Salient Object Detection based on Boundary Contrast with Regularized Manifold Ranking
文献类型：会议论文
| 作者 | Luo, Yongkang1 ; Wang, Peng1; Li, Wanyi1; Shang, Xiaopeng2; Qiao, Hong3,4; Wang Peng
|
| 出版日期 | 2016-06-12 |
| 会议日期 | June 12-15, 2016 |
| 会议地点 | Guilin, China |
| 关键词 | Salient Object Detection Manifold Ranking Contrast Saliency Boundary Connectivity |
| 英文摘要 | Salient object detection via graph-based manifold ranking, which exploits the boundary prior by using image boundaries as labelled background queries, always achieves impressive performance. However, when the salient object broadly touches the image boundary, this method is fragile and may fail. To address this issue, we present a novel approach which bases on boundary contrast with regularized manifold ranking. First, we compute the contrast saliency against the image boundary as ranking queries, instead of directly using the boundaries as background queries. Second, we use an affinity matrix with regularization for manifold ranking to infer saliency value. Third, we integrate saliency inference result with foregroundness based on boundary connectivity to improve the detection accuracy. Last, we adopt multiscale method to mitigate the object scale effect in saliency detection. Experimental results on three benchmark datasets show that the proposed method achieves comparable or better performance than stat-of-the-art methods. |
| 会议录 | 12th World Congress on Intelligent Control and Automation (WCICA)
 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/11606]  |
| 专题 | 智能机器人系统研究 |
| 通讯作者 | Wang Peng |
| 作者单位 | 1.The Research Center of Precision Sensing and Control, Institute of Automation, Chinese Academy of Sciences 2.Beijing Aerospace Automatic Control Institute 3.The State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences 4.CAS Center for Excellence in Brain Science and Intelligence Technology (CEBSIT) |
| 推荐引用方式 GB/T 7714 | Luo, Yongkang,Wang, Peng,Li, Wanyi,et al. Salient Object Detection based on Boundary Contrast with Regularized Manifold Ranking[C]. 见:. Guilin, China. June 12-15, 2016. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。