Tracking method of three-dimensional mark point sequence and system thereof

Abstract

The invention relates to a tracking method of a three-dimensional mark point sequence and a system thereof. The method comprises the following steps: step 1: reading a chain structure model of the human body, and determining a rigid body and characteristic points; step 2: acquiring frames of motion images, wherein each frame has a plurality of images, the images have two-dimensional mark points, and the first frame has recognized three-dimensional mark points; step 3: projecting the three-dimensional mark points recognized in the previous frame in the image of the current frame, searching two-dimensional mark points corresponding to the characteristic points according to the projection, and reconstructing candidate three-dimensional mark points of the characteristic points through the two-dimensional mark points to form a candidate mark point set; and step 4: enumerating mark point combinations from the candidate mark point set of the rigid body, computing corresponding mark likelihood function values, reserving the mark point combination corresponding to the maximum value, and recognizing the candidate three-dimensional mark points in the mark point combination as the three-dimensional mark points of the characteristic points in the current frame. The invention can exactly track each characteristic point in the rigid body of the chain structure model of the human body from the acquired mark point sequence.

Description

Technical field [0001] The invention relates to the field of computer vision and pattern recognition, and in particular to a tracking method and system for a three-dimensional mark point sequence. Background technique [0002] Since the 1980s, optical motion capture technology has become more mature. In optical motion capture, it is necessary to paste reflective markers on the captured object, and use multiple synchronized calibrated cameras to capture the images of these markers, and then from the images The two-dimensional marker points are extracted and tracked and reconstructed to obtain the coordinates of the three-dimensional marker points, and then the motion parameters of the captured object are calculated. [0003] Since the human body movement is more complicated, the marker points are often occluded by the limbs, and the marker points will inevitably fail to track during the tracking process. Therefore, a robust method is needed to improve the tracking effect. [0004] In...

AI Technical Summary

Problems solved by technology

[0003] Due to the complexity of human body movement, marker points are often blocked by limbs, which will inevitably lead to marker point tracking failure during the tracking process, so a robust method is needed to improve the tracking effect

[0004] In addition, the tracking method cannot fully guarantee that all markers are correctly identified, so the problem of marker loss needs to be dealt with in the actual capture system

In the current motion capture system, in order to solve the problem of missing markers, it often requires a very cumbersome manual data repair process, such as the Fill tools in the mainstream commercial system Vicon iQ, and manual data repair often requires rich experience in human motion data It is difficult for ordinary personnel to complete

In addition, manual patching data often causes patching errors, which brings great difficulties to accurate motion tracking of subsequent frames.

Images