Rain Removal From Video
"Pool" Input Video Temporal Method Spatio-temporal method
"Magnolia" Input Video Temporal Method Spatio-temporal method
"Street1" Input Video Temporal Method Spatio-temporal method
Project Description:
Current vision systems are designed to perform in normal weather conditions. However, no one can escape from bad weather conditions. Bad weather reduces scene contrast and visibility, which results in a degradation in the performance of various computer vision algorithms such as object tracking, segmentation, and recognition. Rain causes spatial and temporal intensity fluctuations in images or video frames. These intensity fluctuations are due to the random distribution and high velocities of the raindrops.
Temporal and Spatio-temporal properties of rain pixel are analyzed and using these properties, two rain removal algorithms for the videos captured by the static camera are developed.
Rain affects only the intensity plane of the image. Thus, restoration is needed only for this component.
Highlights:
Chunauti 3.0 from STPI in 2022
National Award for Technology Start-Ups sponsored by Technology Development Board, DST in 2021
Our start-up named ProficientVision Solutions Private Limited received CII Statrtupreneur Award, 2019 in manufacturing.
Awarded 'Abdul Kalam Technology Innovation National Fellowship' from 1st April 2018 for three years which may be extended up to 5 years.
Our research "On glass visualization in real time: Rain removal from videos" received a position among top nine innovations in "University Challenge of IIGP2.0 2017"
Our research work "Real time Fog Removal from Video and Rain Removal from Video" received FICCI R&D Awards 2017 under GLOBAL R&D SUMMIT 2017 on April 6-7, 2017 at The Lalit Ashok, Kumara Krupa High Grounds, Bengaluru, India.
Patents:
Bijaylaxmi Das, Sudipta Mukhopadhyay,, Single image-based rain affected image de-raining method and apparatus, Patent filing no. No. 202331048997 dated 20-07-2023
A. K. Tripathi and S. Mukhopadhyay, "Method and apparatus for detection and removal of rain from video using temporal and spatiotemporal properties", Patent application No: 1284/KOL/2010 dated 15-11- 2010.
Publications:
B. Das, A. Saha, and S. Mukhopadhyay, "Rain removal from a single image using refined inception resnet v2," Circuits, Systems, and Signal Processing (Springer), pp. 1-24, 2023. https://doi.org/10.1007/s00034-022-02279-x
B. Das, S. Mukhopadhyay, "Single image rain removal using cWGAN network," 2022 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Sydney, Australia, 2022, pp. 1-7, doi: 10.1109/DICTA56598.2022.10034600.
3. A. K. Tripathi, S. Mukhopadhyay, "Removal of rain from videos: a review", Signal Image and Video Processing, vol. 8, no. 8, pp. 1421-1430, November 2014.
4. A. K. Tripathi, S. Mukhopadhyay, “Meteorological approach for detection and removal of rain from videos”, IET Computer Vision 2013, 7, 36–47.
5. A. K. Tripathi and S. Mukhopadhyay, “Video Post Processing: Low Latency Spatiotemporal Approach for Detection and Removal of Rain", IET Image processing, Vol. 6, No. 2, pp. 181-196, 2012.
6. A. K. Tripathi and S. Mukhopadhyay, “A probabilistic approach for detection and removal of rain from videos", IETE journal of research, Vol. 57, No. 1, pp. 82-91, 2011.