This paper addresses the problem of classifying actions performed by a human subject in a video sequence. A representation eigenspace approach based on the visual appearance is used to train the classifier. Before dimensionality reduction exploiting the PCA/LLE algorithms, a high dimensional description of each frame of the video sequence is constructed, based on foreground blob analysis. The classification task is performed by matching incrementally the reduced representation of the test image sequence against each of the learned ones, and accumulating matching scores until a decision is obtained; to this aim, two different metrics are introduced and evaluated. Experimental results demonstrate that the approach is accurate enough and feasible for behavior classification. Furthermore, we argue that the choice of both the feature descriptor and the metric for the matching score can dramatically influence the performance of the results.
Behavior monitoring through automatic analysis of video sequences / C. Colombo; D. Comanducci; A. Del Bimbo. - ELETTRONICO. - (2007), pp. 1-6. (Intervento presentato al convegno ACM International Conference on Image and Video Retrieval CIVR 2007 tenutosi a Amsterdam, The Netherlands nel July 2007).
Behavior monitoring through automatic analysis of video sequences
COLOMBO, CARLO;COMANDUCCI, DARIO;DEL BIMBO, ALBERTO
2007
Abstract
This paper addresses the problem of classifying actions performed by a human subject in a video sequence. A representation eigenspace approach based on the visual appearance is used to train the classifier. Before dimensionality reduction exploiting the PCA/LLE algorithms, a high dimensional description of each frame of the video sequence is constructed, based on foreground blob analysis. The classification task is performed by matching incrementally the reduced representation of the test image sequence against each of the learned ones, and accumulating matching scores until a decision is obtained; to this aim, two different metrics are introduced and evaluated. Experimental results demonstrate that the approach is accurate enough and feasible for behavior classification. Furthermore, we argue that the choice of both the feature descriptor and the metric for the matching score can dramatically influence the performance of the results.File | Dimensione | Formato | |
---|---|---|---|
civr07.pdf
Accesso chiuso
Tipologia:
Pdf editoriale (Version of record)
Licenza:
Tutti i diritti riservati
Dimensione
318.8 kB
Formato
Adobe PDF
|
318.8 kB | Adobe PDF | Richiedi una copia |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.