Efficient template generation for object classification in video surveillance

R.G.J. Wijnhoven, P.H.N. With, de, I.M. Creusen

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Samenvatting

For object classification in video surveillance, features extracted from images are compared with a visual dictionary. The best-matching features are learned by the classifier to determine the object class. In this paper, the visual dictionary concept is extended with Interest Point Operators (IPOs). In a first experiment, the influence of using IPOs on the visual dictionary creation process is measured and optimized. Secondly, given this optimal dictionary, the computational efficiency is evaluated for the dictionary matching process. Experiments show that the creation of the dictionary is most effective when extracting features at random locations. For the dictionary matching step, the use of IPOs gives a massive improvement (factor 8) in computational efficiency, while retaining a close-to-optimal classification result.
Originele taal-2Engels
TitelProceedings of the 29th symposium on Information theory in the Benelux, May 29-30. 2008, Leuven, Belium
RedacteurenL. Van der Perre, A. Dejonghe, V. Ramon
Plaats van productieLeuven
UitgeverijIMEC
Pagina's255-262
StatusGepubliceerd - 2008

Vingerafdruk Duik in de onderzoeksthema's van 'Efficient template generation for object classification in video surveillance'. Samen vormen ze een unieke vingerafdruk.

Citeer dit