Unified optical flow field approach to motion analysis from a sequence of stereo images

作者:

Highlights:

摘要

In this paper a new approach to motion analysis from stereo image sequences using unified temporal and spatial optical flow field (UOFF) is reported. That is, based on a four-frame rectangular model and the associated six UOFF field quantities, a set of equations is derived from which both position and velocity can be determined. It does not require feature extraction and correspondence establishment, which are known to be difficult, and only partial solutions suitable for simplistic situations have been developed. Furthermore, it is capable of detecting multiple moving objects even when partial occlusion occurs, and is potentially suitable for nonrigid motion analysis. Unlike the current existing techniques for motion analysis from stereo imagery, the recovered motion by using this new approach is for a whole continuous field instead of only for some features. It is a purely optical flow approach. Two experiments are presented to demonstrate the feasibility of the approach.

论文关键词:Computer vision,Motion analysis,Optical flow,Unified optical flow field,Stereo image sequence,Image sequence processing

论文评审过程:Received 10 March 1993, Revised 8 March 1994, Accepted 7 May 1994, Available online 20 May 2003.

论文官网地址:https://doi.org/10.1016/0031-3203(94)90078-7