Dust and Reflection Removal from Videos Captured in Moving Car

The quality of videos captured in moving cars suffer from dust on the wind screen glass. Dust contaminates the captured videos and makes the videos blurred. Removing dust and restoring high quality dust-free and reflection-free video is a challenging task in the field of video stream processing. In this work, we present a pipeline of dust and reflection removal from the corrupted video streams. To the best of our knowledge, this paper is the first study how to effectively remove dust from video streams captured in a moving car. The pipeline is comprises of two steps. In the first step, it uses the state of the art image matting to model and resolve the captured frames as the merging result of a dust layer, a background layer and a matte layer. To refine the result, the second step employs variances of pixel streams to constrain the matte layer and optimizes the extracted dust layer, background layer and matte layer to make them spatially and temporally consistent in the streams. The test results demonstrate that our proposed method can effectively remove the dust and reflections in the video streams captured in moving cars.

[1]  Shree K. Nayar,et al.  Removing image artifacts due to dirty camera lenses and thin occluders , 2009, ACM Trans. Graph..

[2]  William T. Freeman,et al.  A computational approach for obstruction-free photography , 2015, ACM Trans. Graph..

[3]  Edward H. Adelson,et al.  Separating reflections and lighting using independent components analysis , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[4]  Yoav Y. Schechner,et al.  Blind recovery of transparent and semireflected scenes , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[5]  Stephen Lin,et al.  Removal of Image Artifacts Due to Sensor Dust , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Y. Weiss,et al.  Separating reflections from a single image using local features , 2004, CVPR 2004.

[7]  Frédo Durand,et al.  Reflection removal using ghosting cues , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Takeo Kanade,et al.  Analysis of Rain and Snow in Frequency Space , 2008, International Journal of Computer Vision.

[9]  Anat Levin,et al.  User Assisted Separation of Reflections from a Single Image Using a Sparsity Prior , 2004, ECCV.

[10]  Ramesh Raskar,et al.  Removing photography artifacts using gradient projection and flash-exposure sampling , 2005, SIGGRAPH 2005.

[11]  Yu-Wing Tai,et al.  A Physically-Based Approach to Reflection Separation: From Physical Modeling to Constrained Optimization , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Michael S. Brown,et al.  Single Image Layer Separation Using Relative Smoothness , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Michael S. Brown,et al.  Exploiting Reflection Change for Automatic Reflection Removal , 2013, 2013 IEEE International Conference on Computer Vision.

[14]  Changshui Zhang,et al.  Blindly separating mixtures of multiple layers with spatial shifts , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.