English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In this paper, we present a comprehensive investigation of the challenges ofMonocular Visual Simultaneous Localization and Mapping (vSLAM) methods forunderwater robots. While significant progress has been made in state estimationmethods that utilize visual data in the past decade, most evaluations have beenlimited to controlled indoor and urban environments, where impressiveperformance was demonstrated. However, these techniques have not beenextensively tested in extremely challenging conditions, such as underwaterscenarios where factors such as water and light conditions, robot path, anddepth can greatly impact algorithm performance. Hence, our evaluation isconducted in real-world AUV scenarios as well as laboratory settings whichprovide precise external reference. A focus is laid on understanding the impactof environmental conditions, such as optical properties of the water andillumination scenarios, on the performance of monocular vSLAM methods. To thisend, we first show that all methods perform very well in in-air settings andsubsequently show the degradation of their performance in challengingunderwater environments. The final goal of this study is to identify techniquesthat can improve accuracy and robustness of SLAM methods in such conditions. Toachieve this goal, we investigate the potential of image enhancement techniquesto improve the quality of input images used by the SLAM methods, specificallyin low visibility and extreme lighting scenarios in scattering media. Wepresent a first evaluation on calibration maneuvers and simple imagerestoration techniques to determine their ability to enable or enhance theperformance of monocular SLAM methods in underwater environments.

Investigation of the Challenges of Underwater-Visual-Monocular-SLAM