Trainer adaptive detection method and system based on leg strength training image

Abstract

The invention discloses a trainer adaptive detection method and system based on leg strength training images, and relates to the technical field of image data processing. The training device self-adaptive detection method based on the leg strength training image comprises the following steps: monitoring qualification of primary acquisition of the leg strength training image; leg feature recognition accuracy monitoring; the trainer receives the monitoring. According to the method, the qualification evaluation of the primary acquisition of the leg strength training image is carried out, whether the primary acquisition optimization of the leg strength training image is carried out or not is judged, then the accuracy quantification of leg feature recognition is carried out, and whether the leg feature recognition optimization is carried out or not is judged according to the quantification result; and finally, training device receiving accuracy monitoring is carried out, and whether training device feedback accuracy analysis is carried out is judged, so that the effect of improving the accuracy of self-adaptive resistance feedback of the training device is achieved. The problem that in the prior art, due to leg strength training image recognition interference, the accuracy of self-adaptive resistance feedback of a trainer is low is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of image data processing, and in particular to a training device adaptive detection method and system based on leg strength training images. Background Art

[0002] The adaptive detection method can automatically adapt to image changes under different environments and conditions, and provide feedback for subsequent training results. In the scene of shooting athletes doing leg strength training in the track and field, the trainee's leg action image is first collected by a camera that supports autofocus and preprocessed (such as grayscale, binarization, etc.) to highlight the leg contours. Then, computer vision technology (such as OpenCV or MediaPipe) is used to detect key points (such as knees, ankles, etc.) in the leg action image to analyze the trainee's movement posture. Then, the data corresponding to the leg action image is collected through a data acquisition card connected to the trainer, that is, the data corresponding to the leg action image collected by the camera is transmitted to the trainer, and then the image processing algorithm (such as contour detection, skeleton) is used to obtain the data. Extraction) and machine learning algorithms (such as support vector machines and deep learning models) analyze the data and features corresponding to the received leg motion images, such as edge information, joint angles, and movement speed of the leg motions. Based on the analysis results of the data corresponding to the leg motion images, tactile feedback is finally provided through a vibration motor (the vibration motor is placed at a position corresponding to the leg support structure of the trainer, such as a vibration motor installed on the calf support structure of the trainer). For example, the vibration motor provides tactile feedback through different vibration patterns and intensities. The vibration motor can emit continuous vibration to prompt athletes to dynamically adjust training parameters, such as resistance, target trajectory, etc., and provide real-time feedback.

[0003] In the prior art, when data corresponding to leg motion images is collected through a data acquisition card connected to a trainer, the leg motion images are collected according to the data acquisition card, such as the athlete's left and right leg muscle strength information, to obtain the real-time motor currents of the left and right wheels, and the data acquisition card is connected to the electromagnetic resistance control module. The electromagnetic resistance control module includes a left wheel resistance control submodule and a right wheel resistance control submodule, wherein the left wheel resistance control submodule is used to adjust the motor current of the left wheel to achieve resistance adjustment, and the right wheel resistance control submodule is used to adjust the motor current of the right wheel to achieve resistance adjustment; a twin adaptive training network is built to receive data corresponding to the leg motion images sent by the data acquisition card, wherein the twin adaptive training network can be called by the electromagnetic resistance control module; such as the real-time motor currents of the left and right wheels of the athlete's leg muscle strength information, the twin adaptive training network is called to perform resistance balance fitness calculation with the goal of balancing the left and right leg muscle strength, and the trainer outputs the adjustment resistance according to the analysis results of the data corresponding to the leg motion images to adjust the resistance of the left and right wheels of the trainer.

[0004] For example, the invention patent announcement with announcement number: CN118628620B discloses an interactive LED display system for smart sports, including: a multimodal motion posture capture unit, which captures the athlete's posture data and contact force data with the ground or equipment in real time; an environmental perception unit monitors and captures real-time environmental data such as temperature, humidity and light intensity through environmental sensors, and works in conjunction with an adaptive motion standard database; the database stores standard posture data for various sports movements; a posture comparison and analysis unit uses a machine learning algorithm to analyze the captured data to generate accurate posture analysis results; a feedback generation unit generates posture correction instructions based on this; and the LED display unit displays the athlete's current posture image, the adjusted standard posture image, and specific posture adjustment suggestions based on these instructions.

[0005] For example, the invention patent application with publication number CN117237491A discloses a method and medium for generating state parameters of a motion platform based on video images, including: obtaining a target state parameter set of a target virtual object in a preset video image corresponding to the motion platform, recording the control data generated by the operator on the motion platform while observing the preset video image to form an actual real-time state parameter set for the motion platform, obtaining the control amount that needs to be adjusted for the motion platform based on the target state parameter set and the actual real-time state parameter set of the platform, and performing saturation processing on the control amount, converting the saturated control amount into a control instruction and sending it to the actuator on the motion platform for execution, and once the latest state parameter fed back by the actuator reaches the target state parameter value, the state parameter set of the motion platform at the current moment is used as the generated state parameter of the motion platform.

[0006] However, in the process of implementing the technical solutions of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems: In the prior art, when filming athletes performing leg strength training in a track and field stadium, the images captured by the camera may be affected by factors such as lighting conditions. The lighting system of a track and field stadium is usually composed of high-pole lamps installed above the stands or on lamp poles around the field. The light distribution characteristics lead to significant differences in light intensity in different areas of the field. High-pole lamps are usually installed at the four corners or around the field, and their light coverage presents a certain cone-shaped area. Areas closer to the lamps, such as the edge of the field close to the lamps, will receive more light and have greater light intensity, while the center of the field or the area away from the lamps will have relatively weaker light intensity. Since the light may be unevenly distributed, some areas will have stronger light and some areas will have weaker light. This mixed lighting will lead to large differences in brightness between different areas in the captured image, resulting in uneven light. Under uneven light conditions, some areas in the image may be too bright and some areas may be too dark.

[0007] In addition, histogram equalization enhances contrast by adjusting the histogram distribution of the image to a uniform distribution. This global adjustment method ignores the characteristics of different local areas in the image, which may cause the contrast of some local areas to be over-enhanced and the contrast of other local areas to be weakened, thereby causing contrast imbalance in local areas. The grayscale values ​​of contrast pixels may be mapped to a wider grayscale range, becoming more obvious. The reduction in contrast makes the clarity of the image lower, resulting in a decrease in image quality, obscuring the key points of the legs when detected by computer vision technology (such as OpenCV or MediaPipe), and thus interfering with the recognition of leg contours and textures in the image. When the trainer dynamically adjusts training parameters and provides real-time feedback based on the interfered image data received by the data acquisition card, such as the user's posture, movement amplitude, speed, etc., there is a problem of low accuracy in the trainer's adaptive resistance feedback due to interference in leg strength training image recognition. Summary of the Invention

[0008] The embodiments of the present application solve the problem in the prior art of low accuracy of adaptive resistance feedback of the trainer due to interference in leg strength training image recognition by providing a trainer adaptive detection method and system based on leg strength training images, thereby improving the accuracy of adaptive resistance feedback of the trainer.

[0009] An embodiment of the present application provides a trainer adaptive detection method based on leg strength training images, comprising the following steps: during the trainer adaptive detection process, performing a leg strength training image initial acquisition qualification assessment, determining whether to perform leg strength training image initial acquisition optimization based on the assessment result, performing leg strength training image initial acquisition optimization, indicating that the uniformity of the leg strength training image grayscale distribution is improved through image grayscale setting and histogram equalization clarity optimization to improve the qualification of the leg strength training image initial acquisition; after the leg strength training image initial acquisition qualification assessment is passed, performing leg feature recognition accuracy quantification, determining whether to perform leg feature recognition optimization based on the quantification result, performing leg feature recognition optimization means enhancing the discrimination of edge and contour information of the leg strength training image through non-local mean denoising setting and gradient amplitude mapping to enhance the accuracy of leg feature recognition of the leg strength training image; after the leg feature recognition accuracy quantification is passed, performing trainer reception accuracy monitoring, determining whether to perform trainer feedback accuracy analysis based on the trainer reception accuracy monitoring result to reflect the accuracy of the leg strength training image data fed back by the trainer.

[0010] An embodiment of the present application provides a trainer adaptive detection system based on leg strength training images, and its application is such as a trainer adaptive detection method based on leg strength training images, including a leg strength training image initial acquisition qualification monitoring module, a leg feature recognition accuracy monitoring module and a trainer reception monitoring module: wherein, the leg strength training image initial acquisition qualification monitoring module is used to perform leg strength training image initial acquisition qualification evaluation during the trainer adaptive detection process, and judge whether to perform leg strength training image initial acquisition optimization based on the evaluation result, and perform leg strength training image initial acquisition optimization, which means that the uniformity of the grayscale distribution of the leg strength training image is improved through image grayscale setting and histogram equalization clarity optimization to improve the leg strength training image initial acquisition qualification. The leg feature recognition accuracy monitoring module is used to quantify the leg feature recognition accuracy after the leg strength training image initial acquisition qualification assessment is qualified, and determine whether to perform leg feature recognition optimization based on the quantification result. The leg feature recognition optimization means enhancing the distinction of the edge and contour information of the leg strength training image through non-local mean denoising setting and gradient amplitude mapping to enhance the accuracy of leg feature recognition of the leg strength training image; the trainer reception monitoring module is used to monitor the trainer reception accuracy after the leg feature recognition accuracy is quantified, and determine whether to perform trainer feedback accuracy analysis based on the trainer reception accuracy monitoring result to reflect the accuracy of the leg strength training image data fed back by the trainer.

[0011] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. By conducting an initial leg strength training image acquisition qualification assessment and determining whether to perform initial leg strength training image acquisition optimization based on the assessment results, the initially qualified leg strength training images can more clearly present the muscles, bones and other features of the legs when the light may be unevenly distributed, thereby improving the accuracy of leg feature recognition. After the initial leg strength training image acquisition qualification assessment is passed, the leg feature recognition accuracy is quantified, and based on the quantification results, it is determined whether to perform leg feature recognition optimization, which helps to compare the changes in leg features in the image when the light may be unevenly distributed. Finally, after the leg feature recognition accuracy is quantified, the trainer reception accuracy is monitored, and based on the trainer reception accuracy monitoring results, it is determined whether to perform trainer feedback accuracy analysis, which helps to ensure that the trainer can correctly receive the leg feature recognition results when the light may be unevenly distributed, and ensure that the trainer feedback can match the actual leg strength training situation, thereby achieving an improvement in the accuracy of the trainer's adaptive resistance feedback, and effectively solving the problem in the prior art of low accuracy of the trainer's adaptive resistance feedback due to interference in leg strength training image recognition.

[0012] 2. The leg strength training image initial acquisition data is obtained by quantifying the proportion of the preset leg strength training image initial acquisition parameters and the leg strength training image initial acquisition parameters. The qualified leg strength training image complete interference value obtained by the leg strength training image complete interference evaluation is used to obtain the leg strength training image initial acquisition qualified evaluation value. This helps to better adapt to different lighting conditions during the adaptive detection of the trainer in the track and field, thereby reducing the impact of environmental factors such as uneven light distribution on the leg strength training image acquisition. Compared with the existing analysis of a single variable, it is more conducive to comprehensively evaluating and optimizing the image acquisition process, improving the performance and effect of the adaptive detection of the entire trainer, and realizing the feasibility and adaptability of the leg strength training image initial acquisition qualified evaluation.

[0013] 3. When filming athletes performing leg strength training in a track and field stadium, uneven lighting conditions may lead to differences in image data, which in turn affects the accuracy of the trainer reception and feedback. By monitoring the trainer reception-qualification verification value and, when the trainer reception-qualification verification value is no greater than 0, using the absolute value of the difference between the trainer resistance fed back by the trainer and the preset trainer resistance as the trainer feedback verification value, and making judgments based on the trainer feedback qualified value, it helps to ensure the accuracy of data reception and feedback under complex lighting conditions, enabling the trainer to provide precise resistance based on the athlete's actual performance, and enhancing the adaptability of the trainer feedback parameters to lighting changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a general logic diagram of a training device adaptive detection method based on leg strength training images provided in an embodiment of the present application; Figure 2 A flowchart of a method for adaptively detecting a training device based on leg strength training images provided in an embodiment of the present application; Figure 3 This is a basic framework diagram for the initial acquisition and optimization of leg strength training images provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of a trainer adaptive detection system based on leg strength training images provided in an embodiment of the present application; Figure 5 A coordinate diagram of a leg strength training image provided in an embodiment of the present application. DETAILED DESCRIPTION

[0015] The embodiments of the present application solve the problem in the prior art of low accuracy of resistance feedback of the trainer due to interference in leg strength training image recognition by providing a trainer adaptive detection method and system based on leg strength training images. The method performs an initial acquisition qualification assessment of the leg strength training images and determines whether to perform initial acquisition optimization of the leg strength training images based on the assessment results. When the initial acquisition qualification assessment value of the leg strength training images is not greater than the preset initial acquisition qualification value, the initial acquisition optimization of the leg strength training images is performed. After the initial acquisition qualification assessment of the leg strength training images is passed, the leg feature recognition accuracy is quantified, and it is determined whether to perform leg feature recognition optimization based on the quantification result. When the image muscle positioning error is greater than the preset image muscle positioning error obtained from the database, the leg feature recognition optimization is performed. Finally, after the leg feature recognition accuracy is quantified, the trainer reception accuracy is monitored, and it is determined whether to perform trainer feedback accuracy analysis based on the trainer reception accuracy monitoring result. This improves the accuracy of the trainer adaptive resistance feedback.

[0016] The technical solution in the embodiment of the present application is to solve the problem of low accuracy of the training device's adaptive resistance feedback due to interference in leg strength training image recognition. The overall idea is as follows: By conducting an initial leg strength training image acquisition qualification assessment and judging whether to perform initial leg strength training image acquisition optimization based on the assessment results, and then quantifying the leg feature recognition accuracy after the initial leg strength training image acquisition qualification assessment is passed and judging whether to perform leg feature recognition optimization based on the quantification results, and finally monitoring the trainer reception accuracy after the leg feature recognition accuracy is passed, and judging whether to perform trainer feedback accuracy analysis based on the trainer reception accuracy monitoring results, the effect of improving the accuracy of the trainer's adaptive resistance feedback is achieved.

[0017] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0018] like Figure 1 FIG. 1 is a schematic diagram of the overall logic of the adaptive detection method of the trainer based on the leg strength training image provided by the embodiment of the present application, which is composed of Figure 1It can be seen that the complete interference value of the leg strength training image and the qualified evaluation value of the initial acquisition of the leg strength training image are obtained through the leg strength training image initial acquisition qualification monitoring. The larger the complete interference value of the leg strength training image, the greater the degree of interference of the complete leg strength training image. When the qualified evaluation value of the initial acquisition of the leg strength training image is not greater than the preset qualified value of the initial acquisition, the initial acquisition of the leg strength training image is optimized. The optimization of the initial acquisition of the leg strength training image indicates the sequential image grayscale setting and histogram equalization clarity optimization setting. The histogram equalization clarity optimization setting also includes leg training image sharpening optimization and Gaussian blur radius setting. ; Otherwise, the image muscle positioning error is obtained through leg feature recognition accuracy monitoring. When the image muscle positioning error is greater than the preset image muscle positioning error, leg feature recognition optimization is performed. The leg feature recognition optimization includes setting non-local mean denoising and obtaining gradient amplitude mapping values; Otherwise, the trainer signal synchronization error is obtained through trainer reception monitoring. When the trainer signal synchronization error is greater than the preset trainer signal synchronization error, trainer reception optimization is performed. Otherwise, the trainer feedback verification value is obtained. When the obtained trainer feedback qualified value is greater than 0, a trainer feedback accuracy qualified prompt is sent. Otherwise, a level 5 alarm prompt is sent.

[0019] As an implementation method of the first aspect, Figure 2 FIG. 1 is a flow chart of a method for adaptively detecting a training device based on leg strength training images provided by an embodiment of the present application, the method comprising the following steps: First, the qualification of the initial acquisition of leg strength training images is monitored: during the adaptive detection of the trainer, the qualification of the initial acquisition of leg strength training images is evaluated, and whether to optimize the initial acquisition of leg strength training images is determined based on the evaluation results. The initial acquisition of leg strength training images is optimized, which means that the uniformity of the grayscale distribution of the leg strength training images is improved through image grayscale setting and histogram equalization to improve the qualification of the initial acquisition of leg strength training images. The qualification monitoring of the initial acquisition of leg strength training images helps to ensure the quality of leg strength training image acquisition, provide clear and accurate basic data for subsequent leg feature recognition, and avoid recognition errors caused by image quality problems.

[0020] like Figure 3 As shown in the figure, it is the basic framework diagram of the initial acquisition optimization of leg strength training images provided by the embodiment of the present application, which consists of Figure 3 It can be seen that when the initial acquisition qualified evaluation value of the monitored leg strength training image is greater than the preset initial acquisition qualified value, the leg feature recognition accuracy is quantified. Otherwise, the image grayscale is set first, and then the histogram equalization clarity optimization setting is performed. The image grayscale setting includes obtaining the qualified image grayscale value and obtaining the histogram equalization evaluation value. The histogram equalization clarity optimization setting includes leg training image sharpening optimization and Gaussian blur radius setting.

[0021] Next, the accuracy of leg feature recognition is monitored: after the initial collection of leg strength training images is qualified, the leg feature recognition accuracy is quantified, and whether to perform leg feature recognition optimization is determined based on the quantification results. Leg feature recognition optimization means that the non-local mean denoising setting and gradient amplitude mapping are used to enhance the discrimination of edge and contour information of leg strength training images to enhance the accuracy of leg feature recognition of leg strength training images. Leg feature recognition accuracy monitoring helps to improve the recognition accuracy of leg features and accurately extract key features such as leg muscles and bones.

[0022] Finally, the trainer receives monitoring: after the leg feature recognition accuracy is quantified and qualified, the trainer receives accuracy monitoring, and determines whether to conduct the trainer feedback accuracy analysis based on the trainer reception accuracy monitoring results to reflect the accuracy of the leg strength training image data fed back by the trainer. The leg strength training image data includes the leg joint position and angle, image light intensity, etc. The trainer receives monitoring, which helps to ensure the accuracy and completeness of the image data received by the trainer, and ensures that the trainer can correctly feedback the training information.

[0023] In this embodiment, when shooting athletes performing leg strength training in a track and field stadium, uneven lighting conditions will cause differences in image data, thereby affecting the accuracy of the trainer's reception and feedback; through the mutual correlation and interaction of leg strength training image initial acquisition qualification monitoring, leg feature recognition accuracy monitoring and trainer reception monitoring, accurate leg feature data is provided for the trainer reception monitoring, such as image joint position coordinates, image muscle attachment point coordinates, etc., to ensure that the trainer can receive accurate training information, which is beneficial to providing more accurate feedback resistance to athletes in the track and field stadium; thereby achieving the improvement of the accuracy of the trainer's adaptive resistance feedback.

[0024] It should be added that before the design of the adaptive detection method of the trainer based on leg strength training images provided in this application, a database for storing various setting data is established, which includes but is not limited to the preset leg strength training image resolution deviation, the preset leg image light uniform interference value, the preset leg strength training image initial acquisition delay and the preset qualified leg strength training image complete interference value, etc., and the various numerical values ​​are directly set by technical personnel; for example, the number of successful identifications of the preset leg feature points is represented by the average value of the successful identification number of the preset leg feature points in the historical time period.

[0025] Furthermore, the specific process of conducting the initial acquisition qualification assessment of leg strength training images is as follows: S1, conducting a complete interference assessment of the leg strength training images: by quantifying the proportion of the total number of recognized preset leg feature points in the leg strength training image and the number of successfully recognized preset leg feature points in the leg strength training image, the complete interference value of the leg strength training image is obtained. If the complete interference value of the leg strength training image is not greater than the preset recognition complete interference value, S2 is executed, otherwise a first-level alarm is sent to prompt that the leg strength training image is abnormal; the initial acquisition qualification assessment of the leg strength training image is used to evaluate the qualification of the leg strength training image during the initial acquisition.

[0026] S2, obtain the qualified evaluation value of the initial acquisition of the leg strength training image: S21, quantify the proportion of the preset leg strength training image initial acquisition parameters and the leg strength training image initial acquisition parameters to obtain the leg strength training image initial acquisition data. In this application, the quantification of the proportion means performing a ratio operation. The leg strength training image initial acquisition data includes the resolution deviation-initial acquisition qualified index, the uniform interference-initial acquisition qualified index, the delay-initial acquisition qualified index and the image integrity-initial acquisition qualified index.

[0027] Specifically, the expression of resolution deviation-initial collection qualified index is: , a(W) represents the resolution deviation of the leg strength training image in the Wth preset initial acquisition time period, X1(W) represents the resolution deviation of the Wth preset initial acquisition time period - the initial acquisition qualified index, a(0) represents the preset leg strength training image resolution deviation, F represents the preset constant, the preset constant is used to avoid the meaningless denominator of the leg strength training image initial acquisition data, specifically, it is used to ensure the effectiveness of the evaluation of the deviation degree between the number of pixels in the preset area and the preset number of pixels, the difference degree between the maximum brightness and the minimum brightness of the leg strength training image, the deviation degree between the duration of the leg strength training image and the preset initial acquisition duration, and the complete interference degree of the leg strength training image, and at the same time provide a basis for data standardization. Accurate, W=1,2,...,S, W represents the number of the preset initial acquisition time period, S represents the total number of preset initial acquisition time periods, and the image processor monitors the difference between the average value of the number of pixels in the preset area of ​​the leg strength training image in the preset initial acquisition time period and the preset number of pixels as the leg strength training image resolution deviation. The units of the leg strength training image resolution deviation and the preset leg strength training image resolution deviation are both unitless. The larger the leg strength training image resolution deviation, the more it means that the clarity or detail performance of the leg strength training image is inconsistent with the preset state, and the stronger the effect of the leg strength training image resolution deviation on the initial acquisition qualification degree of the leg strength training image, which in turn leads to a smaller resolution deviation-initial acquisition qualification index.

[0028] Specifically, the expression of uniform interference-initial acquisition qualified index is: , X2(W) represents the uniform interference-initial acquisition qualification index of the Wth preset initial acquisition time period, b(W) represents the leg image light uniform interference value of the Wth preset initial acquisition time period, b(0) represents the preset leg image light uniform interference value, and the average value of the difference between the maximum brightness and the minimum brightness of the leg strength training image in the preset initial acquisition time period is monitored by the image processor as the leg image light uniform interference value. The units of the leg image light uniform interference value and the preset leg image light uniform interference value are both nits. The larger the leg image light uniform interference value, the worse the light uniformity, and the stronger the effect of the leg image light uniform interference value on the initial acquisition qualification of the leg strength training image, which in turn leads to a smaller uniform interference-initial acquisition qualification index.

[0029] Specifically, the expression of the delay-initial collection qualification index is: , X3(W) represents the delay-initial acquisition qualification index of the Wth preset initial acquisition time period, c(W) represents the initial acquisition delay of the leg strength training image of the Wth preset initial acquisition time period, c(0) represents the preset leg strength training image initial acquisition delay, and the average value of the difference between the duration of the leg strength training image in the preset initial acquisition time period and the preset initial acquisition duration is monitored by a timer as the leg strength training image initial acquisition delay. The units of the leg strength training image initial acquisition delay and the preset leg strength training image initial acquisition delay are both milliseconds. The greater the leg strength training image initial acquisition delay, the greater the deviation between the duration of the leg strength training image and the preset initial acquisition duration, and the stronger the effect of the leg strength training image initial acquisition delay on the initial acquisition qualification of the leg strength training image, which in turn leads to a smaller delay-initial acquisition qualification index.

[0030] Specifically, the expression of image integrity-initial acquisition qualified index is: , X4(W) represents the image completeness-initial acquisition qualified index of the W-th preset initial acquisition time period, d(W) represents the qualified leg strength training image complete interference value of the W-th preset initial acquisition time period, d(0) represents the preset qualified leg strength training image complete interference value, the larger the qualified leg strength training image complete interference value, the greater the possibility of incomplete leg strength training image acquisition, the stronger the effect of the qualified leg strength training image complete interference value on the initial acquisition qualified degree of the leg strength training image, and thus the smaller the image completeness-initial acquisition qualified index.

[0031] Then, the leg strength training image initial acquisition data is weightedly coupled with the preset leg strength training image initial acquisition control index obtained from the database to obtain the leg strength training image initial acquisition qualified evaluation value.

[0032] The qualified evaluation value of the initial acquisition of leg strength training images is obtained by the following method: ; Where X(W) represents the qualified evaluation value of the leg strength training image initial acquisition in the Wth preset initial acquisition time period, X1 represents the preset resolution deviation-initial acquisition control index, X2 represents the preset uniform interference-initial acquisition control index, X3 represents the preset delay-initial acquisition control index, and X4 represents the preset image integrity-initial acquisition control index.

[0033] Specifically, the initial acquisition parameters of the leg strength training image include the leg strength training image resolution deviation, the leg image light uniformity interference value, the leg strength training image initial acquisition delay and the qualified leg strength training image complete interference value.

[0034] The leg strength training image resolution deviation is used to reflect the degree of deviation between the number of pixels in a preset area and the preset number of pixels, and is expressed by the difference between the average value of the number of pixels in the preset area of ​​the leg strength training image in the preset initial acquisition time period and the preset number of pixels; the leg image light uniformity interference value is used to reflect the degree of difference between the maximum brightness and the minimum brightness of the leg strength training image, and is expressed by the average value of the difference between the maximum brightness and the minimum brightness of the leg strength training image in the preset initial acquisition time period; the leg strength training image initial acquisition delay is used to reflect the degree of deviation between the duration of the leg strength training image and the preset initial acquisition duration, and is expressed by the average value of the difference between the duration of the leg strength training image in the preset initial acquisition time period and the preset initial acquisition duration; the qualified leg strength training image complete interference value is expressed by a leg strength training image complete interference value that is not greater than the preset identification complete interference value.

[0035] In addition, the preset leg strength training image initial acquisition parameters include preset leg strength training image resolution deviation, preset leg image light uniform interference value, preset leg strength training image initial acquisition delay and preset qualified leg strength training image complete interference value. The preset leg strength training image initial acquisition parameters are represented by the average value of the leg strength training image initial acquisition parameters in the historical time period; the preset leg strength training image initial acquisition control index is used to reflect the degree of influence of the leg strength training image initial acquisition data on the leg strength training image initial acquisition qualified evaluation value, specifically including: preset resolution deviation-initial acquisition control index, preset uniform interference-initial acquisition control index, preset delay-initial acquisition control index and preset image integrity-initial acquisition control index; the leg strength training image initial acquisition qualified evaluation value is used to reflect the effect of the leg strength training image initial acquisition parameters and the preset leg strength training image initial acquisition parameters on the initial acquisition qualified degree of the leg strength training image. The preset initial acquisition time period represents the preset time period when the leg strength training image is initially acquired.

[0036] It should be added that the embodiment of the present application provides a set of preset mapping relationships set in advance by preset personnel, wherein the mapping relationships in the mapping set can be one-to-one or many-to-one relationships, and the leg strength training image initial acquisition data and the preset leg strength training image initial acquisition control indicators are matched one-to-one or many-to-one. The mapping group is obtained from the database and contains a mapping set, wherein the preset leg strength training image initial acquisition control indicator is represented by the proportion of the corresponding leg strength training image initial acquisition data; by inputting the real-time leg strength training image initial acquisition data into the corresponding mapping group, the corresponding preset leg strength training image initial acquisition control indicator can be obtained, and the value range is 0-1.

[0037] In this embodiment, the leg strength training image initial acquisition qualification evaluation value is further obtained by quantifying the initial acquisition qualification degree of the leg strength training image based on the initial acquisition data of the leg strength training image. The larger the leg strength training image initial acquisition data, the stronger the effect of the leg strength training image initial acquisition parameters on the initial acquisition qualification degree of the leg strength training image. That is, the greater the deviation between the number of pixels in the preset area and the preset number of pixels, the greater the difference between the maximum brightness and the minimum brightness of the leg strength training image, the greater the deviation between the duration of the leg strength training image and the preset initial acquisition duration, and the greater the interference in the initial acquisition of the leg strength training image, resulting in smaller leg strength training image initial acquisition data, and thus smaller leg strength training image initial acquisition qualification evaluation value. In summary, in this embodiment, the leg strength training image initial acquisition data and the leg strength training image initial acquisition qualification evaluation value are positively correlated.

[0038] The initial acquisition parameters of the leg strength training images monitored in this embodiment do not exist in isolation, but have interrelated characteristics, and require correlation analysis to describe their joint effects. The larger the leg strength training image resolution deviation, the more likely the leg strength training image is to be blurred or distorted, and the blurred or distorted image may be considered incomplete, resulting in a larger complete interference value for the qualified leg strength training image; the larger the light uniformity interference value, the more likely it is that the brightness distribution in some areas of the image is uneven, and details cannot be clearly displayed, resulting in a larger resolution deviation for the leg strength training image; the larger the leg image light uniformity interference value, the more likely it is that the leg strength training image acquisition delay will be affected, such as the automatic exposure adjustment may cause a delay, resulting in a larger initial acquisition delay for the leg strength training image; through a comprehensive analysis of the initial acquisition parameters of the leg strength training image, the movement details during the leg strength training process can be captured more accurately, and a precise assessment of the initial acquisition qualification of the leg strength training image can be achieved, thereby improving the accuracy of the trainer's adaptive resistance feedback.

[0039] Furthermore, it is determined whether to perform initial acquisition optimization of the leg strength training image based on the evaluation results. The specific process is as follows: the obtained initial acquisition qualified evaluation value of the leg strength training image is compared with the preset initial acquisition qualified value obtained from the database, wherein the preset initial acquisition qualified value is represented by the average value of the initial acquisition qualified evaluation value of the leg strength training image in the historical time period, wherein the range of the initial acquisition qualified evaluation value of the leg strength training image in the embodiment of the present application is 0.5-1; if the initial acquisition qualified evaluation value of the leg strength training image is greater than the preset initial acquisition qualified value, a prompt indicating that the image is initially acquired is sent, and the accuracy of leg feature recognition is quantified; otherwise, a prompt indicating that the image is initially acquired is unqualified, and the initial acquisition optimization of the leg strength training image is performed; the initial acquisition optimization of the leg strength training image is performed in the order of image grayscale setting and histogram equalization clarity optimization setting.

[0040] Among them, the steps of image grayscale setting are as follows: Step 1: Send a prompt to the preset personnel to input the grayscale value of the unqualified leg strength training image and the initial acquisition qualified evaluation value of the leg strength training image into the database for grayscale value correction to obtain the qualified image grayscale value. The unqualified leg strength training image represents the leg strength training image corresponding to the initial acquisition qualified evaluation value of the leg strength training image that is not greater than the preset initial acquisition qualified value. The average value of the grayscale values ​​of each unqualified leg strength training image in the preset time period is monitored by an industrial camera as the grayscale value of the unqualified leg strength training image. The database of this application contains a set of mapping sets for reflecting the grayscale values ​​of the unqualified leg strength training image and the initial acquisition qualified evaluation value of the leg strength training image. The estimation is a mapping relationship between the grayscale value of the qualified image and the corresponding qualified image; the second step is to send a prompt to the preset personnel to set the grayscale of the leg strength training image based on the qualified image grayscale value and the histogram equalization method. When the image grayscale setting prompt is received, the grayscale of the leg strength training image is set based on the qualified image grayscale value and the histogram equalization method, which helps to make the grayscale distribution of the leg strength training image more uniform and reasonable; the qualified image grayscale value is within the preset image grayscale range. By controlling the qualified image grayscale value within the preset image grayscale range, it helps to avoid loss of image details and insufficient contrast, wherein the preset image grayscale range is pre-set by the preset personnel, and the preset image grayscale range includes the upper and lower endpoints of the range.

[0041] In addition, the image grayscale setting also includes: obtaining a histogram equalization evaluation value, which is specifically represented by the difference between the initial acquisition qualified evaluation value of the leg strength training image in the final state of the image grayscale setting and the initial acquisition qualified evaluation value of the leg strength training image in the initial state, and comparing the obtained histogram equalization evaluation value with the preset equalization evaluation value obtained from the database; if the histogram equalization evaluation value is greater than the preset equalization evaluation value, a prompt indicating that the image grayscale setting is qualified is sent, and the leg feature recognition accuracy is quantified, otherwise a histogram equalization clarity optimization setting is performed.

[0042] It should be added that the specific process of histogram equalization clarity optimization setting is as follows: T1, perform leg training image sharpening optimization: send a prompt to the preset personnel to process the leg strength training image based on the unsharp masking method to enhance the clarity and leg texture features of the leg strength training image after the image grayscale setting; T2, perform Gaussian blur radius setting: send a prompt to the preset personnel to input the grayscale value of the leg strength training image at the final state of the image grayscale setting and the initial acquisition qualified evaluation value of the leg strength training image into the database for mapping to obtain a qualified Gaussian blur radius adjustment value. The qualified Gaussian blur radius adjustment value is not greater than the preset maximum image Gaussian blur radius adjustment value obtained from the database. The database of this application contains a set of mapping relationships for reflecting the grayscale value of the leg strength training image at the final state of the image grayscale setting and the initial acquisition qualified evaluation value of the leg strength training image, and the corresponding qualified Gaussian blur radius adjustment value. The preset maximum image Gaussian blur radius adjustment value is set in advance by the preset personnel; T3, send a prompt to the preset personnel based on the amplitude corresponding to the obtained qualified Gaussian blur radius adjustment value. Increasing the Gaussian blur radius of the leg image corresponding to the leg strength training image. By gradually increasing the Gaussian blur radius of the leg image corresponding to the leg strength training image by the amplitude corresponding to the qualified Gaussian blur radius adjustment value, it helps to avoid excessive blurring or loss of detail in the image due to a sudden increase in the blur radius. The Gaussian blur radius of the leg image is not greater than the preset maximum Gaussian blur radius of the leg image obtained from the database. If the initial acquisition qualified assessment value of the leg strength training image obtained after the histogram equalization and clarity optimization setting is still not greater than the preset initial acquisition qualified value, controlling the Gaussian blur radius of the leg image to be no greater than the preset maximum Gaussian blur radius of the leg image helps prevent excessive Gaussian blur processing and ensure that the image can retain sufficient details and information. A second-level alarm prompt is sent to indicate that the histogram equalization and clarity optimization setting is abnormal. Otherwise, the leg feature recognition accuracy is quantified. When the histogram equalization and clarity optimization setting is received, the leg training image is first sharpened and optimized, and then the Gaussian blur radius is set. This can effectively enhance the clarity of the image and the leg texture features, making the details in the image more prominent.

[0043] In this embodiment, the leg strength training image is made clearer by sequentially performing image grayscale setting and histogram equalization and clarity optimization setting, and the histogram equalization and clarity optimization setting can further enhance the details and texture features of the image, thereby improving the pass rate of the initial acquisition of the leg strength training image; this application uses the image grayscale setting, histogram equalization and clarity optimization setting, leg training image sharpening optimization and Gaussian blur radius setting in an orderly and interrelated manner, which can effectively suppress noise without excessive blurring resulting in loss of details in the leg strength training image.

[0044] Furthermore, the accuracy of leg feature recognition is quantified, and whether to perform leg feature recognition optimization is determined based on the quantification results. The specific process is as follows: judgment is made based on the acquired image muscle positioning error: if the acquired image muscle positioning error is not greater than the preset image muscle positioning error obtained from the database, a leg feature recognition accuracy qualification prompt is sent, and the trainer reception accuracy is monitored. The preset image muscle positioning error is represented by the average value of the image muscle positioning error in the historical time period; otherwise, an unqualified prompt is sent and leg feature recognition optimization is performed; when it is monitored that the image muscle positioning error is greater than the preset image muscle positioning error obtained from the database, it means that the current leg feature recognition result is not accurate enough. By performing leg feature recognition optimization, it helps to reduce the source of error and make the recognition result closer to the actual situation; the average value of the distance between each muscle position point successfully identified within the preset recognition time period is monitored by an industrial camera and the corresponding preset muscle position point is used as the image muscle positioning error; the preset recognition time period represents the preset time period corresponding to the leg feature recognition accuracy quantification; the image muscle positioning error is used to reflect the accuracy of feature recognition of the leg strength training image within the preset recognition time period.

[0045] Among them, the specific process of leg feature recognition optimization is as follows: Step 1, perform non-local mean denoising setting: send a prompt to the preset personnel to process the leg strength training image based on the non-local mean denoising method; Step 2, send a prompt to the preset personnel: input the qualified image pixel grayscale value and image muscle positioning error into the database for mapping to obtain the gradient amplitude mapping value. If the obtained gradient amplitude mapping value is greater than the preset gradient amplitude maximum value, send a gradient amplitude mapping alarm prompt, otherwise the corresponding gradient amplitude mapping value is marked as a qualified gradient amplitude mapping value, and send a prompt to the preset personnel to gradually increase the gradient amplitude of the leg strength training image by the amplitude corresponding to the qualified gradient amplitude mapping value. The preset gradient amplitude maximum value is set in advance by the preset personnel, and the database contains a set of mappings that reflect the mapping relationship between the qualified image pixel grayscale value and the image muscle positioning error and the corresponding qualified gradient amplitude mapping value. When the leg feature recognition optimization prompt is received, the gradient amplitude of the leg strength training image is gradually increased by the amplitude corresponding to the qualified gradient amplitude mapping value. The gradient amplitude is closely related to the edge and detail features of the image. The method is closely related to the leg strength training image, and the step-by-step increase method can make the edges and details in the leg strength training image more prominent, thereby enhancing the visibility of the leg strength training image features; the gradient amplitude is within the preset qualified gradient amplitude range, which is set in advance by the preset personnel, and the preset qualified gradient amplitude range includes the endpoints of the upper and lower limits corresponding to the range. By controlling the gradient amplitude within the preset qualified gradient amplitude range, it is helpful to maintain the accuracy of leg feature recognition; the qualified image pixel grayscale value represents the grayscale value of the leg strength training image corresponding to the initial acquisition qualified evaluation value of the leg strength training image that is not greater than the preset initial acquisition qualified value. The feature recognition accuracy of the leg strength training image is evaluated by obtaining the image muscle positioning error. If it is inaccurate, that is, the image muscle positioning error is greater than the preset image muscle positioning error, then non-local mean denoising and gradient amplitude mapping adjustment and other optimization operations are performed in sequence. First, non-local mean denoising is used to reduce image noise interference to make the image clearer; then gradient amplitude mapping adjustment is performed to enhance the edge and detail features of the image, making the leg features more obvious, which is convenient for subsequent feature recognition and analysis.

[0046] At the same time, leg feature recognition optimization also includes feature recognition-qualification verification; the specific process of feature recognition-qualification verification is as follows: obtain the difference between the leg feature recognition accuracy quantification value before leg feature recognition optimization and the leg feature recognition accuracy quantification value after leg feature recognition optimization, which is recorded as the feature recognition-qualification verification value; make a judgment based on the obtained feature recognition-qualification verification value; if the obtained feature recognition-qualification verification value is not greater than 0, send a third-level alarm prompt to prompt the abnormality of leg feature recognition optimization, otherwise, send a feature recognition qualified prompt, and monitor the trainer reception accuracy; the feature recognition-qualification verification value is used to reflect the qualification level of leg feature recognition optimization in the preset recognition time period. By controlling the feature recognition-qualification verification value to be greater than 0, it is helpful to timely discover and avoid invalid or erroneous optimization operations.

[0047] In this embodiment, the leg feature recognition accuracy quantification, leg feature recognition optimization, and feature recognition-qualification verification are interconnected to jointly improve the feature recognition accuracy of the leg strength training image; after the leg feature recognition optimization, the feature recognition accuracy is verified again to ensure that the features of the leg strength training image can be accurately recognized.

[0048] Furthermore, after the leg feature recognition accuracy is quantified and qualified, the trainer reception accuracy is monitored, and the specific process is as follows: the time for the trainer to receive the training signal and the preset trainer reception time are monitored by a timer to quantify the degree of difference. In this application, the quantification of the degree of difference means performing a difference operation as the trainer signal synchronization error, wherein the range of the trainer signal synchronization error in the embodiment of the present application is 10-20 milliseconds; the trainer signal synchronization error is used to reflect the qualification degree of the trainer receiving the leg strength training image data in the preset trainer reception time period; the trainer signal synchronization error is compared with the preset trainer signal synchronization error obtained from the database; if the trainer signal synchronization error is greater than the preset trainer signal synchronization error, a trainer reception accuracy unqualified prompt is sent, and the trainer reception optimization is performed; otherwise, a trainer reception accuracy qualified prompt is sent and the trainer feedback accuracy analysis is performed.

[0049] Specifically, trainer reception optimization means improving the accuracy of leg strength training image data received by the trainer through data bit rate setting. Data bit rate setting means sending a prompt to the preset personnel to gradually increase the trainer data bit rate by the amplitude corresponding to the trainer data bit rate mapping value. When the trainer reception optimization prompt is monitored, the trainer data bit rate is gradually increased by the amplitude corresponding to the trainer data bit rate mapping value, so that more leg strength training image data can be transmitted per unit time, which better assists in the monitoring and analysis of leg strength training effects; the trainer data bit rate is not greater than the preset maximum trainer data bit rate, and the preset maximum trainer data bit rate is set in advance by the preset personnel; the trainer data bit rate mapping value is obtained by inputting the number of transmission requests, trainer data transmission bandwidth and trainer signal synchronization error into the database, and performing mapping processing through the database to obtain the trainer data bit rate mapping value. The database contains a mapping set that reflects the mapping relationship between the number of transmission requests, trainer data transmission bandwidth and trainer signal synchronization error and the corresponding data bit rate mapping value.

[0050] It should be added that the trainer reception optimization also includes the trainer reception accuracy monitoring qualification verification. The specific process is as follows: the difference between the trainer signal synchronization error before the trainer reception optimization and the trainer signal synchronization error after the trainer reception optimization is obtained, which is recorded as the trainer reception-qualification verification value; based on the obtained trainer reception-qualification verification value, a judgment is made: if the trainer reception-qualification verification value is greater than 0, a four-level alarm prompt is sent to indicate that the trainer reception accuracy monitoring is abnormal; otherwise, a trainer reception qualification prompt is sent, and a trainer feedback accuracy analysis is performed. By controlling the trainer reception-qualification verification value to be no greater than 0, it helps to ensure that the signal synchronization error after the trainer reception optimization is not greater than before the optimization, and avoids the situation where the optimization is invalid or the optimization leads to a decrease in reception accuracy, thereby ensuring the qualification of the trainer reception and ensuring that the trainer can stably and reliably receive leg strength training image data.

[0051] In this embodiment, by monitoring the accuracy of the trainer reception and optimizing the trainer reception, after confirming that the leg features of the image can be accurately identified, it is further checked whether the image data received by the trainer is synchronized and accurate. If it is inaccurate, that is, the trainer signal synchronization error is greater than the preset trainer signal synchronization error, it is optimized by adjusting the data bit rate, etc., so that the trainer can stably and accurately receive the leg strength training image data; thereby achieving the improvement of the accuracy of the trainer's adaptive resistance feedback.

[0052] It should be added that the specific process of the trainer feedback accuracy analysis is as follows: obtain the trainer feedback verification value, which is represented by the absolute value of the difference between the trainer resistance fed back by the trainer and the preset trainer resistance; quantify the degree of difference between the trainer feedback verification value and the preset trainer resistance feedback deviation obtained from the database to obtain the trainer feedback qualified value, and the preset trainer resistance is represented by the average value of the trainer resistance fed back by the trainer in the historical time period; make a judgment based on the trainer feedback qualified value: if the obtained trainer feedback qualified value is greater than 0, send a trainer feedback accuracy qualified prompt, otherwise, send a level 5 alarm prompt to indicate that the trainer feedback accuracy analysis is abnormal; the trainer feedback qualified value is used to reflect the feedback accuracy of the trainer adaptively feedbacking the resistance to the preset person after receiving the leg strength training image data.

[0053] As an implementation method of the second aspect, Figure 4 As shown, it is a structural diagram of the adaptive detection system of the trainer based on the leg strength training image provided in the embodiment of the present application. The adaptive detection system of the trainer based on the leg strength training image provided in the embodiment of the present application is applied as the adaptive detection method of the trainer based on the leg strength training image, including a leg strength training image initial acquisition qualification monitoring module, a leg feature recognition accuracy monitoring module and a trainer reception monitoring module.

[0054] like Figure 5 As shown, it is a coordinate diagram of the leg strength training image provided by the embodiment of the present application, which is composed of Figure 5 It can be seen that a plane rectangular coordinate system is set with the center point of the collected leg strength training image as the coordinate origin to quantify the spatial position of joint movement. The nodes marked in the figure are the position points corresponding to key parts such as the hip, knee, and ankle joints, which facilitates the analysis of the coordinated force of each joint and muscle.

[0055] Among them, the leg strength training image initial acquisition qualification monitoring module is used to evaluate the qualification of the leg strength training image initial acquisition during the adaptive detection process of the trainer, and determine whether to optimize the leg strength training image initial acquisition based on the evaluation results. The leg strength training image initial acquisition optimization is performed, which means that the uniformity of the grayscale distribution of the leg strength training image is improved through image grayscale setting and histogram equalization clarity optimization to improve the qualification of the leg strength training image initial acquisition.

[0056] The leg feature recognition accuracy monitoring module is used to quantify the leg feature recognition accuracy after the initial acquisition qualification assessment of the leg strength training image is passed, and determine whether to perform leg feature recognition optimization based on the quantification result. The leg feature recognition optimization means that the non-local mean denoising setting and gradient amplitude mapping are used to enhance the discrimination of the edge and contour information of the leg strength training image to enhance the accuracy of leg feature recognition of the leg strength training image.

[0057] The trainer reception monitoring module is used to monitor the trainer reception accuracy after the leg feature recognition accuracy is quantified and qualified. Based on the trainer reception accuracy monitoring results, it is determined whether to perform trainer feedback accuracy analysis to reflect the accuracy of the leg strength training image data fed back by the trainer.

[0058] In this embodiment, the acquisition and monitoring equipment used in this application includes an image processor, a data acquisition card, an industrial camera, a timer, etc., which monitors the qualified value of the trainer feedback and sends a five-level alarm prompt when the qualified value of the trainer feedback is not greater than 0 to prompt the trainer feedback accuracy analysis abnormality, thereby ensuring that the feedback function of the trainer is always under effective monitoring, reducing failures caused by abnormal feedback, ensuring that the training can be carried out normally and stably, and will not be frequently interrupted due to feedback problems. Once an abnormality occurs, it can respond quickly, thereby achieving the improvement of the accuracy of the trainer's adaptive resistance feedback.

[0059] In summary, the embodiment of the present application performs an initial acquisition qualification assessment of the leg strength training image and determines whether to perform initial acquisition optimization of the leg strength training image based on the assessment results. The leg strength training image that has passed the initial acquisition can more clearly present the muscles, bones and other features of the leg when the light may be unevenly distributed, thereby improving the accuracy of leg feature recognition. Then, after the initial acquisition qualification assessment of the leg strength training image is passed, the leg feature recognition accuracy is quantified, and based on the quantification results, it is determined whether to perform leg feature recognition optimization, which helps to compare the changes in the leg features of the image when the light may be unevenly distributed. Finally, after the leg feature recognition accuracy is quantified, the trainer reception accuracy is monitored, and based on the trainer reception accuracy monitoring results, it is determined whether to perform trainer feedback accuracy analysis, which helps to ensure that the trainer can correctly receive the results of leg feature recognition when the light may be unevenly distributed, and ensure that the trainer feedback can match the actual leg strength training situation, thereby achieving an improvement in the accuracy of the trainer's adaptive resistance feedback, and effectively solving the problem in the prior art of low accuracy of the trainer's adaptive resistance feedback due to interference in leg strength training image recognition.

[0060] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0061] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0062] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0064] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0065] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A training device adaptive detection method based on leg strength training images, characterized in that: The following steps are involved: During the adaptive detection process of the trainer, an assessment is performed on the eligibility of the initial acquisition of the leg strength training images, and based on the assessment results, it is determined whether to perform optimization of the initial acquisition of the leg strength training images. The optimization of the initial acquisition of the leg strength training images means improving the uniformity of the grayscale distribution of the leg strength training images by image grayscale setting and histogram equalization clarity optimization; After the leg strength training image initial collection is qualified, the leg feature recognition accuracy is quantified, and based on the quantification result, it is determined whether to perform leg feature recognition optimization, wherein the leg feature recognition optimization means enhancing the discrimination of edge and contour information of the leg strength training image through non-local mean denoising setting and gradient amplitude mapping; After the leg feature recognition accuracy is quantified and qualified, the trainer reception accuracy is monitored. Based on the trainer reception accuracy monitoring results, it is determined whether to conduct trainer feedback accuracy analysis to reflect the accuracy of the leg strength training image data fed back by the trainer.

2. The method for adaptive detection of a training device based on leg strength training images according to claim 1, wherein: The specific process of performing the qualification assessment of the initial acquisition of leg strength training images is as follows: S1, by quantifying the proportion of the total number of recognized and successfully recognized leg feature points in the leg strength training image, a complete interference value of the leg strength training image is obtained. If the complete interference value of the leg strength training image is not greater than the preset complete interference value of recognition, S2 is executed. Otherwise, a first-level alarm is issued to indicate that the leg strength training image is abnormal. S2, quantifying the proportion of the preset leg strength training image initial acquisition parameters and the leg strength training image initial acquisition parameters, and then weighting and coupling them with the preset leg strength training image initial acquisition control indicators obtained from the database to obtain a leg strength training image initial acquisition qualified evaluation value; The leg strength training image initial acquisition parameters include leg strength training image resolution deviation, leg image light uniformity interference value, leg strength training image initial acquisition delay and qualified leg strength training image complete interference value; The leg strength training image resolution deviation is used to reflect the degree of deviation between the number of pixels in the preset area and the preset number of pixels; The leg image light uniformity interference value is used to reflect the difference between the maximum brightness and the minimum brightness of the leg strength training image; The leg strength training image initial acquisition delay is used to reflect the degree of deviation between the duration of the leg strength training image and the preset initial acquisition duration; The qualified leg strength training image complete interference value is represented by a leg strength training image complete interference value that is not greater than a preset identification complete interference value; The preset leg strength training image initial acquisition control index is used to reflect the influence of the leg strength training image initial acquisition data on the leg strength training image initial acquisition qualified evaluation value; The leg strength training image initial acquisition qualification evaluation value is used to reflect the effect of the leg strength training image initial acquisition parameters and the preset leg strength training image initial acquisition parameters on the initial acquisition qualification level of the leg strength training image.

3. The method for adaptive detection of a training device based on leg strength training images according to claim 2, wherein: The specific process of determining whether to perform initial acquisition optimization of leg strength training images based on the evaluation results is as follows: If the leg strength training image initial acquisition qualification evaluation value is greater than the preset initial acquisition qualification value, a prompt indicating that the image initial acquisition is qualified is sent, and the leg feature recognition accuracy is quantified. Otherwise, a prompt indicating that the image initial acquisition is unqualified is sent, and optimization of the leg strength training image initial acquisition is performed; The initial acquisition optimization of the leg strength training image indicates that the image grayscale setting and the histogram equalization clarity optimization setting are performed in sequence; The steps of setting the image grayscale are as follows: Sending a prompt to a preset person to input the grayscale value of the unqualified leg strength training image and the leg strength training image initial acquisition qualified evaluation value into a database for grayscale value correction to obtain a qualified image grayscale value, wherein the unqualified leg strength training image represents a leg strength training image corresponding to the leg strength training image initial acquisition qualified evaluation value that is not greater than the preset initial acquisition qualified value; Sending a prompt to a preset person to set the grayscale of the leg strength training image based on the qualified image grayscale value and histogram equalization method; The image grayscale setting also includes: obtaining a histogram equalization evaluation value, which is specifically represented by the difference between the initial acquisition qualified evaluation value of the leg strength training image in the final state of the image grayscale setting and the initial acquisition qualified evaluation value of the leg strength training image in the initial state. If the histogram equalization evaluation value is greater than the preset equalization evaluation value, a prompt indicating that the image grayscale setting is qualified is sent, and the leg feature recognition accuracy is quantified. Otherwise, a histogram equalization clarity optimization setting is performed.

4. The method for adaptive detection of a training device based on leg strength training images according to claim 3, wherein: The specific process of the histogram equalization clear optimization setting is as follows: T1, sending a prompt to the preset personnel to process the leg strength training image based on the unsharp masking method to enhance the clarity and leg texture features of the leg strength training image after the image grayscale is set; T2, sending a prompt to the preset personnel to input the grayscale value of the leg strength training image in the final state of image grayscale setting and the initial acquisition qualified evaluation value of the leg strength training image into the database for mapping to obtain a qualified Gaussian blur radius adjustment value; T3, send a prompt to the preset personnel to gradually increase the Gaussian blur radius of the leg image corresponding to the leg strength training image based on the amplitude corresponding to the obtained qualified Gaussian blur radius adjustment value. If the initial acquisition qualified evaluation value of the leg strength training image obtained after the histogram equalization and clarity optimization setting is still not greater than the preset initial acquisition qualified value, send a secondary alarm prompt to indicate that the histogram equalization and clarity optimization setting is abnormal. Otherwise, the leg feature recognition accuracy is quantified.

5. The method for adaptive detection of a training device based on leg strength training images according to claim 1, wherein: The leg feature recognition accuracy is quantified, and whether to perform leg feature recognition optimization is determined based on the quantification result. The specific process is as follows: If the muscle positioning error of the acquired image is not greater than the preset muscle positioning error of the image acquired from the database, a notification indicating that the leg feature recognition accuracy is qualified is sent, and the accuracy of the training device reception is monitored; Otherwise, an unqualified prompt will be sent and leg feature recognition optimization will be performed; The image muscle positioning error is represented by the average value of the distance between each muscle position point successfully identified within a preset recognition time period and the corresponding preset muscle position point; The image muscle positioning error is used to reflect the accuracy of feature recognition of the leg strength training image within a preset recognition time period.

6. The method for adaptive detection of a training device based on leg strength training images according to claim 5, wherein: The specific process of leg feature recognition optimization is as follows: Step 1: Send a prompt to a preset person to process the leg strength training image based on the non-local means denoising method; Step 2: Input the qualified image pixel grayscale value and the image muscle positioning error into the database for mapping to obtain a gradient amplitude mapping value. If the obtained gradient amplitude mapping value is greater than the preset maximum gradient amplitude, a gradient amplitude mapping alarm prompt is issued. Otherwise, the corresponding gradient amplitude mapping value is marked as a qualified gradient amplitude mapping value, and a prompt is sent to the preset personnel to gradually increase the gradient amplitude of the leg strength training image by the amplitude corresponding to the qualified gradient amplitude mapping value. The qualified image pixel grayscale value represents the grayscale value of the leg strength training image corresponding to the leg strength training image initial acquisition qualified evaluation value that is not greater than the preset initial acquisition qualified value.

7. The method for adaptive detection of a training device based on leg strength training images according to claim 6, wherein: The leg feature recognition optimization also includes feature recognition-qualification verification; The specific process of feature identification-qualification verification is as follows: Obtaining a difference between a leg feature recognition accuracy quantification value before leg feature recognition optimization and a leg feature recognition accuracy quantification value after leg feature recognition optimization, and recording the difference as a feature recognition-qualification verification value; If the obtained feature recognition-qualification verification value is not greater than 0, a level 3 alarm prompt is sent to indicate that the leg feature recognition optimization is abnormal. Otherwise, a feature recognition qualified prompt is sent and the trainer reception accuracy is monitored; The feature recognition-qualification verification value is used to reflect the qualification level of the leg feature recognition optimization in the preset recognition time period.

8. The method for adaptive detection of a training device based on leg strength training images according to claim 1, wherein: After the leg feature recognition accuracy is quantified and qualified, the training device reception accuracy is monitored. The specific process is as follows: The difference between the time when the trainer receives the training signal and the preset trainer receiving time is quantified as the trainer signal synchronization error; The trainer signal synchronization error is used to reflect the qualification degree of the leg strength training image data received by the trainer in the preset trainer receiving time period; If the trainer signal synchronization error is greater than the preset trainer signal synchronization error, a trainer reception accuracy failure prompt is sent and the trainer reception optimization is performed; otherwise, a trainer reception accuracy failure prompt is sent and the trainer feedback accuracy analysis is performed; The training device reception optimization means improving the accuracy of the leg strength training image data received by the training device through data bit rate setting, and the data bit rate setting means sending a prompt to the preset personnel to gradually increase the training device data bit rate by the amplitude corresponding to the training device data bit rate mapping value; The method for obtaining the trainer data rate mapping value is as follows: inputting the number of transmission requests, the trainer data transmission bandwidth and the trainer signal synchronization error into a database, and performing mapping processing through the database to obtain the trainer data rate mapping value; The trainer reception optimization also includes trainer reception accuracy monitoring qualification verification, the specific process is as follows: Obtaining a difference between a trainer signal synchronization error before and after the trainer reception optimization, and recording the difference as a trainer reception-qualification verification value; If the trainer reception-qualification verification value is greater than 0, a level 4 alarm prompt is sent to indicate that the trainer reception accuracy monitoring is abnormal. Otherwise, a trainer reception qualified prompt is sent and the trainer feedback accuracy analysis is performed.

9. The method for adaptive detection of a training device based on leg strength training images according to claim 1, wherein: The specific process of the trainer feedback accuracy analysis is as follows: Obtaining a trainer feedback verification value, which is represented by the absolute value of the difference between the trainer resistance fed back by the trainer and the preset trainer resistance; Quantify the difference between the trainer feedback verification value and the preset trainer resistance feedback deviation obtained from the database to obtain the trainer feedback qualified value; If the obtained trainer feedback qualified value is greater than 0, a trainer feedback accuracy qualified prompt is sent; otherwise, a level 5 alarm prompt is sent to indicate that the trainer feedback accuracy analysis is abnormal; The trainer feedback qualification value is used to reflect the feedback accuracy of the trainer in adaptively feeding back resistance to the preset person after receiving the leg strength training image data.

10. A training device adaptive detection system based on leg strength training images, applying the training device adaptive detection method based on leg strength training images according to any one of claims 1 to 9, characterized in that: It includes a leg strength training image initial collection qualification monitoring module, a leg feature recognition accuracy monitoring module and a trainer reception monitoring module: The leg strength training image initial acquisition qualification monitoring module is used to evaluate the qualification of the leg strength training image initial acquisition during the adaptive detection process of the trainer, and determine whether to perform leg strength training image initial acquisition optimization based on the evaluation result. The leg strength training image initial acquisition optimization means improving the uniformity of the leg strength training image grayscale distribution through image grayscale setting and histogram equalization clarity optimization; The leg feature recognition accuracy monitoring module is used to quantify the leg feature recognition accuracy after the leg strength training image initial acquisition qualification assessment is passed, and determine whether to perform leg feature recognition optimization based on the quantification result, wherein the leg feature recognition optimization means enhancing the discrimination of edge and contour information of the leg strength training image through non-local mean denoising setting and gradient amplitude mapping; The trainer reception monitoring module is used to monitor the trainer reception accuracy after the leg feature recognition accuracy is quantified and qualified, and to determine whether to perform trainer feedback accuracy analysis based on the trainer reception accuracy monitoring result to reflect the accuracy of the leg strength training image data fed back by the trainer.

Images