Cross-sensor vision system for maritime object detection

Frontiers in Marine Science

Marine Science

Steven J. Simske¹  Vinay Mohan¹ 

[1] Department of Systems Engineering, Colorado State University, Fort Collins, CO, United States;

关键词: deep learning;    vessel detection system;    maritime vessel;    optical satellite system;    object detection;    convolutional neural network;    synthetic aperture radar;   

DOI  :  10.3389/fmars.2023.1112955

 received in 2022-12-06, accepted in 2023-02-13,  发布年份 2023

来源: Frontiers

【 摘 要 】

Accurate and automated detection of maritime vessels present in aerial images is a considerable challenge. While significant progress has been made in recent years by adopting neural network architectures in detection and classification systems, these systems are usually designed specific to a sensor, dataset or location. In this paper, we present a system which uses multiple sensors and a convolutional neural network (CNN) architecture to test cross-sensor object detection resiliency. The system is composed of five main subsystems: Image Capture, Image Processing, Model Creation, Object-of-Interest Detection and System Evaluation. We show that the system has a high degree of cross-sensor vessel detection accuracy, paving the way for the design of similar systems which could prove robust across applications, sensors, ship types and ship sizes.

【 授权许可】

Unknown   
Copyright © 2023 Mohan and Simske