Vision based obstacle detection and mapping for unmanned surface vehicles

Abstract

An unmanned surface vehicle (USV) is a speed boat that comes with a suit of sensors to understand maritime environment and navigational intelligence to know how to navigate itself autonomously. In this thesis, we focus on exploring and enhancing the perception ability of USV based on vision.Detecting and mapping obstacles in maritime environments with high accuracy and robustness are two important issues for USV in real-life applications, such as surveillance and navigation. Solutions based on vision (cameras) are more cost-I have got a lot of help, supports and encouragements from a number of people for the completion of this thesis.First of all, I would like to thank my supervisor Associate Professor Wang Han, who made it possible for me to come to NTU to pursue my PhD degree in his research group. Moreover, Prof. Wang gave me many advices and instructions on how to do research and what research topic to choose. I am deeply influenced by his passion for research and his patience for teaching, and some ideas of my research were inspired by the discussion with him. I cannot make my research go smoothly without the support of Prof. Wang. Therefore, I give a lot of thanks to Prof. Wang for his selfless help and support.I feel very fortunate to work with many warm-hearted and friendly colleagues.