Robust Visual Saliency Optimization Based on Bidirectional Markov Chains | |
Jiang, Fengling2,3,4; Kong, Bin2,5; Li, Jingpeng1; Dashtipour, Kia1; Gogate, Mandar6 | |
刊名 | COGNITIVE COMPUTATION |
2020-05-29 | |
关键词 | Saliency detection Bidirectional absorbing Markov chain Background and foreground possibility |
ISSN号 | 1866-9956 |
DOI | 10.1007/s12559-020-09724-6 |
通讯作者 | Kong, Bin(bkong@iim.ac.cn) |
英文摘要 | Saliency detection aims to automatically highlight the most important area in an image. Traditional saliency detection methods based on absorbing Markov chain only take into account boundary nodes and often lead to incorrect saliency detection when the boundaries have salient objects. In order to address this limitation and enhance saliency detection performance, this paper proposes a novel task-independent saliency detection method based on the bidirectional absorbing Markov chains that jointly exploits not only the boundary information but also the foreground prior and background prior cues. More specifically, the input image is first segmented into number of superpixels, and the four boundary nodes (duplicated as virtual nodes) are selected. Subsequently, the absorption time upon transition node's random walk to the absorbing state is calculated to obtain the foreground possibility. Simultaneously, foreground prior (as the virtual absorbing nodes) is used to calculate the absorption time and get the background possibility. In addition, the two aforementioned results are fused to form a combined saliency map which is further optimized by using a cost function. Finally, the superpixel-level saliency results are optimized by a regularized random walks ranking model at multi-scale. The comparative experimental results on four benchmark datasets reveal superior performance of our proposed method over state-of-the-art methods reported in the literature. The experiments show that the proposed method is efficient and can be applicable to the bottom-up image saliency detection and other visual processing tasks. |
资助项目 | China Scholarship Council ; National Natural Science Foundation of China[913203002] ; Pilot Project of Chinese Academy of Sciences[XDA08040109] ; Fundamental Research Funds for the Central Universities of China[ACAIM190302] ; Universities Joint Key Laboratory of Photoelectric Detection Science and Technology in Anhui Province[2019GDTCZD02] |
WOS关键词 | BOTTOM-UP ; TOP-DOWN ; OBJECT DETECTION ; INFORMATION ; ATTENTION ; MODEL |
WOS研究方向 | Computer Science ; Neurosciences & Neurology |
语种 | 英语 |
出版者 | SPRINGER |
WOS记录号 | WOS:000536324300001 |
资助机构 | China Scholarship Council ; National Natural Science Foundation of China ; Pilot Project of Chinese Academy of Sciences ; Fundamental Research Funds for the Central Universities of China ; Universities Joint Key Laboratory of Photoelectric Detection Science and Technology in Anhui Province |
内容类型 | 期刊论文 |
源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/103169] |
专题 | 中国科学院合肥物质科学研究院 |
通讯作者 | Kong, Bin |
作者单位 | 1.Univ Stirling, Div Comp Sci & Math, Stirling FK9 4LA, Scotland 2.Chinese Acad Sci, Inst Intelligent Machines, Hefei 230031, Peoples R China 3.Univ Sci & Technol China, Hefei 230026, Peoples R China 4.Hefei Normal Univ, Sch Comp Sci & Technol, Hefei 230061, Peoples R China 5.Key Lab Biomimet Sensing & Adv Robot Technol, Hefei 230031, Peoples R China 6.Edinburgh Napier Univ, Sch Comp, Edinburgh EH10 5DT, Midlothian, Scotland |
推荐引用方式 GB/T 7714 | Jiang, Fengling,Kong, Bin,Li, Jingpeng,et al. Robust Visual Saliency Optimization Based on Bidirectional Markov Chains[J]. COGNITIVE COMPUTATION,2020. |
APA | Jiang, Fengling,Kong, Bin,Li, Jingpeng,Dashtipour, Kia,&Gogate, Mandar.(2020).Robust Visual Saliency Optimization Based on Bidirectional Markov Chains.COGNITIVE COMPUTATION. |
MLA | Jiang, Fengling,et al."Robust Visual Saliency Optimization Based on Bidirectional Markov Chains".COGNITIVE COMPUTATION (2020). |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论