The Early Detection of Motion Boundaries

Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/6814

Full metadata record

DC Field	Value	Language
dc.creator	Spoerri, Anselm	-
dc.date	2004-10-20T19:57:55Z	-
dc.date	2004-10-20T19:57:55Z	-
dc.date	1990-05-01	-
dc.date.accessioned	2013-10-09T02:47:02Z	-
dc.date.available	2013-10-09T02:47:02Z	-
dc.date.issued	2013-10-09	-
dc.identifier	AITR-1275	-
dc.identifier	http://hdl.handle.net/1721.1/6814	-
dc.identifier.uri	http://koha.mediu.edu.my:8181/xmlui/handle/1721	-
dc.description	This thesis shows how to detect boundaries on the basis of motion information alone. The detection is performed in two stages: (i) the local estimation of motion discontinuities and of the visual flowsfield; (ii) the extraction of complete boundaries belonging to differently moving objects. For the first stage, three new methods are presented: the "Bimodality Tests,'' the "Bi-distribution Test,'' and the "Dynamic Occlusion Method.'' The second stage consists of applying the "Structural Saliency Method,'' by Sha'ashua and Ullman to extract complete and unique boundaries from the output of the first stage. The developed methods can successfully segment complex motion sequences.	-
dc.format	98 p.	-
dc.format	6011802 bytes	-
dc.format	4691342 bytes	-
dc.format	application/postscript	-
dc.format	application/pdf	-
dc.language	en_US	-
dc.relation	AITR-1275	-
dc.subject	visual motion	-
dc.subject	motion	-
dc.subject	motion boundaries	-
dc.subject	discont	-
dc.subject	motionsdiscontinuities	-
dc.subject	boundary detection	-
dc.title	The Early Detection of Motion Boundaries	-
Appears in Collections:	MIT Items

Files in This Item:

There are no files associated with this item.

DSpace JSPUI