Abstract | ||
---|---|---|
Recent work in salient object detection has considered the incorporation of depth cues from RGB-D images. In most cases, depth contrast is used as the main feature. However, areas of high contrast in background regions cause false positives for such methods, as the background frequently contains regions that are highly variable in depth. Here, we propose a novel RGB-D saliency feature. Local Background Enclosure (LBE) captures the spread of angular directions which are background with respect to the candidate region and the object that it is part of. We show that our feature improves over state-of-the-art RGB-D saliency approaches as well as RGB methods on the RGBD1000 and NJUDS2000 datasets. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/CVPR.2016.257 | 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) |
Field | DocType | Volume |
Computer vision,Viola–Jones object detection framework,Enclosure,Salient object detection,Pattern recognition,Computer science,Salience (neuroscience),Artificial intelligence,RGB color model,Depth perception,False positive paradox | Conference | 2016 |
Issue | ISSN | Citations |
1 | 1063-6919 | 23 |
PageRank | References | Authors |
0.59 | 10 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
David Feng | 1 | 25 | 1.43 |
Nick Barnes | 2 | 577 | 68.68 |
Shaodi You | 3 | 123 | 20.49 |
Chris Mccarthy | 4 | 97 | 10.41 |