期刊名称：International Journal of Signal Processing, Image Processing and Pattern Recognition
印刷版ISSN：2005-4254
出版年度：2016
卷号：9
期号：6
页码：35-46
DOI：10.14257/ijsip.2016.9.6.04
出版社：SERSC
摘要：In order to increase the effect of matching for local stereo matching method and decrease the amount of computation, a new adaptive weight based local stereo matching method is proposed in this paper. In this method, two methods are mainly employed to construct weight model: (1) Neural Network is used to establish the spatial weight model, which makes good use of the pixels in support window; (2) An edge hold off Mean-Shift method is proposed to distribute the intensity weight accurately. For decreasing the matching cost error, the census transform is introduced to calculate the matching cost. The influence of the parameters on the performance of our method is also discussed at last. Simulation results indicate that the performance of our method is better than that of Yoon's method under low support window.
关键词：Neural Network; Edge Hold Off; Stereo Vision; Adaptive Weight
