886 search results - page 37 / 178 » Computing Visual Attention from Scene Depth |
115
Voted
ICRA
2009
IEEE
15 years 7 months ago
2009
IEEE
Abstract— We address the problem of vision-based multiperson tracking in busy pedestrian zones using a stereo rig mounted on a mobile platform. Specifically, we are interested i...
105
Voted
ISVC
2010
Springer
14 years 11 months ago
2010
Springer
Abstract. We propose a novel Multiple Instance Learning (MIL) framework to perform target localization from image sequences. The proposed approach consists of a softmax logistic re...
114
Voted
IROS
2009
IEEE
15 years 7 months ago
2009
IEEE
— In this paper, we propose a novel approach for the visual navigation of unmanned aerial vehicles (UAV). In contrast to most available methods, a single perspective camera is us...
110
Voted
SI3D
2006
ACM
15 years 6 months ago
2006
ACM
Rendering a scene using a single depth image suffers from disocclusion errors as the view translates away from the reference view. We present the depth discontinuity occlusion cam...
BC
1998
15 years 8 days ago
1998
Abstract. In a stereoscopic system, both eyes or cameras have a slightly dierent view. As a consequence, small variations between the projected images exist (`disparities') ...