Adaptive and nonlinear techniques for visibility improvement of hazy images

Authors:
Saibabu Arigela;Vijayan K. Asari
Affiliations:
Computer Vision and Wide Area Surveillance Laboratory, Department of Electrical and Computer Engineering, University of Dayton, Dayton, Ohio;Computer Vision and Wide Area Surveillance Laboratory, Department of Electrical and Computer Engineering, University of Dayton, Dayton, Ohio
Venue:
ISVC'11 Proceedings of the 7th international conference on Advances in visual computing - Volume Part II
Year:
2011

Citing 6
Cited 0

Adaptive histogram equalization and its variations

Computer Vision, Graphics, and Image Processing
Single image dehazing

ACM SIGGRAPH 2008 papers
Nonlinear enhancement of extremely high contrast images for visibility improvement

ICVGIP'06 Proceedings of the 5th Indian conference on Computer Vision, Graphics and Image Processing
Contrast restoration of weather degraded images

IEEE Transactions on Pattern Analysis and Machine Intelligence
A multiscale retinex for bridging the gap between color images and the human observation of scenes

IEEE Transactions on Image Processing
Improving image quality in poor visibility conditions using a physical model for contrast degradation

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In outdoor video processing systems, the image frames of a video sequence are usually subjected to poor visibility and contrast in hazy or foggy weather conditions. A fast and efficient technique to improve the visibility and contrast of digital images captured in such environments is proposed in this paper. The image enhancement algorithm constitutes three processes viz. dynamic range compression, local contrast enhancement and nonlinear color restoration. We propose a nonlinear function to modify the wavelet coefficients for dynamic range compression and uses an adaptive contrast enhancement technique in wavelet domain. A nonlinear color restoration process based on the chromatic information of the input image frame is applied to convert the enhanced intensity image back to a color image. We also propose a model based image restoration approach which uses a new nonlinear transfer function on luminance component to obtain the transmission map. Experimental results show better visibility compared to those images enhanced with other state of art techniques.