Suspicious event recognition using infrared imagery

The society's concern about safety is growing every day and with it the demand for intelligent surveillance systems with the minimal human intervention possible. In this work we identify suspicious events that could take place in a parking lot based on infrared imagery. The object segmentation process is performed using a dynamic background-subtraction technique which robustly adapts detection to illumination changes. Segmented objects are tracked by a two phase function: prediction and correction. During the tracking process the objects are classified into two categories: Person and Vehicles, based on features like size, velocity and temperature. With the objects correctly segmented and classified using features like velocity and time stood in one spot, it is possible to identify suspicious events occurring in the monitored area. Experimental results are presented to demonstrate the effectiveness of the proposed technique to recognize suspicious events.