Format

Send to

Choose Destination
Sensors (Basel). 2018 Jul 17;18(7). pii: E2313. doi: 10.3390/s18072313.

Fast Visual Odometry for a Low-Cost Underwater Embedded Stereo System .

Author information

1
Aix-Marseille Université, CNRS, ENSAM , Université De Toulon, LIS UMR 7020, Domaine Universitaire de Saint-Jérôme, Bâtiment Polytech, Avenue Escadrille Normandie-Niemen, 13397 Marseille, France. mohamad-motasem.NAWAF@univ-amu.fr.
2
Aix-Marseille Université, CNRS, ENSAM , Université De Toulon, LIS UMR 7020, Domaine Universitaire de Saint-Jérôme, Bâtiment Polytech, Avenue Escadrille Normandie-Niemen, 13397 Marseille, France. Djamal.Merad@univ-amu.fr.
3
Aix-Marseille Université, CNRS, ENSAM , Université De Toulon, LIS UMR 7020, Domaine Universitaire de Saint-Jérôme, Bâtiment Polytech, Avenue Escadrille Normandie-Niemen, 13397 Marseille, France. Jean-Philip.Royer@univ-amu.fr.
4
Aix-Marseille Université, CNRS, ENSAM , Université De Toulon, LIS UMR 7020, Domaine Universitaire de Saint-Jérôme, Bâtiment Polytech, Avenue Escadrille Normandie-Niemen, 13397 Marseille, France. Jean-Marc.Boi@univ-amu.fr.
5
Aix-Marseille Université, CNRS, ENSAM , Université De Toulon, LIS UMR 7020, Domaine Universitaire de Saint-Jérôme, Bâtiment Polytech, Avenue Escadrille Normandie-Niemen, 13397 Marseille, France. Mauro.Saccone@univ-amu.fr.
6
Aix-Marseille Université, CNRS, ENSAM , Université De Toulon, LIS UMR 7020, Domaine Universitaire de Saint-Jérôme, Bâtiment Polytech, Avenue Escadrille Normandie-Niemen, 13397 Marseille, France. Mohamed.Ben-Ellefi@univ-amu.fr.
7
Aix-Marseille Université, CNRS, ENSAM , Université De Toulon, LIS UMR 7020, Domaine Universitaire de Saint-Jérôme, Bâtiment Polytech, Avenue Escadrille Normandie-Niemen, 13397 Marseille, France. pierre.drap@univ-amu.fr.

Abstract

This paper provides details of hardware and software conception and realization of a stereo embedded system for underwater imaging. The system provides several functions that facilitate underwater surveys and run smoothly in real-time. A first post-image acquisition module provides direct visual feedback on the quality of the taken images which helps appropriate actions to be taken regarding movement speed and lighting conditions. Our main contribution is a light visual odometry method adapted to the underwater context. The proposed method uses the captured stereo image stream to provide real-time navigation and a site coverage map which is necessary to conduct a complete underwater survey. The visual odometry uses a stochastic pose representation and semi-global optimization approach to handle large sites and provides long-term autonomy, whereas a novel stereo matching approach adapted to underwater imaging and system attached lighting allows fast processing and suitability to low computational resource systems. The system is tested in a real context and shows its robustness and promising future potential.

KEYWORDS:

3D reconstruction; embedded systems; image processing; stereo vision; underwater imaging; visual odometry

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center