Dense Stereo Matching Based on PCNN
Xiao Shu, Chenhui Yang, Hui Liu · 2009
A key problem in stereo matching lies in selecting an appropriate window size. This paper presents a new method based on using small window for first-step matching and Pulse Coupled Neural Network for perfecting disparity maps. Our algorithm not only reflects the predominance that small window achieves sharper counter, but also gains accurate depth of the region with weak texture and reduces patches effectively. The experimental results indicate that this method could build dense disparity maps with high accuracy compared with common ways.