Xiao, J., Yang, C., Han, F., Cheng, H. (2008). Vehicle and Person Tracking in Aerial Videos. In: Stiefelhagen, R., Bowers, R., Fiscus, J. (eds) Multimodal Technologies for Perception of Humans. RT CLEAR 2007 2007. Lecture Notes in Computer Science, vol 4625. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-68585-2_18
This paper presents two tracking approaches from Sarnoff Corporation to detect moving vehicles and person in the videos taken from aerial platform or plane. In the first approach, we combine layer segmentation approach with background stabilization and post track refinement to reliably detect small moving objects at the relatively low processing speed. Our second approach employ a fast tracking algorithm that has been optimized for real-time application. To classify vehicle and person from the detected objects, a HOG (Hierarchy Of Gradient) based vehicle v.s. person classifier is designed and integrated with the tracking post-processing. Finally, we report the results of our algorithms on a large scale data set collected from VIVID program and the scores evaluated by NIST CLEAR program.