IADO 05364
INSTITUTO ARGENTINO DE OCEANOGRAFIA
Unidad Ejecutora - UE
artículos
Título:
A Vision-Based Navigation System for Path Tracking of Autonomous Underwater Vehicles in Environments with Regular Patterns
Autor/es:
MARIO A. JORDÁN; CARLOS BERGER; JORGE BUSTAMANTE
Revista:
INTERNATIONAL JOURNAL OF COMPUTER VISION
Editorial:
SPRINGER
Referencias:
Año: 2011
ISSN:
0920-5691
Resumen:
In this paper a vision-based algorithm for on-line estimation of position control errors in a guidance system for path tracking is presented.The algorithm uses techniques of pattern recognition, however with a high degree of morphological simplifications. The algorithm detects the path line stretch which is displayed in the actual frame, and estimates the slope of the line and its midpoint. Moreover, it identifies a confidence zone in where the line stretch would be certainly. The complete translation of coordinates from image moving to the camera motion is presented. Ad-hoc experiments with a subaquatic vehicle in an test tank show the features of the algorithm proposed under strong conditions of light perturbation and cloudy water.
