<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Underwater simultaneous localization and mapping (SLAM) poses significant challenges for modern visual SLAM systems. The integration of deep learning networks within computer vision offers promising potential for addressing these difficulties. Our research draws inspiration from deep learning approaches applied to interest point detection and matching, single image depth prediction and underwater image enhancement. In response, we propose 3D-Net, a deep learning-assisted network designed to tackle these three tasks simultaneously. The network consists of three branches, each serving a distinct purpose: interest point detection, descriptor generation, and depth prediction. The interest point detector and descriptor generator can effectively serve as a front end for a classical SLAM system. The predicted depth information is akin to a virtual depth camera, opening up possibilities for various applications. We provide quantitative and qualitative evaluations to illustrate some of these potential uses. The network was trained in in several steps, using in-air datasets and followed by generated underwater datasets. Further, the network is integrated into feature-based SALM systems ORBSLAM2 and ORBSSLAM3, providing a comprehensive assessment of its effectiveness for underwater navigation.</p>
</abstract>

Underwater simultaneous localization and mapping (SLAM) poses significant challenges for modern visual SLAM systems. The integration of deep learning networks within computer vision offers promising potential for addressing these difficulties. Our research draws inspiration from deep learning approaches applied to interest point detection and matching, single image depth prediction and underwater image enhancement. In response, we propose 3D-Net, a deep learning-assisted network designed to tackle these three tasks simultaneously. The network consists of three branches, each serving a distinct purpose: interest point detection, descriptor generation, and depth prediction. The interest point detector and descriptor generator can effectively serve as a front end for a classical SLAM system. The predicted depth information is akin to a virtual depth camera, opening up possibilities for various applications. We provide quantitative and qualitative evaluations to illustrate some of these potential uses. The network was trained in in several steps, using in-air datasets and followed by generated underwater datasets. Further, the network is integrated into feature-based SALM systems ORBSLAM2 and ORBSSLAM3, providing a comprehensive assessment of its effectiveness for underwater navigation.

UW Deep SLAM-CNN Assisted Underwater SLAM

Applied Computer Systems

This work is licensed under the Creative Commons Attribution 4.0 International License.

{"article-title":"UW Deep SLAM-CNN Assisted Underwater SLAM"}

Underwater simultaneous localization and mapping (SLAM) poses significant challenges for modern visual SLAM systems. The integration of deep learning networks...

UW Deep SLAM-CNN Assisted Underwater SLAM

Online veröffentlicht: 17. Aug. 2023

Seitenbereich: 100 - 113

DOI: https://doi.org/10.2478/acss-2023-0010

Schlüsselwörter
Autonomous underwater vehicle, deep-SLAM, machine learning, underwater navigation

© 2023 Chinthaka Amarasinghe et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

UW Deep SLAM-CNN Assisted Underwater SLAM

Online veröffentlicht: 17. Aug. 2023

Seitenbereich: 100 - 113

DOI: https://doi.org/10.2478/acss-2023-0010

SchlüsselwörterAutonomous underwater vehicle, deep-SLAM, machine learning, underwater navigation

© 2023 Chinthaka Amarasinghe et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Autonomous underwater vehicle, deep-SLAM, machine learning, underwater navigation