Recognizing Events in an Automated Surveillance System
Event recognition is probably the ultimate purpose of an automated surveillance system. In this paper, hidden Markov models (HMM) are utilized to recognize the nature of an event occurring in a scene. For this purpose, object trajectories, which are obtained through a successful track, are obtained as a sequence of flow vectors that contain instantaneous velocity and location information. These vectors are clustered by K-means algorithm to obtain a prototype representation. HMMs are trained with sequences obtained from usual motion patterns and abnormality is detected by measuring distances to these models. In order to specify the number of models automatically, a novel approach is proposed which utilizes the clues provided by centroid clustering. Preliminary experimental results are promising for detecting abnormal events.
KeywordsHide Markov Model Flow Vector Event Recognition Abnormal Event Prototype Representation
Unable to display preview. Download preview PDF.
- 1.Orten, B., Soysal, M., Alatan, A.A.: Person Identification in Surveillance Video by Combining MPEG-7 Experts. In: WIAMIS 2005, Montreux (2005)Google Scholar
- 2.Orten, B.: Moving Object Identification and Event Recognition in Video Surveillance Systems. MSc. Thesis (July 2005)Google Scholar
- 3.Oliver, N., Rosario, B., Pentland, A.: A Bayesian Computer Vision System for Modeling Human Interactions. In: Int’l. Conf. on Vision Systems. Springer, Spain (1999)Google Scholar
- 4.Lee, K.K., Yu, M., Xu, Y.: Modeling of human walking trajectories for surveillance. Intelligent Robots and Systems 2, 1554–1559 (2003)Google Scholar
- 5.Starner, T., Pentland, A.: Visual recognition of American sign language using hidden Markov models. In: Proc. Intern. Workshop Automatic Face and Gesture Recognition (1995)Google Scholar
- 6.Kettnaker: Time dependent HMMs for visual intrusion detection. In: IEEE Workshop on Detection and Recognizing Events in Video (2003)Google Scholar