Long-range surveillance systems are typically used in rural areas for detecting and tracking illegal border crossings, trafficking and drug activity. These systems commonly deploy mast or tower-based surveillance systems equipped with thermal infrared cameras, which have the advantage of providing early warnings and increasing the range of observation. However, these systems are subject to high frequency vibration due to slight wind or wind gusts, which is difficult to correct mechanically. In order to identify the border activity, it is critical for the vision system to robustly detect the objects in the scene, classify the objects and track the detected targets. The performance of these post-processing algorithms is known to suffer if the video is not properly stabilized.
Surveillance systems in rural areas, particularly in thermal band, pose several unique challenges to video stabilization algorithms. First, the scene rarely contains man-made objects. Water surface, trees and forests present very low contrast and ambiguous textures such that stabilization algorithms struggle to consistently and repeatedly extract distinctive corners and features. Second, even if the system captures certain human activities or structural objects in the scene, the video typically lacks sharpness in the background due to the motion blur at the long range. In this research paper, we propose a biologically-inspired, robust and compact video motion stabilization algorithm, which is ideal for rural areas. Our novel algorithm is compared quantitatively with other competing algorithm (SURF) in terms of robustness and performance. Finally, we evaluate the resource usage on FPGA platforms.