文献类型：期刊文献

英文题名：Illumination-Invariant Video Cut-Out Using Octagon Sensitive Optimization

作者：Chen, Zhihua[1];Wang, Jingye[1];Sheng, Bin[2,3];Li, Ping[4];Feng, David Dagan[5]

机构：[1]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China;[2]Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, Shanghai 200240, Peoples R China;[3]Shanghai Jiao Tong Univ, AI Inst, MoE Key Lab Artificial Intelligence, Shanghai 200240, Peoples R China;[4]Macau Univ Sci & Technol, Fac Informat Technol, Macau 999078, Peoples R China;[5]Univ Sydney, Sch Informat Technol, Biomed & Multimedia Informat Technol Res Grp, Sydney, NSW 2006, Australia

年份：2020

卷号：30

期号：5

起止页码：1410

外文期刊名：IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY

收录：;EI(收录号：20191106621540);WOS:【SCI-EXPANDED(收录号:WOS:000534237900016)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 61872241, Grant 61572316, Grant 61672228, and Grant 61370174, in part by the Project of Establishment of Shanghai Belt and Road Joint Laboratory under Grant 18410750700, in part by the National Key Research and Development Program of China under Grant 2017YFE0104000 and Grant 2016YFC1300302, in part by the Macau Science and Technology Development Fund under Grant 0027/2018/A1, in part by the Science and Technology Commission of Shanghai Municipality under Grant 18410750700, Grant 17411952600, and Grant 16DZ0501100, and in part by the Shanghai Automotive Industry Science and Technology Development Foundation under Grant 1837.

语种：英文

外文关键词：Image segmentation; Lighting; Motion segmentation; Object segmentation; Feature extraction; Task analysis; Optical imaging; Video cut-out; illumination-invariant; local features; seeds update; graph-cut

摘要：This paper presents an effective video cut-out approach, which can be utilized to segment the moving object in video shots. We first introduce the Octagon-Sensitive-Filtering (OSF) and its illumination invariant feature (IIF), which is computed on each pixel of the image via adding contributions from neighboring pixels. We integrate our IIF into the variational model and obtain the seeds during preprocessing to help address large displacement and illumination changes. An effective seed update method based on tracking-then-refinement based on IIF is presented to compensate for location ambiguities, and the strategy is effective to deal with illumination variances and objects deformation. Furthermore, we apply the IIF-based graph-cut to deal with fuzzy boundaries. Multiple experiments on quantitative challenging datasets have shown the robustness, high-quality video cut-out and efficiency of our approach to acute variances of illumination and complex motion.