Video Behaviour Profiling for Anomaly Detection

This paper aims to address the problem of modelling video behaviour captured in surveillance videos for the applications of online normal behaviour recognition and anomaly detection. A novel framework is developed for automatic behaviour profiling and online anomaly sampling/detection without any manual labelling of the training dataset. The framework consists of the following key components: (1) A compact and effective behaviour representation method is developed based on discrete scene event detection. The similarity between behaviour patterns are measured based on modelling each pattern using a Dynamic Bayesian Network (DBN). (2) Natural grouping of behaviour patterns is discovered through a novel spectral clustering algorithm with unsupervised model selection and feature selection on the eigenvectors of a normalised affinity matrix. (3) A composite generative behaviour model is constructed which is capable of generalising from a small training set to accommodate variations in unseen normal behaviour patterns. (4) A run-time accumulative anomaly measure is introduced to detect abnormal behaviour while normal behaviour patterns are recognised when sufficient visual evidence has become available based on an online Likelihood Ratio Test (LRT) method. This ensures robust and reliable anomaly detection and normal behaviour recognition at the shortest possible time. The effectiveness and robustness of our approach is demonstrated through experiments using noisy and sparse datasets collected from both indoor and outdoor surveillance scenarios. In particular, it is shown that a behaviour model trained using an unlabelled dataset is superior to those trained using the same but labelled dataset in detecting anomaly from an unseen video. The experiments also suggest that our online LRT based behaviour recognition approach is advantageous over the commonly used Maximum Likelihood (ML) method in differentiating ambiguities among different behaviour classes observed online.