Improving visual odometry for AUV navigation in marine environments
DOI:
https://doi.org/10.5821/iwp.2021.21.14783Abstract
Visual odometry is usually integrated in the localization and control modules of underwater robots, combined with other data coming from diverse instruments and sensors, such as, Doppler Velocity Logs (DVL), pressure sensors or inertial units, to compute the vehicle motion and pose by means of death reckoning. Dead reckoning is subject to cumulative drift, and, in underwater scenarios is specially afected by the challenging structures, color textures and environmental conditions (currents, haze, water density, salinity, wind, etc...), increasing the need of specifc improvement or adjustment to this media. This article presents preliminary results of an evolution of the well known VISO2 stereo odometer, modifed in order to improve its performance when run online in marine scenarios, and from a moving Autonomous Underwater Vehicle (AUV) equipped with cameras pointing downwards to the sea bottom.
Issue
Section
License
Universitat Politècnica de Catalunya has joined the Berlin Declaration on Open Access to Knowledge in the Sciences and Humanities. This declaration proposes the universal acces to the results of scientific and technical research.
All papers presented at Martech will be published in both the UPCommons and the Martech organization web sites, the former being the institutional digital deposit of Universitat Politècnica de Catalunya (https://upcommons.upc.edu). This difussion will be made through the Creative Commons License Attribution-NonCommercial-NoDerivs 2.5 or similar (http://creativecommons.org/licenses/by-nc-nd/2.5/deed.en).
When sending the final paper, the author must agree to the conference having non-exclusive rights on this operation. The author will maintain his/her right to diffuse the paper elsewhere.
