A Statistical Video Content Recognition Method Using Invariant Features on Object Trajectories

Abstract--This work is dedicated to a statistical trajectorybased approach addressing two issues related to dynamic video content understanding: recognition of events and detection of unexpected events. Appropriate local differential features combining curvature and motion magnitude are defined and robustly computed on the motion trajectories in the image sequence. These features are invariant to image translation, inthe-plane rotation and spatial scaling. The temporal causality of the features is then captured by Hidden Markov Models dedicated to trajectory description, whose states are properly quantized values. The similarity between trajectories is expressed by exploiting this quantization-based HMM framework. Moreover statistical techniques have been developed for parameter estimations. Evaluations of the method have been conducted on several data sets including real trajectories obtained from sport videos, especially Formula One and ski TV program. The novel method compares favor...

• Type: Journal
• Year: 2008
• Where: TCSV
• Authors: Alexandre Hervieu, Patrick Bouthemy, Jean-Pierre Le Cadre
• Keywords: Dynamic Video Content, Hidden Markov Models, Statistical Trajectorybased Approach, TCSV 2008