A kind of human posture training method

Abstract

The invention relates to a human body posture training method. After collecting the key frames of the actions of the coach and the trainees, and then collecting the action video data of the coaches and the trainees, first use the DTW algorithm to make the duration and timing of the trainer's action video and the trainee's action video consistent, and establish a trainer-based The first feature plane group of the action key frame and the second feature plane group of the student’s action key frame match the key frame of the coach’s action and the key frame of the student’s action by comparing the angle between their normal vectors, and then obtain the detailed coordinates of the joint points of the human body The included angles of the side vectors in the second characteristic plane group are compared with the included angles of the side vectors in the first characteristic plane group to confirm the similarity of the student's movements. The benefit of the invention lies in improving the trainee's training exercise effect, and ensuring that the movements are sufficiently safe and free from hidden dangers to health. It enables students to gain sufficient training experience from one movement and improves the training effect of students.

Description

technical field [0001] The invention relates to the technical field of motion capture training evaluation, in particular to a human body posture training method. Background technique [0002] Human body pose recognition refers to the process of recovering the position of human body joints in an image or video based on a video or image. According to the image type, human pose recognition algorithms can be divided into algorithms based on depth maps and algorithms directly based on RGB images. Because the depth map algorithm has high requirements on image acquisition equipment, resulting in high cost, it is only suitable for high-level applications. Human body posture recognition algorithms based on RGB images have low equipment requirements, especially nowadays hardware equipment manufacturers provide a A TOF radar, the so-called time-of-flight 3D imaging sensor, continuously sends light pulses to the target, and then uses the sensor to receive the light returned from the ob...

AI Technical Summary

Problems solved by technology

At present, there is no human body posture recognition training method based on RGB images. In general, signal emitters are placed on the human body to track the posture of the human body. The cost is high. This kind of sports teaching equipment can only be used in the national training center class. Professional high-level applications are thousands of miles away from ordinary people

Images