Visual navigation of an autonomous underwater vehicle using image sequences of a scanning sonar

We use image sequences generated by an electronic scanning sonar to achieve the aim of obstacle avoidance and visual navigation for an autonomous underwater vehicle (AUV). Using sonar systems for the sensing of unknown underwater environments is the best selection in practice. However, the critical demand for real-time signal processing and the uncertainties of AUV's dynamics make online detection of obstacles a challenging task. We use the track-before-detect algorithm to extract information contained in image sequences to estimate the dynamics of the AUV and to solve the problem of detection. This method reduces the computational cost to meet the real-time demand on obstacle avoidance and navigation of the AUV.