1. DSpace at MEDIU
  2. Harvested articles مقالات مستوردة من مؤسسات وجامعات عالمية
  3. MIT Items
Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/6075
Full metadata record
DC FieldValueLanguage
dc.creatorDarrell, T.-
dc.creatorDemirdjian, D.-
dc.creatorChecka, N.-
dc.creatorFelzenswalb, P.-
dc.date2004-10-04T14:37:37Z-
dc.date2004-10-04T14:37:37Z-
dc.date2001-02-01-
dc.date.accessioned2013-10-09T02:42:44Z-
dc.date.available2013-10-09T02:42:44Z-
dc.date.issued2013-10-09-
dc.identifierAIM-2001-001-
dc.identifierhttp://hdl.handle.net/1721.1/6075-
dc.identifier.urihttp://koha.mediu.edu.my:8181/xmlui/handle/1721-
dc.descriptionIn a known environment, objects may be tracked in multiple views using a set of back-ground 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.-
dc.format5522496 bytes-
dc.format672260 bytes-
dc.formatapplication/postscript-
dc.formatapplication/pdf-
dc.languageen_US-
dc.relationAIM-2001-001-
dc.titlePlan-view Trajectory Estimation with Dense Stereo Background Models-
Appears in Collections:MIT Items

Files in This Item:
There are no files associated with this item.
Show simple item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.