Dynamic scene rain removal for moving cameras

Rain removal is important to ensure the robustness of applications which rely on video input towards rainy conditions. A number of algorithms have thus been proposed to remove the rain effect based on the properties of rain. However, most of these methods are not able to remove rain effectively for scenes taken from moving cameras. We propose a rain removal algorithm which can effectively remove rain from dynamic scenes taken from moving cameras by improving a recent state-of-the-art rain removal method. We do so by first aligning neighboring frames to a target frame before the target frame is de-rained. Experiments show that our proposed method is able to remove rain effectively for moving camera scenes.

[1]  Sudipta Mukhopadhyay,et al.  Video post processing: low-latency spatiotemporal approach for detection and removal of rain , 2012 .

[2]  Sudipta Mukhopadhyay,et al.  Meteorological approach for detection and removal of rain from videos , 2013, IET Comput. Vis..

[3]  Andrew Zisserman,et al.  MLESAC: A New Robust Estimator with Application to Estimating Image Geometry , 2000, Comput. Vis. Image Underst..

[4]  Jie Chen,et al.  A Rain Pixel Recovery Algorithm for Videos With Highly Dynamic Scenes , 2014, IEEE Transactions on Image Processing.

[5]  Takeo Kanade,et al.  Spatio-Temporal Frequency Analysis for Removing Rain and Snow from Videos , 2007 .

[6]  Hao Li,et al.  Rain Removal in Video by Combining Temporal and Chromatic Properties , 2006, 2006 IEEE International Conference on Multimedia and Expo.

[7]  Li-Wei Kang,et al.  Context-Aware Single Image Rain Removal , 2012, 2012 IEEE International Conference on Multimedia and Expo.

[8]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[9]  Shree K. Nayar,et al.  Detection and removal of rain from videos , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..