Saliency Optimization from Robust Background Detection
Wangjiang Zhu, Shuang Liang, Yichen Wei et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2014
Recent progresses in salient object detection have exploited the boundary prior, or background information, to assist other saliency cues such as contrast, achieving state-of-the-art results. However, their usage of boundary prior is very simple, fragile, and the integration with other cues is mostly heuristic. In this work, we present new methods to address these issues. First, we propose a robust background measure, called boundary connectivity. It characterizes the spatial layout of image regions with respect to image boundaries and is much more robust. It has an intuitive geometrical interpretation and presents unique benefits that are absent in previous saliency measures. Second, we propose a principled optimization framework to integrate multiple low level cues, including our background measure, to obtain clean and uniform saliency maps. Our formulation is intuitive, efficient and achieves state-of-the-art results on several benchmark datasets.
Cited by 1,330 works. doi:10.1109/cvpr.2014.360
Authors
References
- A model of saliency-based visual attention for rapid scene analysis
- "GrabCut"
- SLIC Superpixels Compared to State-of-the-Art Superpixel Methods
- Efficient Algorithms for Shortest Paths in Sparse Networks
- Graph-Based Visual Saliency
- Saliency Detection: A Spectral Residual Approach
- Frequency-tuned salient region detection
- Global contrast based salient region detection
- Learning to Detect A Salient Object
- Learning to predict where humans look