A Probabilistic Underwater Localisation based on Cross-view and Cross-domain Acoustic and Aerial Images

This paper presents a cross-domain and cross-view framework for underwater robot localisation, which does not require any Global Positioning System (GPS) information. The proposed localisation method uses colour aerial images and underwater acoustic images to estimate the robot’s position. The method identifies the correlation among images from distinct domains, given by the matching of images acquired in partially structured environments with shared features. The validation of the proposed method is done using a real dataset, which was acquired by an underwater vehicle in a Marina. Besides, it was compared to Dead Reckoning and a learning-based particle filter method. The experimental results present the feasibility of the proposed method and its advances in relation to state-of-the-art algorithms.