Rotating adaptive Haar wavelet transform for human tracking in thermal omnidirectional vision

Abstract

In this paper, a novel surveillance system, thermal omnidirectional vision system, is introduced which is robust to illumination and has a global field of view. According to the characteristic of the proposed system, a rotating adaptive Haar wavelet transform is developed for human tracking in thermal omnidirectional vision. The proposed feature can effectively handle the nonisotropic distortion of catadioptric omnidirectional vision (COV). For robust tracking, we develop a rotational kinematic model based adaptive particle filter, which can handle various movements including rapid movement. Since the involvement of the rotational kinematic model, the proposed tracking algorithm can well deal with the short term occlusion. Finally, a series of experiments verify the effectiveness of the proposed rotating adaptive Haar wavelet transform and the rotational kinematic model based adaptive particle filter for human tracking in thermal omnidirectional vision.