A survey on stereo vision matching algorithms

Stereo matching is an important research topic in the field of stereo vision. According to the stereo matching information, stereo matching algorithms can be divided into local, global, and semi-global algorithms. This paper summarizes the advantages and shortcomings of these matching algorithms. An experimental platform is set up for health care, and some matching algorithms are tested. Experimental results demonstrate that the dimensionality reduction and minimum spanning tree algorithm outperform guided filter and binary method in terms of both accuracy and speed.