Robust and Efficient 3D Recognition by Alignment

dc.creator	Alter, Tao Daniel
dc.date	2004-10-20T19:55:26Z
dc.date	2004-10-20T19:55:26Z
dc.date	1992-09-01
dc.date.accessioned	2013-10-09T02:46:58Z
dc.date.available	2013-10-09T02:46:58Z
dc.date.issued	2013-10-09
dc.identifier	AITR-1410
dc.identifier	http://hdl.handle.net/1721.1/6799
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721
dc.description	Alignment is a prevalent approach for recognizing 3D objects in 2D images. A major problem with current implementations is how to robustly handle errors that propagate from uncertainties in the locations of image features. This thesis gives a technique for bounding these errors. The technique makes use of a new solution to the problem of recovering 3D pose from three matching point pairs under weak-perspective projection. Furthermore, the error bounds are used to demonstrate that using line segments for features instead of points significantly reduces the false positive rate, to the extent that alignment can remain reliable even in cluttered scenes.
dc.format	113 p.
dc.format	903052 bytes
dc.format	1830006 bytes
dc.format	application/octet-stream
dc.format	application/pdf
dc.language	en_US
dc.relation	AITR-1410
dc.subject	computer vision
dc.subject	object recognition
dc.subject	error models
dc.subject	salignment
dc.subject	weak perspective
dc.subject	pose estimation
dc.title	Robust and Efficient 3D Recognition by Alignment

Files in this item

Files	Size	Format	View
There are no files associated with this item.