Algorithm and Hardware Implementation of Image Haze Removal Combining with Sky Recognition

DOI

10.2991/eia-17.2017.27How to use a DOI?

Keywords

dark channel prior; guided image filter; sky recognition; fpga

Abstract

When a picture is taken in the haze, the picture is abstract and much information is hidden by the haze. In this paper, on the basis of the dark channel prior algorithm, dehazing of hazy images is carried out. At the same time, given defects of the dark channel prior algorithm, namely halo, color lumps and color cast etc. on the sky area after dehazing, sky recognition algorithm and guided filter algorithm are integrated together to dehaze. The sky recognition algorithm can distinguish the sky region effectively. And high-precision transmissivity parameter can be obtained using guided filter algorithm. The whole algorithm has been verified in both the C language simulation environment and the Matlab simulation environment. The hardware implementation is completed on the self-designed FPGA hardware platform. Running results show that the operation of the algorithm proposed in this paper is stable and it can carry out image dehazing effectively.

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  - Xiaobo ZHOU
AU  - Xiaodong FAN
PY  - 2017/07
DA  - 2017/07
TI  - Algorithm and Hardware Implementation of Image Haze Removal Combining with Sky Recognition
BT  - Proceedings of the 2017 International Conference on Electronic Industry and Automation (EIA 2017)
PB  - Atlantis Press
SP  - 126
EP  - 131
SN  - 1951-6851
UR  - https://doi.org/10.2991/eia-17.2017.27
DO  - 10.2991/eia-17.2017.27
ID  - ZHOU2017/07
ER  -