Ground obstacle tracking on forward looking sonar images
Résumé
Obstacle avoidance capability for an Autonomous Underwater Vehicle (AUV) is of high interest for the French defence and especially GESMA centre which is involved in the development of decisional autonomy for AUV for several years. In addition to its original mission, the vehicle must ensure its own survival and must therefore understand the environment in safety. The use of a Forward Looking Sonar (FLS) on AUV is one of the most efficient solutions to detect unexpected and potentially dangerous changes of the environment, like the presence of obstacles or seabed slope. Like this, a FLS can prevent the vehicle from obstacles or terrain that may endanger the underwater vehicle. A process model has been derived based on navigation data in order to predict the motion of a ground target which has been detected in the sonar image. This model has been used in the prediction step of a Kalman filter that enables still targets tracking through successive frames. The article gives an overview of the overall architecture with a focus on Kalman filtering. An assessment will be done on synthetic and real data recorded in April 2006 during sea trials organized by GESMA.
Origine : Fichiers produits par l'(les) auteur(s)