Image Enhancement of Low Light UAV via Global Illumination Self-aware feature Estimation

Jingyu Niu, Dianwei Wang*, Pengfei Han, Jie Fang, Xincheng Ren, Yongrui Qin, Zhijie Xu

*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

UAV images acquired under low light conditions are often characterized by low contrast and poor visual effect. To improve image quality, a low light UAV image enhancement method via global illumination self-aware feature estimation was proposed. First, a novel lightweight GhostNet is introduced to extract deeper image features. Secondly, the self-aware module is used to correct the possible missing information between encoder network and decoder network. Finally, gradient loss and structural similarity loss are used to constrain the network to achieve the goal of edge preservation and detail restoration. Through extensive experiments, the method proposed can effectively improve the visualization effect, and get more natural and real results.

Original languageEnglish
Title of host publicationProceedings - 2021 3rd International Conference on Natural Language Processing, ICNLP 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages225-231
Number of pages7
ISBN (Electronic)9781665414111
DOIs
Publication statusPublished - Mar 2021
Externally publishedYes
Event3rd International Conference on Natural Language Processing, ICNLP 2021 - Beijing, China
Duration: 26 Mar 202128 Mar 2021

Publication series

NameProceedings - 2021 3rd International Conference on Natural Language Processing, ICNLP 2021

Conference

Conference3rd International Conference on Natural Language Processing, ICNLP 2021
Country/TerritoryChina
CityBeijing
Period26/03/2128/03/21

Keywords

  • feature extraction
  • GhostNet
  • image enhancement
  • self-aware
  • UAV image

Fingerprint

Dive into the research topics of 'Image Enhancement of Low Light UAV via Global Illumination Self-aware feature Estimation'. Together they form a unique fingerprint.

Cite this