Salient object detection via boosting object-level distinctiveness and saliency refinement |
| |
| Affiliation: | 1. School of Automation, Huazhong University of Science and Technology, Wuhan, 430074, China;2. National Key Lab of Science and Technology on Multi-spectral Information Processing, Wuhan 430074, China;1. College of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024, China;2. Department of Information Management, Chaoyang University of Technology, Taichung, Taiwan;1. Department of Computer Science, University of California, Irvine, USA;2. School of Computer Science and Center for OPTical IMagery Analysis and Learning (OPTIMAL), Northwestern Polytechnical University, China;3. Faculty of Information and Communication Technology, Mahidol University, Thailand;1. Graduate School at Shenzhen, Tsinghua University, Shenzhen 518055, Guangdong, China;2. University of Virginia, Department of ECE, Charlottesville, VA 22904, USA;3. BJUT Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China |
| |
| Abstract: | Many salient object detection approaches share the common drawback that they cannot uniformly highlight heterogeneous regions of salient objects, and thus, parts of the salient objects are not discriminated from background regions in a saliency map. In this paper, we focus on this drawback and accordingly propose a novel algorithm that more uniformly highlights the entire salient object as compared to many approaches. Our method consists of two stages: boosting the object-level distinctiveness and saliency refinement. In the first stage, a coarse object-level saliency map is generated based on boosting the distinctiveness of the object proposals in the test images, using a set of object-level features and the Modest AdaBoost algorithm. In the second stage, several saliency refinement steps are executed to obtain a final saliency map in which the boundaries of salient objects are preserved. Quantitative and qualitative comparisons with state-of-the-art approaches demonstrate the superior performance of our approach. |
| |
| Keywords: | Saliency Salient object detection Object-level distinctiveness Boosting algorithm Saliency refinement |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
