Superpixel-Based Global Optimization Method for Stereo Disparity Estimation

摘要：

　　We proposed a novel global optimization method based on superpixel for stereo matching in this paper.Comparing with the pixel-based global optimization methods,the matching accuracy of our method is significantly improved.For improving the initial matching cost’s accuracy,we developed an adaptive matching window integrated with shape and size information to build the data term.To ensure the soft constraints of planar disparity distribution,a superpixel-based plane fitting method is introduced to obtain the initial disparity plane.We present a global optimization framework with data term and pixel-based smooth term to refine the disparity results.The experimental results on the Middlebury Stereo Datasets show that our method outperforms some state-of-the-art pixel-based global optimization approaches both quantitatively and qualitatively.

关键词： global optimization stereo disparity estimation superpixel stereo matching

作者: Haiqiang Jin Sheng Liu Shaobo Zhang Gaoxuan Ying

作者单位: College of Computer Science and Technology,Zhejiang University of Technology Hangzhou,310023,Zhejiang,P.R. China

会议类型: 国际会议

会议名称: Chinese Conference on Pattern Recognition, CCPR(2014年全国模式识别学术会议)

会议地点: 长沙

会议语种:英文

页码: 445-454

在线出版日期: 2014-11-01（万方平台首次上网日期，不代表论文的发表时间）