amplitude conforms to the vertical jump standard by using the position of the skeletal points in the tester's jumping action in the feature action image. The motion compensation assessment unit is used to determine whether the rotation amplitude of the tester's hip and knee joints and feet conforms to the no-motion compensation standard by using the position of skeletal points in the tester's take-off and landing movements in the feature motion image. The comprehensive evaluation unit is used to provide the judgment results of the tester's action evaluation.