In a known environment, objects may be tracked in multiple views using a set of background models. Stereo-based models can be illumination-invariant, but often have undefined values which inevitably lead to foreground classification errors. We derive dense stereo models for object tracking using long-term, extended dynamic-range imagery, and by detecting and interpolating uniform but unoccluded planar regions. Foreground points are detected quickly in new images using pruned disparity search. We adopt a "late-segmentation" strategy, using an integrated plan-view density representation. Foreground points are segmented into object regions only when a trajectory is finally estimated, using a dynamic programming-based method. Object entry and exit are optimally determined and are not restricted to special spatial zones.
Plan-view trajectory estimation with dense stereo background models
Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 ; 2 ; 628-635 vol.2
2001-01-01
893536 byte
Conference paper
Electronic Resource
English
Plan-View Trajectory Estimation with Dense Stereo Background Models
British Library Conference Proceedings | 2001
|Handling occlusions in dense multi-view stereo
IEEE | 2001
|Handling Occlusions in Dense Multi-View Stereo
British Library Conference Proceedings | 2001
|Plan View Display (PVD) Background Lighting
NTIS | 1976
|Multi-View Stereo Reconstruction of Dense Shape and Complex Appearance
British Library Online Contents | 2005
|