Reconnaissance d’événements vidéos par l’analyse de trajectoires à l’aide de modèles de Markov
Alexandre Hervieu, Patrick Bouthémy, Jean–Pierre Le Cadre · DSpace (Centre National De La Recherche Scientifique) · 2009
We address the problem of dynamic event recognition in videos. This is motivated by increasing needs for contentbased exploitation of video footage, as encouraged in numerous applications, e.g., retrieving video sequences in large TV archives, creating automatic video summarization of sport TV programs, or detecting specific actions or activities in video-surveillance. It implies to tackle the well-known semantic gap between computed low-level features and high-level concepts. Considering 2D trajectories is attractive since they form computable image features which capture elaborated spatio-temporal information on the viewed actions. Methods for tracking moving objects in an image sequence are now available to get reliable enough 2D trajectories in various situations. These trajectories are given as a set of consecutive positions (x, y) in the image plane over time. If they are embedded in an appropriate modeling framework, high-level information on the dynamic scene can then be reachable. We aim at designing a general trajectory classification method that does not exploit strong a priori information on the scene structure, the camera set-up, the 3D object motions, while taking into account both the trajectory shape (geometrical information related to the type of motion and to variations in the motion direction) and the speed changes of the moving object on its trajectory (dynamics-related information). Appropriate local differential features combining curvature and motion magnitude are defined and robustly computed on the motion trajectories....