TY - GEN
T1 - Efficient single image dehazing via scene-adaptive segmentation and improved dark channel model
AU - Zhang, He
AU - Liu, Xin
AU - CHEUNG, Yiu Ming
N1 - Funding Information:
The work was supported by the National Science Foundation of China under Grants 61272366, 61300138, the Promotion Program for Young and Middle-aged Teacher in Science and Technology Research (No. ZQN-PY309) of Huaqiao University, and also partially supported by the supported by Faculty Research Grant of HKBU with the project code: No.FRG2/14-15/075, FRG1/14-15/041 and FRG2/15-16/049.
PY - 2016/10/31
Y1 - 2016/10/31
N2 - In this paper, we present an efficient single image dehazing approach via scene-adaptive segmentation and improved dark channel model. First, we detect the image depth information and segment the raw image into the close view and distant view. Then, we utilize the minimum channel image of distant view to regularize the atmospheric veil and simultaneously estimate its light value of close view within the haze-opaque area, through which the whole transmission map can be well optimized. Finally, the haze degraded image can be well restored via the atmosphere scattering model. The experimental results have shown that the proposed single image dehazing approach has significantly increased the perceptual visibility of the scene and achieved a better color fidelity visually.
AB - In this paper, we present an efficient single image dehazing approach via scene-adaptive segmentation and improved dark channel model. First, we detect the image depth information and segment the raw image into the close view and distant view. Then, we utilize the minimum channel image of distant view to regularize the atmospheric veil and simultaneously estimate its light value of close view within the haze-opaque area, through which the whole transmission map can be well optimized. Finally, the haze degraded image can be well restored via the atmosphere scattering model. The experimental results have shown that the proposed single image dehazing approach has significantly increased the perceptual visibility of the scene and achieved a better color fidelity visually.
UR - http://www.scopus.com/inward/record.url?scp=85007179608&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2016.7727640
DO - 10.1109/IJCNN.2016.7727640
M3 - Conference proceeding
AN - SCOPUS:85007179608
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 3440
EP - 3445
BT - 2016 International Joint Conference on Neural Networks, IJCNN 2016
PB - IEEE
T2 - 2016 International Joint Conference on Neural Networks, IJCNN 2016
Y2 - 24 July 2016 through 29 July 2016
ER -