A limb motion scoring system based on image recognition

Abstract

This invention provides a body movement scoring system based on image recognition, belonging to the field of image recognition processing technology. Its features include an image recording system, an image storage device, a computer-based body recognition module, and a comparison and evaluation module. The image recording system includes a planar camera and body node markers. The body node markers include several Bluetooth location signal transmission devices. The image storage device can pre-record relevant body node movement information. The computer-based body recognition module can retrieve image data and body movement data from the image storage device. The comparison and evaluation module compares the position of the body node movement information and combines it with the subjective judgment of relevant evaluators to make a final score. The advantages of this invention are: convenient and accurate acquisition of body movement information, and evaluation and grading based on the subjective scores of evaluators and data ranges, improving scoring efficiency and accuracy.

Description

Technical Field

[0001] This invention relates to the field of image recognition processing technology, and in particular to a limb movement scoring system based on image recognition. Background Technology

[0002] As universities place greater emphasis on physical education activities, the workload of teachers, whether in regular physical education classes or specialized sports training, is gradually increasing. This is especially true in exam grading, where the small number of teachers and large student population can severely impact overall efficiency and the professionalism of grading. Currently available methods use motion capture devices to evaluate participants' data and assign scores, but these methods have poor accuracy in motion capture and cannot adequately measure the standard of physical movements. Summary of the Invention

[0003] The purpose of this invention is to provide a limb movement scoring system based on image recognition, which solves the technical problem of poor limb movement capture accuracy in the prior art, and achieves high-precision and high-efficiency limb movement capture, making scoring convenient.

[0004] To achieve the above-mentioned objectives, the technical solution adopted by this invention is as follows:

[0005] A body movement scoring system based on image recognition includes an image recording system, an image storage device, a computer-based body recognition module, and a comparison and evaluation module. The image recording system includes a planar camera device and body node markers. The image recording system is positioned facing the subject. The body node markers include several Bluetooth location signal transmission devices, which are respectively located at the joints of the limbs and at the shoulders and hips. The planar camera device can capture the position images of the Bluetooth devices. The image storage device can pre-record relevant body node movement information and save the image data uploaded by the image recording system. The computer-based body recognition module can retrieve the image data and body movement data stored in the image storage device and construct corresponding 3D models and movement data based on the body node movement information. The comparison and evaluation module compares the pre-recorded body node movement information with the location and combines it with the subjective judgment of relevant evaluators to make a final score.

[0006] As an improvement, the planar camera device will identify the scene information after shooting and mark multiple fixed objects in the video. After the video is finished shooting, it will identify the objects that have not moved in the entire recording and use them to create a corresponding coordinate system for environmental comparison. Then, the limb node markers will be used to create corresponding planar coordinate motion data based on the environmental comparison markers.

[0007] As an improvement, the limb node marker is fixed to the subject's body with an elastic strap. The limb node marker has a red indicator light on the outside for easy video image processing. The limb node marker also includes a set of waist markers. The waist marker has four marker devices on its outside. When wearing it, the marker devices must be positioned on both sides of the waist, as well as in front and behind. The waist marker can establish a coordinate system for the body position to accurately measure the movement data of the limb nodes.

[0008] As an improvement, the image storage device can transmit signals to the image recording system and computer limb recognition module via the Internet. The limb node motion information can be pre-entered by the corresponding motion capture personnel, and the controllable range of the relative position of each node can be adjusted to accommodate people of different heights and body types.

[0009] As an improvement, the comparison and evaluation module can be used in conjunction with subjective evaluation to score and classify the evaluation results of different node movements. The scoring and classification is determined by comparing the movement range of nodes after comparing their movement paths and combining the final score. After comparing and calculating a large amount of data, the image data can be directly classified and sent back to the relevant grade reviewers for further review.

[0010] The beneficial effects of this invention are as follows: by setting up a planar camera device and limb node markers, two sets of coordinate systems can be established, thereby accurately identifying the corresponding movement information. By configuring a computer limb recognition module, it is possible to further facilitate the data evaluation of image data and refine the relevant motion data. By setting up a comparison evaluation module, the data data can be graded and rated in conjunction with the subjective judgment of relevant evaluators, thereby facilitating the scoring by reviewers. Attached Figure Description

[0011] Figure 1 This is a flowchart of a limb movement scoring system based on image recognition according to the present invention. Detailed Implementation

[0012] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0013] It should be noted that the terms "first" and "second" in this application are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0014] like Figure 1 As shown, a body movement scoring system based on image recognition includes an image recording system, an image storage device, a computer-aided body recognition module, and a comparison and evaluation module. The image recording system includes a planar camera and body node markers, positioned facing the subject. The body node markers include several Bluetooth position signal transmission devices, respectively positioned at the joints of the limbs and at the shoulders and hips. The planar camera captures the positional images of the Bluetooth devices. The image storage device can pre-record relevant body node movement information and simultaneously save the image data uploaded by the image recording system. The computer-aided body recognition module can retrieve the image data and body movement data stored in the image storage device and construct corresponding 3D models and movement data using the body node movement information. The comparison and evaluation module compares the pre-recorded body node movement information with the positional data and combines it with the subjective judgment of relevant evaluators to make a final score. The planar camera can acquire multiple sets of relevant movement data in a single shot, requiring the subject to wear body node markers with different matching signal sources.

[0015] After recording, the planar camera device identifies scene information and marks multiple fixed objects within the video. Once recording is complete, it identifies any stationary objects in the entire recording and uses this information to create a coordinate system for environmental comparison. Subsequently, it generates planar coordinate motion data for the limb node markers based on these environmental comparison markers. The limb node markers are secured to the subject with elastic straps. Each limb node marker has a red indicator light on its outer side for easy video image processing. The limb node markers also include a set of waist markers with four marker devices on their outer side. When worn, these marker devices must be positioned on both sides of the waist, as well as directly in front and behind. The waist markers establish a coordinate system based on body position for precise measurement of limb node motion data. The limb node markers can be secured to the subject using straps, adhesive, etc., as needed. For example, in track and field, they can be secured at the ankle. Vector representations can be added to the limb node markers to obtain their motion trajectory and orientation, thereby improving the accuracy of data analysis.

[0016] The image storage device can transmit signals to the image recording system and computer limb recognition module via the Internet. The limb node motion information can be pre-entered by corresponding motion capture personnel, and the controllable range of the relative position of each node can be adjusted to accommodate people of different heights and body types. The computer limb recognition module can manually adjust the node position information for different heights to further improve data accuracy.

[0017] The comparative evaluation module can work with subjective evaluation to score and categorize the evaluation results of different node movements. This scoring and categorization is determined by comparing the movement range of each node's movement path and combining this with the final score. After comparing and calculating a significant amount of data, the image data can be directly categorized and sent back to the relevant level of reviewers for further evaluation. The comparative evaluation module can determine the relevant data range based on the movement range of the limb marker device and, in conjunction with the reviewer's subjective evaluation, confirm the scoring standards for the relevant intervals. The comparative evaluation module can incorporate an AI data extraction module to facilitate the quantitative scoring of interval data.

[0018] When in use, the judges can set up a planar camera device on site. Then, after wearing the limb node identification device, the tester aligns the node identification device with their body in a "T" shape. At this time, fixed markers can be manually placed in the captured image for environmental comparison to facilitate data acquisition. During this process, the tester needs to wear clothing with a color that contrasts significantly with the environment. After the video is captured, the image data and node motion data are transmitted to the image storage device via the Internet. Then, the computer limb recognition module combines the pre-stored node motion standards to analyze the motion data and perform action modeling. The relevant data is then sent to the comparison and evaluation module, where the node motion trajectory is compared with the standard data. Combined with the judges' subjective scoring, relevant graded scoring data is obtained, thereby achieving batch and accurate scoring.

[0019] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A limb movement scoring system based on image recognition, characterized in that, The system includes an image recording system, an image storage device, a computer-aided limb recognition module, and a comparison and evaluation module. The image recording system comprises a planar camera and limb node markers, positioned facing the subject. The limb node markers include several Bluetooth location signal transmission devices, respectively positioned at the joints of the limbs, shoulders, and hips. The planar camera captures the positional images of the Bluetooth devices. The image storage device can pre-record relevant limb node movement information and simultaneously save the image data uploaded by the image recording system. The computer-aided limb recognition module can retrieve image data and limb movement data from the image storage device and construct corresponding 3D models and movement data using the limb node movement information. The comparison and evaluation module compares the pre-recorded limb node movement information with the location data and combines it with the subjective judgment of relevant evaluators to generate a final score.

2. The limb movement scoring system based on image recognition according to claim 1, characterized in that, After taking a picture, the planar camera device will identify the scene information and mark multiple fixed objects in the video. After the video is taken, it will identify the objects that have not moved in the entire recording and use them to create a corresponding coordinate system for environmental comparison. Then, the limb node markers will be used to create corresponding planar coordinate motion data based on the environmental comparison markers.

3. The limb movement scoring system based on image recognition according to claim 1, characterized in that, The limb node marker is fixed to the subject's body with an elastic strap. The limb node marker has a red indicator light on the outside for easy video image processing. The limb node marker also includes a set of waist markers. The waist marker has four marker devices on its outside. When wearing the marker, the marker devices must be positioned on both sides of the waist, as well as in front and behind. The waist marker can establish a coordinate system for the body position to accurately measure the movement data of the limb nodes.

4. The limb movement scoring system based on image recognition according to claim 1, characterized in that, The image storage device can transmit signals to the image recording system and computer limb recognition module via the Internet. The limb node motion information can be pre-entered by the corresponding motion capture personnel, and the controllable range of the relative position of each node can be adjusted to accommodate people of different heights and body types.

5. A limb movement scoring system based on image recognition according to claim 1, characterized in that, The comparative evaluation module can work with subjective evaluation to score and categorize the evaluation results of different node movements. The scoring and categorization are determined by comparing the movement range of nodes after comparing their movement paths, and combining the final score to confirm the categorization. After comparing and calculating a large amount of data, the image data can be directly categorized and sent back to the relevant grade reviewers for further review.

Images