Carregant...
Carregant...

Vés al contingut (premeu Retorn)

Dense segmentation-aware descriptors

Autor
Kokkinos, I.; Trulls, E.; Sanfeliu, A.; Moreno-Noguer, F.
Tipus d'activitat
Presentació treball a congrés
Nom de l'edició
IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2013
Any de l'edició
2013
Data de presentació
2013
Llibre d'actes
Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on
Pàgina inicial
2890
Pàgina final
2897
DOI
https://doi.org/10.1109/CVPR.2013.372 Obrir en finestra nova
Projecte finançador
FP7-ICT- 287617 Aerial Robotics Cooperative Assembly System
Visual Sense, Tagging visual data with semantic descriptions PCIN-2013-047
Repositori
http://hdl.handle.net/2117/22317 Obrir en finestra nova
URL
http://dx.doi.org/10.1109/CVPR.2013.372 Obrir en finestra nova
Resum
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...
Citació
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.
Paraules clau
appearance descriptors, computer vision, image segmentation, optical flow, pattern recognition, stereo
Grup de recerca
VIS - Visió Artificial i Sistemes Intel.ligents

Participants