Convolutional neural networks for ship type recognition

被引：17

作者：

Rainey, Katie ^{[1
]}

Reeder, John D. ^{[1
]}

Corelli, Alexander G. ^{[1
]}

机构：

[1] Space & Naval Warfare Syst Ctr Pacific, 53560 Hull St, San Diego, CA 92152 USA

来源：

AUTOMATIC TARGET RECOGNITION XXVI | 2016年 / 9844卷

关键词：

Deep Learning; Image Recognition; Neural Networks; Satellite Imagery;

D O I：

10.1117/12.2229366

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

Algorithms to automatically recognize ship type from satellite imagery are desired for numerous maritime applications. This task is difficult, and example imagery accurately labeled with ship type is hard to obtain. Convolutional neural networks (CNNs) have shown promise in image recognition settings, but many of these applications rely on the availability of thousands of example images for training. This work attempts to understand for which types of ship recognition tasks CNNs might be well suited. We report the results of baseline experiments applying a CNN to several ship type classification tasks, and discuss many of the considerations that must be made in approaching this problem.

引用

页数：11