Unmanned Surface Vehicles

Low-end small unmanned surface vehicles (USV) are higly agile machines ideal for patrolling coastal waters. Such vehicles are typically used in perimeter surveillance, in which the USV travels along a pre-planned path. To quickly and efficiently respond to the challenges from highly dynamic environment, the USV requires an onboard logic to observe the surrounding, detect potentially dangerous situations, and apply proper route modifications. This page is a collection of algorithms and approaches that we have developed for such machines.

ViAMaRo (Vision for autonomous marine robots)

Modd thumb.png
The project primary goal is to develop functionalities required for robust autonomous navigation of USVs in uncontrolled environments, primarily relying on the captured visual information. The project focuses on obstacle detection using monocular and stereo systems, development of efficient visual tracking algorithms for marine environments and environment representation through sensor fusion.

A PKP student project

A six month student project funded by Slovenian initiative "Creative approach to practical knowledge". The students have been developing several computer vision algorithms for enabling autonomous navigation in a USV built by Harpha Sea Koper, while working as a team, distributing administration work, jointly writing reports, presentations and papers. This gave the students an opportunity to gain practical engineering skills as well as team-work competences.


Ssm thumb.png
This is a Matlab demo code for the semantic segmentation model for obstacle image map estimation for unmanned surface vehicles. The demo requires downloading the MOD dataset and has pretrained hiperparameters on the MOD dataset.
Modd thumb.png
This dataset contains marine videos, captured by unmanned surface vehicle (USV). The challenge, posed by this dataset, is to segment each image into three natural regions: the sky, the shore and the sea, and furthermore, detect obstacles in the sea area.
Stereo recalibration.jpg
This dataset contains image pairs and reference calibrations that can be used for developing autocalibration methods for stereo camera systems.

Relevant publications