Knowledge-Based Supervised Learning Methods in a Classical Problem of Video Object Tracking

Lionel Carminati , Jenny Benois-Pineau (1) , Christian Jennewein

1 LaBRI - Laboratoire Bordelais de Recherche en Informatique

In this paper we present a new scheme for detection and tracking of specific objects in a knowledge-based framework. The scheme uses a supervised learning method: support vector machines. Both problems, detection and tracking, are solved by a common approach: objects are located in video sequences by a SVM classifier. They are next tracked along the time by a SVM tracker with complete 6 parameters affine model. The method is applied in a video surveillance application for detection and tracking of frontal view faces. Real time application constraints are met by reduction of support vector set.

Mots clés: Supervised learning; Support vector machines; Face detection; Support vector machine classification; Object detection; Video surveillance; Training data; Testing; Polynomials; Kernel

Domaines: Multimédia [cs.MM]; Informatique [cs]; Sciences de l'ingénieur [physics]

Lionel Carminati, Jenny Benois-Pineau, Christian Jennewein. Knowledge-Based Supervised Learning Methods in a Classical Problem of Video Object Tracking. 2006 13th IEEE International Conference on Image Processing (ICIP 2006), Oct 2006, Atlanta, GA, United States. pp.2385-2388, ⟨10.1109/ICIP.2006.312942⟩. ⟨hal-01438952⟩