Why Stereo Vision is Not Always About 3D Reconstruction

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/5947

Full metadata record

DC Field	Value	Language
dc.creator	Grimson, W. Eric L.	-
dc.date	2004-10-04T14:15:53Z	-
dc.date	2004-10-04T14:15:53Z	-
dc.date	1993-07-01	-
dc.date.accessioned	2013-10-09T02:42:04Z	-
dc.date.available	2013-10-09T02:42:04Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AIM-1435	-
dc.identifier	http://hdl.handle.net/1721.1/5947	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	It is commonly assumed that the goal of stereovision is computing explicit 3D scene reconstructions. We show that very accurate camera calibration is needed to support this, and that such accurate calibration is difficult to achieve and maintain. We argue that for tasks like recognition, figure/ground separation is more important than 3D depth reconstruction, and demonstrate a stereo algorithm that supports figure/ground separation without 3D reconstruction.	-
dc.format	11 p.	-
dc.format	393745 bytes	-
dc.format	520870 bytes	-
dc.format	application/octet-stream	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AIM-1435	-
dc.subject	stereo vision	-
dc.subject	camera calibration	-
dc.subject	noise sensitivity	-
dc.title	Why Stereo Vision is Not Always About 3D Reconstruction	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI