Loading...
Loading...

Go to the content (press return)

Dense segmentation-aware descriptors

Author
Kokkinos, I.; Trulls, E.; Sanfeliu, A.; Moreno-Noguer, F.
Type of activity
Presentation of work at congresses
Name of edition
IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2013
Date of publication
2013
Presentation's date
2013
Book of congress proceedings
Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on
First page
2890
Last page
2897
DOI
https://doi.org/10.1109/CVPR.2013.372 Open in new window
Project funding
FP7-ICT- 287617 Aerial Robotics Cooperative Assembly System
Visual Sense, Tagging visual data with semantic descriptions PCIN-2013-047
Repository
http://hdl.handle.net/2117/22317 Open in new window
URL
http://dx.doi.org/10.1109/CVPR.2013.372 Open in new window
Abstract
In this work we exploit segmentation to construct appearance descriptors that can robustly deal with occlusion and background changes. For this, we downplay measurements coming from areas that are unlikely to belong to the same region as the descriptor’s center, as suggested by soft segmentation masks. Our treatment is applicable to any image point, i.e. dense, and its computational overhead is in the order of a few seconds. We integrate this idea with Dense SIFT, and also with Dense Scale and...
Citation
Trulls, E. [et al.]. Dense segmentation-aware descriptors. A: IEEE Conference on Computer Vision and Pattern Recognition. "Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on". Portland: 2013, p. 2890-2897.
Keywords
appearance descriptors, computer vision, image segmentation, optical flow, pattern recognition, stereo
Group of research
VIS - Artificial Vision and Intelligent Systems

Participants