Multi-person motion capture method based on three-dimensional hypothesis spatial clustering

Abstract

The invention provides a multi-person motion capture method based on three-dimensional hypothesis spatial clustering. The method can be used for unmarked human motion capture. The method comprises thesteps of associating two-dimensional joint point candidate points between different views, reconstructing three-dimensional joint point candidate points, and carrying out three-dimensional attitude analysis and attitude tracking. Under the condition that a human body model is not utilized or any human body prior knowledge is assumed, stable and credible two-dimensional and global three-dimensional human body posture estimation can be carried out on a plurality of persons with different figures and unfixed number of people. The generated posture meets the multi-view geometric constraint and the human body bone length constraint, and robust and credible human body posture estimation under challenging scenes such as multi-person mutual shielding and close interaction is achieved.

Description

technical field [0001] The invention relates to a multi-person motion capture method based on three-dimensional hypothetical space clustering. Background technique [0002] According to different input data, the existing 3D human pose estimation methods can be divided into: based on monocular RGB image (sequence); based on depth image (sequence); and based on multi-view image (sequence). Estimating 3D human body pose based on monocular RGB images (sequences) is a problem with serious constraints. The observation input of the system is a complex natural image, and the state output is a high-dimensional human body pose. The process from observation input to state output is highly nonlinear. . Insufficient 3D pose training data sets, differences in the size and proportion of different human bodies, and the high dimensionality of the 3D pose space all make the reliability of 3D pose reconstruction a key problem to be solved. The 3D human pose estimation method based on depth i...

AI Technical Summary

Problems solved by technology

However, the 3D pose data set is difficult to obtain and the scale is small; at the same time, the state parameters of the 3D pose have a high dimensionality, and the individual body proportions and sizes vary greatly

This leads to the inability to guarantee the reliability of the 3D pose estimation results

Secondly, most 3D pose estimation methods only consider that there is only one person in the scene, and it is difficult to extend to multi-person scenes

Images