FPGA-based Anomalous trajectory detection using SOFM

A system for automatically classifying the trajectory of a moving object in a scene as usual or suspicious is presented. The system uses an unsupervised neural network (Self Organising Feature Map) fully implemented on a reconfigurable hardware architecture (Field Programmable Gate Array) to cluster trajectories acquired over a period, in order to detect novel ones. First order motion information, including first order moving average smoothing, is generated from the 2D image coordinates (trajectories). The classification is dynamic and achieved in real-time. The dynamic classifier is achieved using a SOFM and a probabilistic model. Experimental results show less than 15\% classification error, showing the robustness of our approach over others in literature and the speed-up over the use of conventional microprocessor as compared to the use of an off-the-shelf FPGA prototyping board