Efficient Airport Detection Using Region-based Fully Convolutional Neural Networks

被引：0

作者：

Xin, Peng ^{[1
]}

Xu, Yuelei ^{[1
]}

Zhang, Xulei ^{[2
]}

Ma, Shiping ^{[1
]}

Li, Shuai ^{[1
]}

Lv, Chao ^{[1
]}

机构：

[1] Air Force Engn Univ, Inst Aeronaut & Astronaut Engn, Xian 710038, Shaanxi, Peoples R China

[2] Training Base Xinjiang Border Def Corps, Xinjiang 831100, Changji Hui Aut, Peoples R China

来源：

NINTH INTERNATIONAL CONFERENCE ON GRAPHIC AND IMAGE PROCESSING (ICGIP 2017) | 2018年 / 10615卷

基金：

中国国家自然科学基金;

关键词：

Airport detection; region-based fully convolutional neural networks; alternating optimization; IMAGES;

D O I：

10.1117/12.2302952

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

This paper presents a model for airport detection using region-based fully convolutional neural networks. To achieve fast detection with high accuracy, we shared the conv layers between the region proposal procedure and the airport detection procedure and used graphics processing units (GPUs) to speed up the training and testing time. For lack of labeled data, we transferred the convolutional layers of ZF net pretrained by ImageNet to initialize the shared convolutional layers, then we retrained the model using the alternating optimization training strategy. The proposed model has been tested on an airport dataset consisting of 600 images. Experiments show that the proposed method can distinguish airports in our dataset from similar background scenes almost real-time with high accuracy, which is much better than traditional methods.

引用

页数：7