Download Full Text (6.0 MB)
Nowadays, the widespread use of computer vision algorithms in surveillance systems and autonomous robots has increased the demand for video enhancement algorithms. Bad weather conditions like rain affect the feature extraction process in videos and thus affect other post-processing operations. In this paper, we propose an algorithm based on phase congruency features to detect and remove rain and thus improve the quality of video. We make use of the following characteristics of rain streaks in video in order to detect them: (1) rain streaks do not occlude the scene at all instances, (2) all the rain streaks in a frame are oriented in a single direction, and (3) presence of rain streak at a particular pixel causes a positive change in intensity. Combining all these properties we are able to detect rain streaks in a particular frame using phase congruency features. The pixels in a frame which are identified as rain streaks are then replaced using the pixel information of its spatial and temporal neighbors which are not affected by rain. When this method is used in conjunction with phase correlation, we are able to remove rain of medium density from videos even when complex camera movement is involved. By making the selection of candidate rain pixels in an adaptive manner, we were able to remove rain when moving objects are present in the scene. However, the movement is causing some noise along the edges in the resultant videos. We are in the process of devising a method to remove that noise. By excluding the directional property of rain streaks and including some constraints related to intensity, we were able to adapt the algorithm to removing snow from videos as well. However, the results are noisy and research is in progress to make the algorithm more effective in such scenarios.
Vijayan K. Asari
Primary Advisor's Department
Electrical and Computer Engineering
Stander Symposium poster
"Phase Space Analysis to Detect and Remove Rain from Video" (2012). Stander Symposium Posters. 145.