Geodesic distance framework for contour-based consistent stereo image segmentation

作     者：Li, Xujie Huang, Hui Wang, Yandan Hu, Mingxiao 

作者机构：Wenzhou Univ Intelligent Informat Syst Inst Wenzhou Peoples R China 

出 版 物：《JOURNAL OF ELECTRONIC IMAGING》 (电子成像杂志)

年 卷 期：2018年第27卷第5期

页      面：053047-053047页

核心收录：

学科分类：0808[工学-电气工程] 1002[医学-临床医学] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 0702[理学-物理学] 

基　　金：Zhejiang Provincial Natural Science Foundation of China [LY18F020022, LQ17F020002, LY14F020032] National Natural Science Foundation of China NVIDIA Corporation 

主　　题：stereo image segmentation contour extraction geodesic distance patch-based technique 

摘      要：This study concentrates on consistent object contour extraction method for stereo image segmentation after the object regions in the left image have been obtained. By taking advantage of the epipolar geometry, our approach introduces an energy optimization framework that incorporates both the stereo correspondence term and patch-based object contour probability term. The contour map is generated by integrating the terms of stereo correspondence and patch-based object contour probability;then, the optimal contours are obtained using geodesic distance technology. The core of the proposed method is to build upon an energy optimization framework with two key contributions: first, it incorporates the patch-based object contour probability term that introduces two search strategies to efficiently find the joint nearest neighbor patch pairs for the stereo image pair. The patch-based object contour probability term provides consistent and reliable priors for the contour extraction. Second, previous methods encounter missing pixels in the extracted contour in the occluded regions. Our approach overcomes this limit by introducing the geodesic distance technology to search the optimal contours. Experimental evaluation on Middlebury dataset and Adobe open dataset indicates that the results of our stereo image segmentation are comparable with or of higher quality than state-of-the-art methods. (c) 2018 SPIE and IS&T