Restoration of Day and Night Foggy Images Using Fuzzy Based Dark Channel Prior: Restoration of Day and Night Foggy Images Using Fuzzy

Sameen Habib; Aun  Irtaza; Nudrat Nida; Muhammad  Imran; Ali Javed

Authors

Sameen Habib Department of Computer Science, University of Engineering and Technology, Taxila 47050, Pakistan
Aun Irtaza Department of Computer Science, University of Engineering and Technology, Taxila 47050, Pakistan
Nudrat Nida Department of Computer Science, Air University, Islamabad, Aerospace & Aviation Campus, Kamra, Pakistan
Muhammad Imran Department of Computer Science, SZABIST Islamabad Campus, Islamabad, Pakistan
Ali Javed Department of Software Engineering, University of Engineering and Technology, Taxila 47050, Pakistan

Keywords:

Dark Channel Prior, Fuzzy Logic, Guided Filter, Transmission map, Air-Light, Realistic Single Image De-hazing (RESIDE)

Abstract

In this paper we proposed a fuzzy method based on dark channel prior to enhance the visibility of images that are degraded by fog or haze. In order to improve the perceptual visibility of RGB images, we modified the dark channel prior through fuzzy logic. The dark channel prior significantly measures the statistical estimation of haze-free outdoor images. It is based on fact that in haze free images most patches include pixels which have very low intensity in channel that is effective in estimation of thickness of haze and is capable to recover high quality haze-free images. We applied fuzzy logic with dark channel prior for computing probabilistic values other than lowest pixel intensity values among channels of images. Our experimental finding reveals that proposed method for restoration of foggy images using fuzzy logic along with atmospheric light, transmission map, and scene radiance effectively recovers the original fog free image. To further enhance the image perceptual quality, the guided filter was applied on the resultant fog free images for edge smoothing and noise removal. For performance evaluation of proposed method, we used Realistic Single Image De-hazing (RESIDE) dataset consisting of foggy images of different haze density. We introduce proposed scheme by combining the fuzzy logic with dark channel prior and demonstrate that the proposed method is capable to estimate the corresponding fog function which is significant for fog removal, improve image visibility, and increase user safety.

References

H. Wei., Y. Wang, and A. Wang. A high fidelity haze removal algorithm for optical satellite images using progressive transmission estimation based on the dark channel prior. International Journal of Remote Sensing, 40(9) 3486-3503 (2018).

Y. Wang., F. Fangfa., L. Fengchang., X. Weizhe., S. Jinjin, and J. Wang. Haze removal algorithm based on single-images with chromatic properties. Signal Processing: Image Communication (2018).

Y. Liang., Z. Kuibin., Z. Wenqiang, and Y. Li. Research on single image haze removal algorithm based on parameter optimization search of linear model. IEEE,International Conference on Advanced Mechatronic Systems (ICAMechS): 326-331 (2018).

L. Jimin., Y. Wang, and S. Zhou. Haze Removal Algorithm Using Color Attenuation Prior and Guided Filter. In Proceedings of the 3rd International Conference on Multimedia Systems and Signal Processing, ACM: 41-45 (2018).

Yuan, and H. Huang. Image Haze Removal via Reference Retrieval and Scene Prior. IEEE Transactions on Image Processing 27: 4395-4409 : doi: 10.1109/TIP.283790 (2018).

N.S. Pal., S. Lal, and K. Shinghal. A Visibility Restoration Framework for rainy images by using Lo gradient minimization and Bilateral Filtering. International Conference on Advances in Computing, Communication Control and Networking (ICACCCN) : 848-852 (2018).

G. Zhenfei., J. Mingye, and Z. Deng-yin. A Single Image Dehazing Method Using Average Saturation Prior. Mathematical Problems in Engineering : 1-17 (2017).

W. Jinbao., K. Lu, J. Xue., N. He, and L. Shao. Single image dehazing based on the physical model and MSRCR algorithm. IEEE Transactions on Circuits and Systems for Video Technology 28: 2190-2199 (2018).

K. Jin-Hwan., J.Y. Sim, and C.S. Kim. Single image dehazing based on contrast enhancement. In Acoustics, Speech and Signal Processing (ICASSP), IEEE International Conference on: 1273-1276 (2011).

P. Mario., H. Belzner., G. Rigoll, and S. Ilić. Image based fog detection in vehicles. In Intelligent Vehicles Symposium (IV): 1132-1137 (2012).

H. Farhan, and J. Jeong. Visibility enhancement of scene images degraded by foggy weather conditions with deep neural networks. Journal of Sensors (2016).

B. Yu., B.S. Kim, and K.H. Lee. Visibility Enhancement Based Real--Time Retinex for Diverse Environments. In Signal Image Technology and Internet Based Systems (SITIS), Eighth International Conference on: 72-79 (2012).

E. Salari., M. Li, and D. Ouyang. Foggy image enhancement based on Principal Component Analysis. In Circuits and Systems (MWSCAS), IEEE 56th International Midwest Symposium on: 1259- 1262 (2013).

L. He., C. Zhang, R. Yang, and K. Zhu. Convex optimization for fast image dehazing. IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, 2246-2250: doi: 10.1109/ ICIP.7532758(2016).

Y. Liu., J. Shang, L. Pan, A. Wang, and M. Wang. A Unified Variational Model for Single Image Dehazing. in IEEE Access 7: 15722-15736: doi: 10.1109/ACCESS.2894525 (2019).

S. Bianco., L. Celona., F. Piccoli, and R. Schettini. High-Resolution Single Image Dehazing using Encoder-Decoder Architecture. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2019).

Q. Liu., X. Gao, L. He, and W. Lu. Single Image Dehazing With Depth-Aware Non-Local Total Variation Regularization. IEEE Transactions on Image Processing 27: 5178-5191 (2018).

A.O. Ancuti., C. Ancuti, and P. Bekaert. Effective single image dehazing by fusion. IEEE International Conference on Image Processing, Hong Kong, 3541-3544 (2010).

H. Kaiming., J. Sun, and X. Tang. Single image haze removal using dark channel prior. IEEE transactions on pattern analysis and machine intelligence 33: 2341-2353 (2011).

H. Muhammad., A. Hussain, and T.S. Choi. Adaptive threshold based fuzzy directional filter design using background information. Applied soft computing 29: 471-478 (2015).

K. Fei., W. Chen., C. Wen, and Z. Li. Gradient domain guided image filtering. IEEE Transactions on Image Processing 24: 4528-4539 (2015).

Lotfi. Z.A. Toward a theory of fuzzy information granulation and its centrality in human reasoning and fuzzy logic. Fuzzy sets and systems 90, p. 111- 127 (1997).

H. Kaiming., J. Sun, and X. Tang. Guided image filtering. In European conference on computer vision, Springer, Berlin, Heidelberg, 1-14 (2010).

B. Cai., X. Xu, K. Jia, C. Qing, and D. Tao. DehazeNet: An End-to-End System for Single Image Haze Removal. IEEE Transactions on Image Processing 25: 5187-5198 (2016).

P. Luo., R. Chunwang., K. Jian,and Q. Zheng. Improvement of the Algorithm Based on Dark Channel Prior Defogging. IOP Conference Series. Earth and Environmental Science. 300: doi:10.1088/1755-1315/300/2/022045 (2019).

Y.T. Peng., C. Keming, and C. Pamela. Generalization of the Dark Channel Prior for Single Image Restoration. IEEE Transactions on Image Processing, 1-1: doi: 10.1109/TIP.2813092 (2019).

W. Wencheng., Y. Xiaohui., W. Xiaojin, and L. Yunlong. Fast Image Dehazing Method Based on Linear Transformation. IEEE Transactions on Multimedia, 1-1: doi: 10.1109/TMM.2652069(2017).

M. Everingham., L.V. Gool., C.K.I. Williams, J. Winn, and A. Zisserman. The pascal visual object classes (voc) challenge. International Journal of Computer Vision, 88(2):303– 338 (2010).

L. Boyi., W. Ren., D. Fu., D. Tao, and D. Feng. Benchmarking Single Image Dehazing and Beyond. IEEE Transactions on Image Processing 28: 492-505 (2019)

Restoration of Day and Night Foggy Images Using Fuzzy Based Dark Channel Prior