DarkSLAM: GAN-assisted Visual SLAM for Reliable Operation in Low-light Conditions

Alena Savinykh, Mikhail Kurenkov, Evgeny Kruzhkov, Evgeny Yudin, Andrei Potapov, Pavel Karpyshev, Dzmitry Tsetserukou

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

Abstract

Existing visual SLAM approaches are sensitive to illumination, with their precision drastically falling in dark conditions due to feature extractor limitations. The algorithms currently used to overcome this issue are not able to provide reliable results due to poor performance and noisiness, and the localization quality in dark conditions is still insufficient for practical use. In this paper, we present a novel SLAM method capable of working in low light using Generative Adversarial Network (GAN) preprocessing module to enhance the light conditions on input images, thus improving the localization robustness. The proposed algorithm was evaluated on a custom indoor dataset consisting of 14 sequences with varying illumination levels and ground truth data collected using a motion capture system. According to the experimental results, the reliability of the proposed approach remains high even in extremely low light conditions, providing 25.1% tracking time on darkest sequences, whereas existing approaches achieve tracking only 0.6% of the sequence time.

Original languageEnglish
Title of host publication2022 IEEE 95th Vehicular Technology Conference - Spring, VTC 2022-Spring - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665482431
DOIs
Publication statusPublished - 2022
Event95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring - Helsinki, Finland
Duration: 19 Jun 202222 Jun 2022

Publication series

NameIEEE Vehicular Technology Conference
Volume2022-June
ISSN (Print)1550-2252

Conference

Conference95th IEEE Vehicular Technology Conference - Spring, VTC 2022-Spring
Country/TerritoryFinland
CityHelsinki
Period19/06/2222/06/22

Keywords

  • Generative Adversarial Networks
  • Localization
  • Low-light Enhancement
  • Mapping
  • Monocular Camera
  • Visual SLAM

Fingerprint

Dive into the research topics of 'DarkSLAM: GAN-assisted Visual SLAM for Reliable Operation in Low-light Conditions'. Together they form a unique fingerprint.

Cite this