Skip to main navigation Skip to search Skip to main content

A Dynamic Adaptive White Patch Retinex Algorithm for Enhancing Aerial Images of Power Lines

  • Xi'an Jiaotong University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The traditional White Patch Retinex algorithm is based on the "global white spot assumption", which leads to issues such as noise robustness, illumination estimation bias, and detail loss. To address these issues, this paper proposes a Dynamic Adaptive White Patch Retinex algorithm, named DAWPR, which introduces the Sobel operator to calculate the gradient amplitude of the image as a measure of image complexity. A mapping model is Constructed between gradient values and window size to form a dynamic window size adjustment mechanism for effectively solving the problem of light adaptability in power aerial images. The experimental results demonstrate that DAWPR has significant advantages in preserving details, enhancing clarity, and improving contrast.

Original languageEnglish
Title of host publication2025 8th International Conference on Information Communication and Signal Processing, ICICSP 2025
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages546-550
Number of pages5
ISBN (Electronic)9798350357653
DOIs
StatePublished - 2025
Event8th International Conference on Information Communication and Signal Processing, ICICSP 2025 - Hybrid, Xi'an, China
Duration: 12 Sep 202514 Sep 2025

Publication series

Name2025 8th International Conference on Information Communication and Signal Processing, ICICSP 2025

Conference

Conference8th International Conference on Information Communication and Signal Processing, ICICSP 2025
Country/TerritoryChina
CityHybrid, Xi'an
Period12/09/2514/09/25

Keywords

  • Comprehensive assessment system
  • Dynamic window mechanism
  • Image enhancement
  • Image gradient magnitude

Fingerprint

Dive into the research topics of 'A Dynamic Adaptive White Patch Retinex Algorithm for Enhancing Aerial Images of Power Lines'. Together they form a unique fingerprint.

Cite this