Low-Light Image Enhancement Algorithm for Unmanned Aerial Vehicle Imagery via Color Distribution

Xiaotong Bai*, Dianwei Wang*, Jie Fang, Yuanqing Li, Jiayin Wen, Zhijie Xu

*Corresponding author for this work

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

Abstract

Unmanned aerial vehicle (UAV) imagery captured under low-light conditions are often suffering from uneven illumination and lack of detail. To address these issues, this paper proposes a low-light image enhancement algorithm for UAV imagery, which locate different illumination regions with local color distribution. Firstly, a bright channel prior(BCP) is utilized to train the enhancement network by unsupervised learning approach. Secondly, a color distribution module is constructed to locate and enhance different illumination regions. Experimental results show that the proposed method can preserve the detailed information in images while enhancing image brightness, and enhance different illumination regions in low-light UAV images.

Original languageEnglish
Title of host publication2024 6th International Conference on Natural Language Processing, ICNLP 2024
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages520-524
Number of pages5
ISBN (Electronic)9798350349115
DOIs
Publication statusPublished - 2024
Externally publishedYes
Event6th International Conference on Natural Language Processing, ICNLP 2024 - Hybrid, Xi'an, China
Duration: 22 Mar 202424 Mar 2024

Publication series

Name2024 6th International Conference on Natural Language Processing, ICNLP 2024

Conference

Conference6th International Conference on Natural Language Processing, ICNLP 2024
Country/TerritoryChina
CityHybrid, Xi'an
Period22/03/2424/03/24

Keywords

  • bright channel prior
  • color distribution module
  • low-light image enhancement
  • UAV imagery

Fingerprint

Dive into the research topics of 'Low-Light Image Enhancement Algorithm for Unmanned Aerial Vehicle Imagery via Color Distribution'. Together they form a unique fingerprint.

Cite this