Events test

Matej Kristan presents Computer vision-based obstacle detection for autonomous boats

On 2021-07-14 11:00 at https://feectu.zoom.us/j/99518559188
CHANGE: the seminar will be held on line, zoom link
https://feectu.zoom.us/j/99518559188

Autonomy is transforming most industries, and maritime robotics is no
exception.

With 90% of goods moved across the world in vessels, unmanned surface vehicles
(USVs) present a considerable market opportunity. Small-sized USVs, in
particular, present affordable devices for automated inspection of hazardous
areas and periodic surveillance of coastal waters and have a strong potential
for a wide-spread use. Apart from efficient control and high-level planning,
safe and uninterrupted navigation relies on environment perception, in
particular on obstacle detection and timely collision avoidance. The inherent
dynamics of aquatic environment combined with a large variety of potential
obstacles presents considerable challenges to computer vision systems, leaving
robust obstacle detection an open research problem.

In this talk I will overview our work in the ViCoS laboratory
(https://vicos.si/research/autonomous-boats/) on camera-based obstacle detection
for USVs and the datasets we have created to facilitate the research in the USV
obstacle detection.
Responsible person: Petr Pošík