CONTEXTUAL PERSON DETECTION IN MULTI-MODAL OUTDOOR SURVEILLANCE

In this paper we present a new approach to person detection in outdoor surveillance tasks. A multi-modal segmentation (RGB, Polarimetric, thermal sensors) of the world into re-gions sky, road, bush, trees, grass etc. is used to learn the normal spatial context of people appearing in normal training data. The context feature is a novel application of the work of Wolf et al. [1] which enables the probability of a person ap-pearing in a certain location to be computed. By using motion as a precursor to the deployment of a HOG person detector in conjunction with the spatial context likelihood we obtain significant improvement in person detection for challenging scenes. Comprehensive ROC analysis on 4 outdoor scenes is reported for normal activity detection. Anomaly detection is then achieved using learned context and we show that 72 % of true positive anomalies are found for a false positive rate of 0.19 % over all data in thermal and visual band data. Index Terms — Surveillance, Sensor fusion, person de-tection