Towards Visual Autonomy Underwater

Visual input is considered unreliable underwater and therefore its current use in automatic analysis and decisions is limited. This influences the design of autonomous underwater vehicles which are usually equipped with multiple sensors which make them expensive and cumbersome. On the other hand, human divers often manage to complete complicated tasks using a very lean sensor suite that is heavily based on vision. We aim to bridge this gap and develop algorithms that can exploit the problematic visual underwater input, and systems that use this input for underwater tasks. In the talk I will present several methods we developed for enhancing the visibility underwater and ongoing work on underwater autonomous vehicles using vision.