Home > Published Issues > 2022 > Volume 17, No. 7, July 2022 >

Implementation of Satellite Road Image Denoising using Iterative Domain Guided Image Filtering with Gray World Optimization

D. Subhashini 1,2 and V. B. S. Srilatha Indira Dutt 2
1. GITAM (Deemed to be University), Visakapatnam, India
2. Dept of ECE, GITAM (Deemed to be University), Visakapatnam, India

Abstract—Generally, Satellite road images are in noisy conditions such as noise, snow, thin cloud, dust, etc., which results in contrast degradations in the image. Denoising is defined as the technique for removing noise or atmospheric impurities from an image to increase the quality of an image. But most of the state of art approaches failed to remove the atmospheric effects and noise from the road image perfectly. To solve this problem, this paper majorly focuses on developing a Gray World Optimization (GWO) algorithm for the perfect estimation of atmospheric road light. The work also develops the novel method for dark channel prior-based transmission map estimation and refinement in pixel-wise and patch-wise manner. Thus, the atmospheric road effects are resolved in each pixel-based patch. Finally, a fast iterative domain guided image filtering (ID-GIF) approach was developed to obtain smoothen output with Denoising properties. The simulation results show that the proposed work provides better quantitative and qualitative results than state-of-the-art approaches.
 
Index Terms—Gray world optimization, fast iterative domain guided image filtering, dark channel prior

Cite: D. Subhashini and V. B. S. Srilatha Indira Dutt, "Implementation of Satellite Road Image Denoising using Iterative Domain Guided Image Filtering with Gray World Optimization," Journal of Communications vol. 17, no. 7, pp. 581-591, July 2022. Doi: 10.12720/jcm.17.7.581-591

Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.