Towards a fixed-gear AIS trajectory differentiation

Abstract

The increasing digital traces of fishing fleets nowadays available allow for automatized observation of the oceans, a vulnerable space which could hardly be monitored or governed previously. Data streams from satellite base communication systems are being used for a variety of applications such as collision avoidance, route optimization, and monitoring of illegal activities. Classification of fishing vessels according to the specific fishing method is a developing branch towards assessing the compliance of fishing regulations. It is not feasible to verify reported fishing efforts, fishing quota or even fishing methods at sea via manual inspections. Classification of the fishing trajectories into trawlers, long-liners, pure-seine, and fixed-gear are well researched. However, the distinction between different fixed-gear fishing methods has not been studied so far. Therefore, this work proposes the vision to distinguish the previously undifferentiated fixed-gear fishing trajectories. We outline our vision, discuss the challenges of exploiting the small differences in the trajectories, and potential approaches towards realizing this vision.