We present a new approach to recognizing events in videos. We first detect and track moving objects in the scene. Based on the shape and motion properties of these objects, we infer probabilities of primitive events frame-by-frame by using Bayesian networks. Composite events, consisting of multiple primitive events, over extended periods of time are analyzed by using a hidden, semi-Markov finite state model. This results in more reliable event segmentation compared to the use of standard HMMs in noisy video sequences at the cost of some increase in computational complexity. We describe our approach to reducing this complexity. We demonstrate the effectiveness of our algorithm using both real-world and perturbed data.
Large-scale event detection using semi-hidden Markov models
Proceedings Ninth IEEE International Conference on Computer Vision ; 1455-1462 vol.2
2003-01-01
4797265 byte
Conference paper
Electronic Resource
English
Large-Scale Event Detection Using Semi-Hidden Markov Models
British Library Conference Proceedings | 2003
|Online Identification of Hidden Semi-Markov Models
British Library Conference Proceedings | 2003
|Crash Detection System Using Hidden Markov Models
SAE Technical Papers | 2004
|Crash Detection System Using Hidden Markov Models
British Library Conference Proceedings | 2004
|Crash detection system using hidden markov models
Automotive engineering | 2004
|