Work

Marine Event Vision: Harnessing Event Cameras for Robust Object Detection in Marine Scenarios

Year: 2025

Type: conference-paper

Abstract: 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 high-light the robustness and versatility of the method, extending its applicability beyond marine environments.

Source: IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)

DOI: 10.1109/wacvw65960.2025.00166

Authors: Nenyi Kweku Nkensen Dadson, Corina Barbalata

Institution: Louisiana State University

Language: English

Topic: Video Surveillance and Tracking Methods

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Life below water

Open Access status: green

Funder: National Science Foundation