ashok321
ELITE MEMBER
- Joined
- Nov 1, 2010
- Messages
- 17,942
- Reaction score
- 4
- Country
- Location
NEW DELHI: An algorithm developed by IIT Kharagpur promises to cut delays and cancellations of flights and trains by clearing hazy visuals caused by rain, fog or smog in real time.
The Railways and Defence Research and Development Organisation (DRDO) have already initiated talks for acquiring this technology from the Institute, which has named it ‘Real Time Fog Removal from Videos & Real-Time Rain Removal from Videos’.
“We are in touch with DRDO and they are interested in using this technology during rocket launches and missile test fires done by Integrated Test Range (ITR),” said Sudipta Mukhopadhyay of the department of electronics and electrical communication under whose leadership the algorithm has been developed.
“During such events, scientists need to track the trajectory through cameras mounted in ground stations, but the video often gets degraded due to weather conditions.” The technology has already received international patent and the Institute is also in talks with the railways for deploying it, he said.
So how does it work? The fog algorithm estimates the distance of objects from the camera in the form of a depth map. The depth map is further refined using anisotropic diffusion to smooth depth map and identify clear boundaries of the object. Based on the refined depth, the image is restored to give clean images.
“This operation is performed on every frame of the video to generate a defogged video stream in real time,” Mukhopadhyay said.
Source>>
The Railways and Defence Research and Development Organisation (DRDO) have already initiated talks for acquiring this technology from the Institute, which has named it ‘Real Time Fog Removal from Videos & Real-Time Rain Removal from Videos’.
“We are in touch with DRDO and they are interested in using this technology during rocket launches and missile test fires done by Integrated Test Range (ITR),” said Sudipta Mukhopadhyay of the department of electronics and electrical communication under whose leadership the algorithm has been developed.
“During such events, scientists need to track the trajectory through cameras mounted in ground stations, but the video often gets degraded due to weather conditions.” The technology has already received international patent and the Institute is also in talks with the railways for deploying it, he said.
So how does it work? The fog algorithm estimates the distance of objects from the camera in the form of a depth map. The depth map is further refined using anisotropic diffusion to smooth depth map and identify clear boundaries of the object. Based on the refined depth, the image is restored to give clean images.
“This operation is performed on every frame of the video to generate a defogged video stream in real time,” Mukhopadhyay said.
Source>>
