Multi-model human motion tracking method

Abstract

The invention discloses a multi-model human motion tracking method, and relates to the technical field of image processing, which mainly solves the problems that human motion ambiguity and time complexity are high and excellent three-dimensional body posture estimation cannot be obtained by increasing motion models purely in the conventional method. The multi-model human motion tracking method comprises the following steps of: (1) inputting a human motion video image to acquire a human silhouette and an edge and a skeleton line thereof; (2) detecting the positions of human articulation points; (3) training the motion models by a ridge regression method; (4) initializing a model set M1; (5) performing an interactive multi-model algorithm to acquire a human motion posture; and (6) activating the motion models which meet the activating condition, and terminating the motion models which meet the termination condition. The multi-model human motion tracking method has the advantages of low time complexity and good tracking effect, has high cost effectiveness, and can be applied in fields of sports training, animation production and the like.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to human body motion tracking, in particular to a multi-model human body motion tracking and three-dimensional posture estimation, which can be used in fields such as sports training and animation production. Background technique [0002] The main task of human motion tracking is to detect the human body from the image, locate the human body parts, then recognize the human motion posture, and finally reconstruct the three-dimensional human motion. Since the obtained video or image sequence is the projection of a 3D scene on a 2D image, a large amount of depth information is missing, and in the process of human body movement, self-occlusion of human body limbs often occurs, and the quality of video images cannot be guaranteed. The work of recovering human motion pose from unlabeled monocular videos is challenging. However, due to the potential application and economic value o...

AI Technical Summary

Problems solved by technology

In order to solve the shortcomings of the learning-based method, predecessors have tried to use the interactive multi-model algorithm IMM to complete human motion tracking, and use a carefully selected motion model set for a specific human motion mode to obtain a better tracking effect, but in practical applications , since a small set of motion models cannot solve the complexity and variability of human motion patterns, it is not feasible to simply increase the number of motion models. A Structural Multi-Model Approach for Human Motion Tracking

In a nutshell, the present invention solves the human body motion tracking problem by using the motion model trained by motion capture data and combining the LMS-VSMM algorithm framework on the basis of detecting the position of the joint points of the human body.

Images