Zygmunt L. Szpak
Computer Vision & Machine Learning

Maritime Surveillance

The aim of this project is to develop a computer vision system that is able to track various targets on the ocean. Ultimately the system will have to cope with a high resolution 360 degree field of view, and because it will be mounted on a ship, it will need to be able to track from a moving unstable platform. Furthermore, the targets are typically very small and poorly contrasted. Since there are many elements to the system, our collaborators are each focusing on different aspects of the system. So far, my work has been on developing a tracking algorithm for the maritime surveillance under the assumption of a panning camera. You can read more about the method in this publications.

The algorithms we developed for maritime surveillance were tested by the Optronics Sensor Systems department of the Center for Scientific and Industrial Research (CSIR) in live field trials. They did an excellent job of transferring the research ideas into a system that actually worked in real-time, and it was a pleasure to collaborate with them.

last update: Tue Oct 06, 2015