A HIDDEN MARKOV MODEL FRAMEWORK FOR TRAFFIC EVENT DETECTION USING VIDEO FEATURES (WA-P7)

Author(s) : Xiaokun Li (University of Cincinnati, USA) Fatih M. Porikli (Misubishi Electric Research Labs, USA)

Abstract : A novel approach for highway traffic event detection in video is presented. The proposed algorithm extracts event features directly from compressed video and detects traffic event via Gaussian Mixture Hidden Markov Model (GMHMM). Firstly invariant feature vector is extracted from Discrete Cosine Transform (DCT) domain after video parse. The feature vector accurately describes the change of traffic state and is robust to different video sources (highways), and illumination situations, such as sunny, cloud, and dark. This success leads to the development of an accurate event modeling and detection strategy which is based on GMHMM. The proposed algorithm is efficient both in terms of computational and space criteria. Six traffic patterns are defined in our testing system. The experimental results show the system has a high detection rate and the model-based system can be easily extended for detecting more traffic events.

Menu