Ship Detection in Spaceborne Optical Image With SVD Networks

TLDR

Automatic ship detection in spaceborne optical images is challenging due to cloud and wave interference, difficulty detecting inshore and offshore vessels, and high computational costs. The study proposes SVDNet, a fast, robust, and compact ship detection method for spaceborne optical imagery. SVDNet combines convolutional neural networks with a singular value decomposition algorithm to adaptively learn features from remote sensing images, and is evaluated on GaoFen‑1 and Venezuelan satellite data. Experiments demonstrate that SVDNet achieves robust detection and efficient runtime, effectively overcoming cloud, wave, and computational obstacles.

Abstract

Automatic ship detection on spaceborne optical images is a challenging task, which has attracted wide attention due to its extensive potential applications in maritime security and traffic control. Although some optical image ship detection methods have been proposed in recent years, there are still three obstacles in this task: 1) the inference of clouds and strong waves; 2) difficulties in detecting both inshore and offshore ships; and 3) high computational expenses. In this paper, we propose a novel ship detection method called SVD Networks (SVDNet), which is fast, robust, and structurally compact. SVDNet is designed based on the recent popular convolutional neural networks and the singular value decompensation algorithm. It provides a simple but efficient way to adaptively learn features from remote sensing images. We evaluate our method on some spaceborne optical images of GaoFen-1 and Venezuelan Remote Sensing Satellites. The experimental results demonstrate that our method achieves high detection robustness and a desirable time performance in response to all of the above three problems.