Item


Visual SLAM for 3D large-scale seabed acquisition employing underwater vehicles

This paper presents a novel technique to align partial 3D reconstructions of the seabed acquired by a stereo camera mounted on an autonomous underwater vehicle. Vehicle localization and seabed mapping is performed simultaneously by means of an Extended Kalman Filter. Passive landmarks are detected on the images and characterized considering 2D and 3D features. Landmarks are re-observed while the robot is navigating and data association becomes easier but robust. Once the survey is completed, vehicle trajectory is smoothed by a Rauch-Tung-Striebel filter obtaining an even better alignment of the 3D views and yet a large-scale acquisition of the seabed

IEEE

Author: Salvi, Joaquim
Petillot, Yvan R.
Batlle, Elisabet
Abstract: This paper presents a novel technique to align partial 3D reconstructions of the seabed acquired by a stereo camera mounted on an autonomous underwater vehicle. Vehicle localization and seabed mapping is performed simultaneously by means of an Extended Kalman Filter. Passive landmarks are detected on the images and characterized considering 2D and 3D features. Landmarks are re-observed while the robot is navigating and data association becomes easier but robust. Once the survey is completed, vehicle trajectory is smoothed by a Rauch-Tung-Striebel filter obtaining an even better alignment of the 3D views and yet a large-scale acquisition of the seabed
Document access: http://hdl.handle.net/2072/63215
Language: eng
Publisher: IEEE
Rights: Tots els drets reservats
Subject: Imatges -- Processament
Kalman, Filtre de
Robots mòbils
Robots submarins
Vehicles submergibles
Image processing
Kalman filtering G
Mobile robots
Submersibles
Underwater robots
Title: Visual SLAM for 3D large-scale seabed acquisition employing underwater vehicles
Type: info:eu-repo/semantics/article
Repository: Recercat

Subjects

Authors