Human body continuous action similarity evaluation method and evaluation device

Abstract

The invention provides a human body continuous action similarity evaluation method and evaluation device. The evaluation method comprises the steps of obtaining a color image sequence and a depth image sequence when a first human body moves; acquiring three-dimensional coordinates of the first human body key point relative to a camera coordinate system; intercepting a coordinate sequence of the first human body key points and forming a template action library; obtaining a frame of color image and a depth image when the second human body moves; acquiring three-dimensional coordinates of the second human body key point relative to the camera coordinate system; obtaining the time length of a template action sequence to be compared selected from a template action library; taking the intercepted second human body key point coordinate sequence as an input action sequence, wherein the time length of the intercepted second human body key point coordinate sequence is the same as that of the template action sequence, and the deadline is the latest time of the currently input second human body key point coordinate sequence; and evaluating the similarity between the input action and the template action. The similarity between the continuous action input by the user and the template action can be dynamically evaluated in real time.

Description

technical field [0001] The application belongs to the technical field of human motion analysis, and in particular relates to a method and an evaluation device for evaluating the similarity of continuous human motions. Background technique [0002] With the advancement of science and technology and the improvement of human living standards, people's demand for various sports is increasing. In the process of exercise, people are not only satisfied with the simple amount of exercise, but also pay more attention to the similarity between their own movements and the template movements. However, due to the limitation of time, venue and number of people, it is often difficult for people to obtain the action guidance of the coach at any time. In addition, even if people learn by watching teaching videos, there will be big differences between people's movements and template movements due to differences in understanding ability and lack of targeted teaching. In the prior art, there ...

AI Technical Summary

Problems solved by technology

However, due to the limitation of time, venue and number of people, it is often difficult for people to obtain the action guidance of the coach at any time

In addition, even if you learn by watching teaching videos, there will be a big difference between people's movements and template movements due to differences in understanding ability and lack of targeted teaching.

In the prior art, there is a static comparison of the difference between the input action and the template action, and it is not possible to dynamically compare the difference between the input action and the template action.

Images