Action evaluation method based on human body three-dimensional articulation point detection

Abstract

The invention relates to an action evaluation method based on human body three-dimensional articulation point detection, which belongs to the field of computer vision and comprises the following steps: S1, performing human body three-dimensional articulation point detection on a single-frame picture after video framing; S2, extracting key frames of a specified number of frames of the video; S3, constructing motion vector features and joint kinetic energy features, and extracting feature values; and S4, constructing a key frame action similarity comparison model through multi-feature fusion: fusing the sub-features in the step S3, and constructing a personalized model for different types of actions; constructing a motion vector feature similarity function based on cosine similarity, and constructing a joint kinetic energy similarity function based on a weighting function; and obtaining a key frame action similarity comparison model based on the two similarity functions, comparing the action to be detected with the key frame set of the standard action, and finally obtaining the action similarity of the motion video. The method is more accurate and scientific, and can be used for physical fitness action correction and teaching.

Description

Technical field [0001] The invention belongs to the field of computer vision technology, and particularly relates to an action evaluation method based on three-dimensional joint point detection of the human body. Background technique [0002] With the advancement of artificial intelligence algorithms and computer image processing performance, posture assessment and behavioral understanding of targets in videos have become hot issues in the field of computer vision. And it has been applied in many fields, such as sports-assisted training, behavioral anomaly detection, gesture and gait recognition, etc. [0003] Human posture assessment can be widely used in various sports. Human body movement recognition is used in physical education and fitness teaching to capture and analyze movements to obtain personalized technical diagnosis reports and provide auxiliary training tools for athletes and coaches. , improve the level of athletes. [0004] The standard degree of movements i...

AI Technical Summary

Problems solved by technology

[0006] However, there is still a lack of effective solutions for using sports videos to analyze and evaluate the actions of target people.

One of the difficulties is that the two-dimensional human posture assessment is easily affected by occlusions, and the accuracy of unconventional movements such as interlaced joints is low. The second difficulty is that there are physical differences between individuals, such as fat or thin, tall or short. Calculating the Euclidean distance of the joint points to evaluate the accuracy of the action is low; the third difficulty is that the same action can be performed by different people at different speeds, and it cannot be compared and analyzed frame by frame

[0007] To sum up, there is currently a lack of mature algorithms and products for the standard evaluation of motion in sports videos.

Images