期刊
IEEE TRANSACTIONS ON MULTIMEDIA
卷 21, 期 7, 页码 1660-1671出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMM.2018.2884481
关键词
Co-saliency detection; RGBD images; global sparsity reconstruction; pairwise sparsity reconstruction; energy function refinement
资金
- National Natural Science Foundation of China [61520106002, 61722112, 61731003, 61332016, 61620106009, U1636214, 61602345]
- Key Research Program of Frontier Sciences, Chinese Academy of Sciences [QYZDJ-SSW-SYS013]
- Technology Research and Development Program of Tianjin [15ZXHLGX00130]
Co-saliency detection aims to discover common and salient objects in an image group containing more than two relevant images. Moreover, depth information has been demonstrated to be effective for many computer vision tasks. In this paper, we propose a novel co-saliency detection method for RGBD images based on hierarchical sparsity reconstruction and energy function refinement. With the assistance of the intrasaliency map, the inter-image correspondence is formulated as a hierarchical sparsity reconstruction framework. The global sparsity reconstruction model with a ranking scheme focuses on capturing the global characteristics among the whole image group through a common foreground dictionary. The pairwise sparsity reconstruction model aims to explore the corresponding relationship between pairwise images through a set of pairwise dictionaries. In order to improve the intra-image smoothness and inter-image consistency, an energy function refinement model is proposed, which includes the unary data term, spatial smooth term, and holistic consistency term. Experiments on two RGBD co-saliency detection benchmarks demonstrate that the proposed method outperforms the state-of-the-art algorithms both qualitatively and quantitatively.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据