Video-based urban expressway traffic measurement and performance monitoring

This paper presents an urban expressway video surveillance and monitoring system for traffic flow measurement and abnormal performance detection. The proposed flow detection module collects traffic flow statistics in real time by leveraging multi-vehicle tracking information. Based on these online statistics, road operating situations can be easily obtained. Using spatiotemporal trajectories, vehicle motion paths are encoded by hidden Markov models. With path division and parameter matching, abnormal performances containing extra low or high speed driving, illegal stopping and turning are detected in real scenes. The traffic surveillance approach is implemented and evaluated on a DM642 DSP-based embedded platform. Experimental results demonstrate that the proposed system is feasible for the detection of vehicle speed, vehicle counts and road efficiency, and it is effective for the monitoring of the aforementioned anomalies with low computational costs.

Human behavior clustering for anomaly detection

This paper aims to address the problem of modeling human behavior patterns captured in surveil- lance videos for the application of online normal behavior recognition and anomaly detection. A novel framework is developed for automatic behavior modeling and online anomaly detection without the need for manual labeling of the training data set. The framework consists of the following key components. 1） A compact and effective behavior representation method is developed based on spatial-temporal interest point detection. 2） The natural grouping of behavior patterns is determined through a novel clustering algorithm, topic hidden Markov model （THMM） built upon the existing hidden Markov model （HMM） and latent Dirichlet allocation （LDA）, which overcomes the current limitations in accuracy, robustness, and computational efficiency. The new model is a four- level hierarchical Bayesian model, in which each video is modeled as a Markov chain of behavior patterns where each behavior pattern is a distribution over some segments of the video. Each of these segments in the video can be modeled as a mixture of actions where each action is a distribution over spatial-temporal words. 3） An online anomaly measure is introduced to detect abnormal behavior, whereas normal behavior is recognized by runtime accumulative visual evidence using the likelihood ratio test （LRT） method. Experimental results demonstrate the effectiveness and robustness of our approach using noisy and sparse data sets collected from a real surveillance scenario.