Back to all available

Fast Retinex enhancement for UAV-to-satellite image matching in low-light and GPS-denied conditions

artificial-intelligence
autonomous-systems
computer-vision
data-mining-and-machine-learning
spatial-and-geographic-information-systems

Abstract

Uncrewed aerial vehicles (UAVs) are increasingly used in environmental monitoring and autonomous navigation. However, in certain specific tasks, UAVs often need to operate in low-light conditions. Low-light environments severely degrade image quality and make visual matching with high-quality satellite maps difficult. Similarly, many UAV missions require high real-time image processing capabilities. To address this issue, we investigated a low-light UAV image enhancement method based on a lightweight Retinex model. We aim to achieve faster image enhancement in low-light scenarios while maintaining high matching accuracy as much as possible. We obtain low-light UAV images for experiments by processing well-lit aerial images with exposure reduction, gamma compression, and noise injection. We then validate the method using the SuperPoint-LightGlue feature matching and the homography-based RANSAC algorithm. Using this validation process, we evaluated the matching performance of UAVs and satellite images under different lighting and preprocessing conditions. Using multi-scale Retinex and color restoration (MSRCR) as baseline enhancement methods, we reproduce and test the MSRCR algorithm. Experimental results show that, while the MSRCR algorithm effectively brightens images, it is computationally expensive and amplifies noise, making it unsuitable for real-time systems. To address this issue, we propose a fast Retinex variant algorithm. This method operates on the luminance channel, multiplexes Gaussian convolutions across scales, and linearly fuses the enhanced result with the original image. This reduces computational cost while effectively controlling noise growth. Experiments show that, under low-light conditions, our method achieves a slightly higher RANSAC inlier count and a similar inlier rate compared to the MSRCR algorithm. At the same time, it reduces the processing time of the enhancement stage by approximately 66\%. Therefore, without significantly sacrificing matching performance, our proposed method effectively reduces the computational cost of low-light image enhancement.
Ask to review this manuscript

Notes for potential reviewers

  • Volunteering is not a guarantee that you will be asked to review. There are many reasons: reviewers must be qualified, there should be no conflicts of interest, a minimum of two reviewers have already accepted an invitation, etc.
  • This is NOT OPEN peer review. The review is single-blind, and all recommendations are sent privately to the Academic Editor handling the manuscript. All reviews are published and reviewers can choose to sign their reviews.
  • What happens after volunteering? It may be a few days before you receive an invitation to review with further instructions. You will need to accept the invitation to then become an official referee for the manuscript. If you do not receive an invitation it is for one of many possible reasons as noted above.
  • PeerJ Computer Science does not judge submissions based on subjective measures such as novelty, impact or degree of advance. Effectively, reviewers are asked to comment on whether or not the submission is scientifically and technically sound and therefore deserves to join the scientific literature. Our Peer Review criteria can be found on the "Editorial Criteria" page - reviewers are specifically asked to comment on 3 broad areas: "Basic Reporting", "Experimental Design" and "Validity of the Findings".
  • Reviewers are expected to comment in a timely, professional, and constructive manner.
  • Until the article is published, reviewers must regard all information relating to the submission as strictly confidential.
  • When submitting a review, reviewers are given the option to "sign" their review (i.e. to associate their name with their comments). Otherwise, all review comments remain anonymous.
  • All reviews of published articles are published. This includes manuscript files, peer review comments, author rebuttals and revised materials.
  • Each time a decision is made by the Academic Editor, each reviewer will receive a copy of the Decision Letter (which will include the comments of all reviewers).

If you have any questions about submitting your review, please email us at [email protected].