File Download
Supplementary

Conference Paper: Neurally inspired object tracking system

TitleNeurally inspired object tracking system
Authors
Issue Date2004
Citation
The Brain Inspired Cognitive Systems (BICS 2004), Stirling, Scotland, U.K., 29 August-1 September 2004. In Proceedings of the Brain Inspired Cognitive Systems, 2004, p. 1-7 How to Cite?
AbstractObject tracking is useful in applications like computer-aided medical diagnosis, video editing, visual surveillance etc. Commonly used approaches usually involve the use of filter (e.g. Kalman filter) to predict the location of the object in next image frame. Such approaches actually borrow ideas from signal theory and are limited to applications where dynamic model is known. In this paper, a flexible and reliable estimation algorithm using wavelet network (or wavenet) is proposed to build an object tracking system. This system simulates the perception of motion that occurs in primates. Neural-based filters will be used for color, shape and motion analysis. Experimental results show that object can be tracked accurately without fixing any dynamic model compare with commonly used Kalman filter.
DescriptionBIS3-3
Persistent Identifierhttp://hdl.handle.net/10722/137135

 

DC FieldValueLanguage
dc.contributor.authorWong, SF-
dc.contributor.authorWong, KKY-
dc.date.accessioned2011-08-23T06:54:05Z-
dc.date.available2011-08-23T06:54:05Z-
dc.date.issued2004-
dc.identifier.citationThe Brain Inspired Cognitive Systems (BICS 2004), Stirling, Scotland, U.K., 29 August-1 September 2004. In Proceedings of the Brain Inspired Cognitive Systems, 2004, p. 1-7-
dc.identifier.urihttp://hdl.handle.net/10722/137135-
dc.descriptionBIS3-3-
dc.description.abstractObject tracking is useful in applications like computer-aided medical diagnosis, video editing, visual surveillance etc. Commonly used approaches usually involve the use of filter (e.g. Kalman filter) to predict the location of the object in next image frame. Such approaches actually borrow ideas from signal theory and are limited to applications where dynamic model is known. In this paper, a flexible and reliable estimation algorithm using wavelet network (or wavenet) is proposed to build an object tracking system. This system simulates the perception of motion that occurs in primates. Neural-based filters will be used for color, shape and motion analysis. Experimental results show that object can be tracked accurately without fixing any dynamic model compare with commonly used Kalman filter.-
dc.languageeng-
dc.relation.ispartofProceedings of the Brain Inspired Cognitive Systems-
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License-
dc.titleNeurally inspired object tracking systemen_US
dc.typeConference_Paperen_US
dc.identifier.emailWong, SF: sfwong@csis.hku.hk-
dc.identifier.emailWong, KKY: kykwong@cs.hku.hk-
dc.description.naturepostprint-
dc.identifier.hkuros96731-
dc.identifier.spage1-
dc.identifier.epage7-
dc.description.otherThe Brain Inspired Cognitive Systems (BICS 2004), Stirling, Scotland, U.K., 29 August-1 September 2004. In Proceedings of the Brain Inspired Cognitive Systems, 2004, p. 1-7-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats