Marine Event Vision: Harnessing Event Cameras For Robust Object Detection In Marine Scenarios

Nenyi Kweku Nkensen Dadson, Corina Barbalata; Proceedings of the Winter Conference on Applications of Computer Vision (WACV) Workshops, 2025, pp. 1520-1529

Automated object detection in marine environments presents unique challenges due to factors such as water turbidity variable lighting natural camouflage dynamic object movements sensor limitations noise and environmental influences like currents and biofouling. This paper addresses these issues by introducing a novel approach for detecting moving objects in marine settings leveraging event-based cameras and an event-driven Generalized Hough Transform (GHT) within a template-matching framework enhanced by a clustering algorithm. The approach is validated through qualitative results demonstrating object detection in the water column and on the surface as well as quantitative analysis of moving objects. The results highlight the robustness and versatility of the method extending its applicability beyond marine environments.