Feature tracking and depth estimation in front-scan sonar image sequences

This paper describes a set of methods that make it possible to estimate the position of a feature inside a three-dimensional (3D) space by starting from a sequence of two-dimensional (2D) acoustic images of the seafloor acquired with a sonar system. The front-scan sonar devoted to generate a 2D image of the seafloor to sail over, and allows one to collect a sequence of images showing a specific feature during the approach of the ship. This fact seems to make it possible to recover the 3D position of a feature by comparing the feature position along the sequence of images acquired from different (known) ship positions. A feature extraction and analysis, a Kalman filter for robust feature tracking, and some ad hoc equations for depth estimation are proposed. Simulated image sequences demonstrated the great potential of the developed system, even though real sequences pointed out some inaccuracies due to errors concerning the knowledge of the ship position and the discrete image nature.