Drone-View Haze Removal via Regional Saturation-Value Translation and Soft Segmentation

Drone-View Haze Removal via Regional Saturation-Value Translation and Soft Segmentation

This paper proposes an innovative single image dehazing framework, termed Regional Saturation-Value Translation (RSVT), to address the color distortion problems commonly encountered in bright regions by conventional dehazing approaches. The proposed RSVT framework is developed based on two key insig...

Full description

Saved in:
Bibliographic Details
Main Authors: Truong-Dong do, Le-Anh Tran, Seokyong Moon, Jio Chung, Ngoc-Phi Nguyen, Sung Kyung Hong
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Dehazing prior
haze removal
image defogging
image dehazing
image restoration
Online Access:https://ieeexplore.ieee.org/document/10818626/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes an innovative single image dehazing framework, termed Regional Saturation-Value Translation (RSVT), to address the color distortion problems commonly encountered in bright regions by conventional dehazing approaches. The proposed RSVT framework is developed based on two key insights derived from the HSV color space: first, the hue component shows negligible variation between corresponding hazy and haze-free points; and second, in the 2D saturation-value coordinate system, the majority of lines connecting hazy-clean point pairs tend to converge near the atmospheric light coordinates. Consequently, haze removal can be achieved through appropriate translations within the saturation-value coordinates. Additionally, a robust soft segmentation method that employs a morphological min-max channel is integrated into the framework. By combining the soft segmentation mask with the RSVT prior, a comprehensive single image dehazing framework is established. Experimental evaluations across various datasets demonstrate that the proposed approach effectively mitigates color distortion and successfully restores visually appealing images. Moreover, a case study involving actual flight test demonstrates the feasibility and effectiveness of the proposed approach in real-world scenarios. The code is available at <uri>https://github.com/tranleanh/rsvt</uri>.
ISSN:2169-3536

Similar Items