Saliency Detection via Depth-Induced Cellular Automata on Light Field
- 点击次数：
- 论文类型：期刊论文
- 发表时间：2020-01-01
- 发表刊物：IEEE TRANSACTIONS ON IMAGE PROCESSING
- 收录刊物：EI、SCIE
- 卷号：29
- 页面范围：1879-1889
- ISSN号：1057-7149
- 关键字：Saliency detection; Image color analysis; Automata; Three-dimensional
displays; Two dimensional displays; Visualization; Computational
modeling; Saliency detection; light field; focusness cue; depth cue;
depth-induced cellular automata (DCA) model
- 摘要：Incorrect saliency detection such as false alarms and missed alarms may lead to potentially severe consequences in various application areas. Effective separation of salient objects in complex scenes is a major challenge in saliency detection. In this paper, we propose a new method for saliency detection on light field to improve the saliency detection in challenging scenes. We construct an object-guided depth map, which acts as an inducer to efficiently incorporate the relations among light field cues, by using abundant light field cues. Furthermore, we enforce spatial consistency by constructing an optimization model, named Depth-induced Cellular Automata (DCA), in which the saliency value of each superpixel is updated by exploiting the intrinsic relevance of its similar regions. Additionally, the proposed DCA model enables inaccurate saliency maps to achieve a high level of accuracy. We analyze our approach on one publicly available dataset. Experiments show the proposed method is robust to a wide range of challenging scenes and outperforms the state-of-the-art 2D/3D/4D (light-field) saliency detection approaches.
- 发表时间：2020-01-01
