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 onboard implementation.
CITATION STYLE
Lahouli, I., Haelterman, R., Chtourou, Z., De Cubber, G., & Attia, R. (2019). Pedestrian tracking in the compressed domain using thermal images. In Communications in Computer and Information Science (Vol. 842, pp. 35–44). Springer Verlag. https://doi.org/10.1007/978-3-030-19816-9_3
Mendeley helps you to discover research relevant for your work.