You are here

Statistical Analysis in Complex Visual Scenes

Along with the deployment of video surveillance in public spaces, there is a increasing demand of automatic analysis tools able to extract typical and anomalous patterns in complex scenes. We have developed and field-tested traffic analysis tools for monitoring road intersections and queues. We also study statistical methods for analyzing complex visual scenes involving people and their activities.

Selected publications:

D. Xu, E. Ricci, Y. Yan, J. Song, N. Sebe: Learning Deep Representations of Appearance and Motion for Anomalous Event Detection. British Machine Vision Conference (BMVC), 7 – 10 September 2015, Swansea, UK (oral)

E. Ricci, G. Zen, N. Sebe, S. Messelodi: A Prototype Learning Framework using EMD: Application to Complex Scenes Analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 35, N. 3, pp. 513-526, 2013

S. Messelodi, C.M. Modena and M. Zanin: A computer vision system for the detection and classification of vehicles at urban road intersections. Pattern Analysis and Applications, Vol. 8, No. 1-2, pp. 17-31

S. Messelodi, C.M. Modena: A Computer Vision System for Traffic Accident Risk Measurement. A Case Study. Advances in Transportation Studies, Vol. 7, pp. 51-66

E. Ricci, F. Tobia, G. Zen: Learning Pedestrian Trajectories with Kernels. International Conference on Pattern Recognition - ICPR 2010, Istanbul, Turkey, August 23-26, 2010, pp. 149-152

Research topics: