Ship Detection and Fine-Grained Recognition in Large-Format Remote Sensing Images Based on Convolutional Neural Network
Jingrun Li, Jinwen Tian, Peng Gao, Linfeng Li
Abstract
Ship detection and fine-grained recognition in large-format remote sensing image are an important research direction in the field of remote sensing image detection. But less research has been done in this area. Aiming at this problem, this paper constructs a large-format remote sensing image ship target dataset with ship category information, and proposes a background filtering network and a ship fine-grained classification network. The background filtering network is used to quickly filter out the background area, and the ship fine-grained classification network is used to detect ship targets and distinguish ship categories. Compared with the previous method, the method proposed in this paper can significantly improve the efficiency of ship target detection in large-format remote sensing images, while also improving the detection accuracy.