Restoration for High-overlapped Image Sequence with Composite Motion Blurs

Abstract

Motion blur is a common degradation which usually brings difficulties to subsequent image process and analysis of a machine vision system. In this paper, an effective restoration scheme is proposed for high-overlapped image sequence with composite motion blurs which refer to the blurs caused during the exposure time by dual relative motions among the background of the scene, the moving objects and the scanning camera, resulting in additional local blurs in the global motion blurred image. Taking full advantages of high-overlapping ratios between neighboring frames, the global motion is estimated first to differentiate the local motion blurred region from the global blurred background. The local motion is then estimated from the extracted local motion blurred region. And the space-variant Point Spread Functions (PSFs) are calculated respectively based on different motion estimation results as the initiations for the Richardson-Lucy-based sectional restorations. A series of experiments and comparisons are carried out to testify the validity of the proposed method. The restoration results show that the proposed method can enhance the image quality effectively. 