Pedestrian Tracking in the Compressed Domain Using Thermal Images

The video surveillance of sensitive facilities or borders poses many challenges like the high bandwidth requirements and the high computational cost. In this paper, we propose a framework for detecting and tracking pedestrians in the compressed domain using thermal images. Firstly, the detection process uses a conjunction between saliency maps and contrast enhancement techniques followed by a global image content descriptor based on Discrete Chebychev Moments (DCM) and a linear Support Vector Machine (SVM) as a classifier. Secondly, the tracking process exploits raw H.264 compressed video streams with limited computational overhead. In addition to two, well-known, public datasets, we have generated our own dataset by carrying six different scenarios of suspicious events using a thermal camera. The obtained results show the effectiveness and the low computational requirements of the proposed framework which make it suitable for real-time applications and on-board implementation.