Saliency Optimization from Robust Background Detection

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 mostl...

Full description

Saved in:
Bibliographic Details
Published in:2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 2814 - 2821
Main Authors: Zhu, Wangjiang, Liang, Shuang, Wei, Yichen, Sun, Jian
Format: Conference Proceeding Journal Article
Language:English
Published: IEEE 01.06.2014
Subjects:
Benchmark testing
Boundaries
Computer vision
Conferences
Cues
Image color analysis
Layout
Object detection
Optimization
Pattern recognition
Robustness
State of the art
ISSN:1063-6919, 1063-6919
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Conference-1
ObjectType-Feature-3
content type line 23
SourceType-Conference Papers & Proceedings-2
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2014.360