Skip to content

This is the MATLAB source code of a haze removal algorithm published in Remote Sensing (MDPI) under the title "Robust Single-Image Haze Removal Using Optimal Transmission Map and Adaptive Atmospheric Light". The transmission map was estimated by maximizing an objective function quantifying image contrast and sharpness. Additionally, an adaptive …

Notifications You must be signed in to change notification settings

datngo93/OTM-AAL

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

OTM-AAL

Summary

This is the MATLAB source code of a haze removal algorithm, which was published in Remote Sensing (MDPI) under the title "Robust Single-Image Haze Removal Using Optimal Transmission Map and Adaptive Atmospheric Light". In this paper, the transmission map was estimated by maximizing an objective function quantifying image contrast and shaprness. Additionally, an adaptive atmospheric light was devised to prevent the loss of dark details after removing haze. The pros and cons of this algorithm is summarized as follows:

Pros Cons
Quality of dehazed images are quite good. Optimal estimate of transmission map is not always guaranteed.
Dark details are well preserved. Extremely time-consuming is a main problem.

Run the code

Executing the file OTM_demo.m in MATLAB R2019a to view the demonstration results on different types of input images, namely:

  • Synthetic road scene.
  • Real hazy scene.
  • Real yellow dust scene.

The souce code of this algorithm was placed in the souce-code folder and the full datasets are available at: Dropbox link

Future development

Solving the optimization problem analytically to derive a direct solution of transmission map. This will significantly accelerate the processing rate and favor the hardware implementation for real-time processing.

Reference

In any publication related to the use of source code or datasets, you are kindly requested to cite the following reference:

  1. Ngo, D.; Lee, S.; Kang, B. Robust Single-Image Haze Removal Using Optimal Transmission Map and Adaptive Atmospheric Light. Remote Sens. 2020, 12, 2233.
  2. Tarel, J.P.; Hautiere, N.; Caraffa, L.; Cord, A.; Halmaoui, H.; Gruyer, D. Vision Enhancement in Homogeneous and Heterogeneous Fog. IEEE Intell. Transp. Syst. Mag. 2012, 4, 6–20.
  3. Ancuti, C.O.; Ancuti, C.; Timofte, R.; De Vleeschouwer, C. O-HAZE: A Dehazing Benchmark with Real Hazy and Haze-Free Outdoor Images. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA, 18–22 June 2018; pp. 867–8678.
  4. Ancuti, C.O.; Ancuti, C.; Timofte, R.; De Vleeschouwer, C. I-HAZE: A dehazing benchmark with real hazy and haze-free indoor images. arXiv 2018, arXiv:1804.05091.

Qualitative results

First Second Third Fourth Fifth Sixth

About

This is the MATLAB source code of a haze removal algorithm published in Remote Sensing (MDPI) under the title "Robust Single-Image Haze Removal Using Optimal Transmission Map and Adaptive Atmospheric Light". The transmission map was estimated by maximizing an objective function quantifying image contrast and sharpness. Additionally, an adaptive …

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages