REMOVING RAIN TRACKS FROM IMAGES USING IMAGE PROCESSING ALGORITHMS
Keywords:
Dynamic Image, Threshold Filters, Gaussian Mixture Model (GMM), Rain Line Removal, Image Processing, VideoAbstract
This article discusses the problem of removing rain tracks from video. Although it is important to remove rain tracks from the image, there is not much research in this area and there are no reliable real-time algorithms. Difficulties in the rain trail removal algorithm are caused by the difficulty of seeing, low light, and the presence of a moving camera and objects. The problem facing the rain line restoration algorithm is to identify the rain lines and replace them with their original values for image processing. In this paper, we discuss the use of photometric and chromatic features for rain detection. An updated Gaussian mixture model (updated GMM) detected moving objects. This rain streak removal algorithm is used to detect rain streaks in videos and replace them with calculated values equal to the original value. Spatial and temporal features are used to replace rain lines with their original values.
References
Beknazarova SS, Bekmirzayeva M.Sh. (2023). Study of the effect of fog on images in visualization systems. International journal of theoretical and practical issues of digital technologies. B. 53-57.
M.Sh. Bekmirzayeva "Preliminary methods of image processing." JOURNAL OF INDISCIPLINARY INNOVATIONS AND SCIENTIFIC RESEARCH IN UZBEKISTAN 2.13 (2022): 760-764.
Astha Modak, Samruddhi Paradkar, Shruti Manwatkar, Amol R. Madane, Ashwini M. Deshpande, “Human Head Pose and Eye State Based Driver Distraction Monitoring System”, 3rd Computer Vision and Image Processing (CVIP) 2018, Indian Institute of Information Technology, Design and Manufacturing, Jabalpur (IIITDMJ), India.
C. Stauffer, WEL Grimson, "Adaptive background mixture models for real-time tracking", Computer Vision and Pattern Recognition IEEE Computer SocioentyfeCrence , vol. 2, pp. 252-259, 23-25 June 1999
Kshitiz Garg and SK Nayar, "Vision and rain", International Journal on Computer Vision, vol. 75, no. 1, pp. 3–27, 2007.