Fast Single Image Haze Removal Method based on Atmospheric Scattering Model

DOI

10.2991/icwcsn-16.2017.22How to use a DOI?

Keywords

dehaze; saturation; low-pass filter; contrast; transmission map estimation

Abstract

In this paper, we propose an effective and efficient method to remove haze from a single input image. We first remove fine details from the minimum channel of RGB channels by a low-pass filter and then use it as a rough estimation of the transmission map. Then, we refine the rough estimation by using the saturation channel of HSI color space and local contrast. Based on the atmospheric scattering model, we then obtain a high-quality haze-removed image. Results on a variety of hazy images demonstrate the effectiveness and efficiency of our method.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - De-Wei Huang
AU  - Ke-Xin Chen
AU  - Jian-Qiang Lu
AU  - Wei-Xing Wang
PY  - 2016/12
DA  - 2016/12
TI  - Fast Single Image Haze Removal Method based on Atmospheric Scattering Model
BT  - Proceedings of the 3rd International Conference on Wireless Communication and Sensor Networks (WCSN 2016)
PB  - Atlantis Press
SP  - 100
EP  - 104
SN  - 2352-538X
UR  - https://doi.org/10.2991/icwcsn-16.2017.22
DO  - 10.2991/icwcsn-16.2017.22
ID  - Huang2016/12
ER  -