Abstract | ||
---|---|---|
Motion deblurring is a challenging problem in computer vision. Most previous blind deblurring approaches usually assume that the Point Spread Function (PSF) is spatially invariant. However, non-uniform motions exist ubiquitously and cannot be handled successfully. In this paper, we present an automatic method for object motion deblurring based on non-uniform motion information from video. First, the feature points of the object are tracked throughout a video sequence. Then, the object motion between frames is estimated and the circular blurring paths (i.e. PSFs) of each point are computed along the linear moving path in polar coordinates. Finally, an alpha matte of the blurred object is extracted to separate the foreground from the background, and an iterative Richardson-Lucy algorithm is carried out on the foreground using the obtained blurring paths. Experimental results show our proposed approach outperforms the state-of-the-art motion deblurring algorithms. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1016/j.neucom.2012.01.017 | Neurocomputing |
Keywords | Field | DocType |
blur estimation,alpha matte,video-based non-uniform object motion,previous blind deblurring,non-uniform motion,non-uniform motion information,automatic method,object motion,motion deblurring,point spread function,video sequence,state-of-the-art motion,deconvolution | Computer vision,Deblurring,Pattern recognition,Motion blur,Deconvolution,Polar coordinate system,Artificial intelligence,Invariant (mathematics),Motion estimation,Point spread function,Mathematics | Journal |
Volume | ISSN | Citations |
86, | 0925-2312 | 7 |
PageRank | References | Authors |
0.41 | 25 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaoyu Deng | 1 | 31 | 3.74 |
Yan Shen | 2 | 7 | 0.41 |
Mingli Song | 3 | 1646 | 98.10 |
Dacheng Tao | 4 | 19032 | 747.78 |
Jiajun Bu | 5 | 4106 | 211.52 |
Chun Chen | 6 | 4727 | 246.28 |