Advanced driver assistance system (ADAS) can recognize traffic signals, vehicles, pedestrians, and so on all over the vehicle. However, because the ADAS is based on images taken in an outdoor environment, it is susceptible to ambient weather such as fog. So, preprocessing such as de-fog and de-hazing techniques is required to prevent degradation of object recognition performance due to decreased visibility. But, if such a fog removal technique is applied in an environment where there is little or no fog, the visual quality may be deteriorated due to excessive contrast improvement. And in foggy road environments, typical fog removal algorithms suffer from color distortion. In this paper, we propose a temporal filter-based fog detection algorithm to selectively apply de-fogging method only in the presence of fog. We also propose a method to avoid color distortion by detecting the sky region and applying different methods to the sky region and the non-sky region. Experimental results show that in the actual images, the proposed algorithm shows an average of more than 97% fog detection accuracy, and improves subjective image quality of existing de-fogging algorithms. In addition, the proposed algorithm shows very fast computation time of less than 0.1ms per frame.
Kyeongmin JEONG
Inha University
Kwangyeon CHOI
Inha University
Donghwan KIM
Inha University
Byung Cheol SONG
Inha University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Kyeongmin JEONG, Kwangyeon CHOI, Donghwan KIM, Byung Cheol SONG, "Fast Fog Detection for De-Fogging of Road Driving Images" in IEICE TRANSACTIONS on Information,
vol. E101-D, no. 2, pp. 473-480, February 2018, doi: 10.1587/transinf.2017EDP7211.
Abstract: Advanced driver assistance system (ADAS) can recognize traffic signals, vehicles, pedestrians, and so on all over the vehicle. However, because the ADAS is based on images taken in an outdoor environment, it is susceptible to ambient weather such as fog. So, preprocessing such as de-fog and de-hazing techniques is required to prevent degradation of object recognition performance due to decreased visibility. But, if such a fog removal technique is applied in an environment where there is little or no fog, the visual quality may be deteriorated due to excessive contrast improvement. And in foggy road environments, typical fog removal algorithms suffer from color distortion. In this paper, we propose a temporal filter-based fog detection algorithm to selectively apply de-fogging method only in the presence of fog. We also propose a method to avoid color distortion by detecting the sky region and applying different methods to the sky region and the non-sky region. Experimental results show that in the actual images, the proposed algorithm shows an average of more than 97% fog detection accuracy, and improves subjective image quality of existing de-fogging algorithms. In addition, the proposed algorithm shows very fast computation time of less than 0.1ms per frame.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017EDP7211/_p
Copy
@ARTICLE{e101-d_2_473,
author={Kyeongmin JEONG, Kwangyeon CHOI, Donghwan KIM, Byung Cheol SONG, },
journal={IEICE TRANSACTIONS on Information},
title={Fast Fog Detection for De-Fogging of Road Driving Images},
year={2018},
volume={E101-D},
number={2},
pages={473-480},
abstract={Advanced driver assistance system (ADAS) can recognize traffic signals, vehicles, pedestrians, and so on all over the vehicle. However, because the ADAS is based on images taken in an outdoor environment, it is susceptible to ambient weather such as fog. So, preprocessing such as de-fog and de-hazing techniques is required to prevent degradation of object recognition performance due to decreased visibility. But, if such a fog removal technique is applied in an environment where there is little or no fog, the visual quality may be deteriorated due to excessive contrast improvement. And in foggy road environments, typical fog removal algorithms suffer from color distortion. In this paper, we propose a temporal filter-based fog detection algorithm to selectively apply de-fogging method only in the presence of fog. We also propose a method to avoid color distortion by detecting the sky region and applying different methods to the sky region and the non-sky region. Experimental results show that in the actual images, the proposed algorithm shows an average of more than 97% fog detection accuracy, and improves subjective image quality of existing de-fogging algorithms. In addition, the proposed algorithm shows very fast computation time of less than 0.1ms per frame.},
keywords={},
doi={10.1587/transinf.2017EDP7211},
ISSN={1745-1361},
month={February},}
Copy
TY - JOUR
TI - Fast Fog Detection for De-Fogging of Road Driving Images
T2 - IEICE TRANSACTIONS on Information
SP - 473
EP - 480
AU - Kyeongmin JEONG
AU - Kwangyeon CHOI
AU - Donghwan KIM
AU - Byung Cheol SONG
PY - 2018
DO - 10.1587/transinf.2017EDP7211
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E101-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2018
AB - Advanced driver assistance system (ADAS) can recognize traffic signals, vehicles, pedestrians, and so on all over the vehicle. However, because the ADAS is based on images taken in an outdoor environment, it is susceptible to ambient weather such as fog. So, preprocessing such as de-fog and de-hazing techniques is required to prevent degradation of object recognition performance due to decreased visibility. But, if such a fog removal technique is applied in an environment where there is little or no fog, the visual quality may be deteriorated due to excessive contrast improvement. And in foggy road environments, typical fog removal algorithms suffer from color distortion. In this paper, we propose a temporal filter-based fog detection algorithm to selectively apply de-fogging method only in the presence of fog. We also propose a method to avoid color distortion by detecting the sky region and applying different methods to the sky region and the non-sky region. Experimental results show that in the actual images, the proposed algorithm shows an average of more than 97% fog detection accuracy, and improves subjective image quality of existing de-fogging algorithms. In addition, the proposed algorithm shows very fast computation time of less than 0.1ms per frame.
ER -