Ship Target Detection Algorithm Based on Improved Faster R-CNN
Ship target detection has urgent needs and broad application prospects in military and marine transportation. In order to improve the accuracy and efficiency of the ship target detection, an improved Faster R-CNN (Faster Region-based Convolutional Neural Network) algorithm of ship target detection i...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-08-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/8/9/959 |
id |
doaj-f1bc4cfb07004ee3bb54b959aeb9046c |
---|---|
record_format |
Article |
spelling |
doaj-f1bc4cfb07004ee3bb54b959aeb9046c2020-11-25T01:19:21ZengMDPI AGElectronics2079-92922019-08-018995910.3390/electronics8090959electronics8090959Ship Target Detection Algorithm Based on Improved Faster R-CNNLiang Qi0Bangyu Li1Liankai Chen2Wei Wang3Liang Dong4Xuan Jia5Jing Huang6Chengwei Ge7Ganmin Xue8Dong Wang9Ship Intelligent Manufacturing and Intelligent Ship Integrated Laboratory, School of Electronic Information, Jiangsu University of Science and Technology, 2 Mengxi Road, Zhenjiang 212000, ChinaInstitute of Automation, Chinese Academy of Sciences, 95 Zhongguancun East Road, Beijing 100190, ChinaShip Intelligent Manufacturing and Intelligent Ship Integrated Laboratory, School of Electronic Information, Jiangsu University of Science and Technology, 2 Mengxi Road, Zhenjiang 212000, ChinaShip Intelligent Manufacturing and Intelligent Ship Integrated Laboratory, School of Electronic Information, Jiangsu University of Science and Technology, 2 Mengxi Road, Zhenjiang 212000, ChinaShip Intelligent Manufacturing and Intelligent Ship Integrated Laboratory, School of Electronic Information, Jiangsu University of Science and Technology, 2 Mengxi Road, Zhenjiang 212000, ChinaShip Intelligent Manufacturing and Intelligent Ship Integrated Laboratory, School of Electronic Information, Jiangsu University of Science and Technology, 2 Mengxi Road, Zhenjiang 212000, ChinaShip Intelligent Manufacturing and Intelligent Ship Integrated Laboratory, School of Electronic Information, Jiangsu University of Science and Technology, 2 Mengxi Road, Zhenjiang 212000, ChinaShip Intelligent Manufacturing and Intelligent Ship Integrated Laboratory, School of Electronic Information, Jiangsu University of Science and Technology, 2 Mengxi Road, Zhenjiang 212000, ChinaShip Intelligent Manufacturing and Intelligent Ship Integrated Laboratory, School of Electronic Information, Jiangsu University of Science and Technology, 2 Mengxi Road, Zhenjiang 212000, ChinaShip Intelligent Manufacturing and Intelligent Ship Integrated Laboratory, School of Electronic Information, Jiangsu University of Science and Technology, 2 Mengxi Road, Zhenjiang 212000, ChinaShip target detection has urgent needs and broad application prospects in military and marine transportation. In order to improve the accuracy and efficiency of the ship target detection, an improved Faster R-CNN (Faster Region-based Convolutional Neural Network) algorithm of ship target detection is proposed. In the proposed method, the image downscaling method is used to enhance the useful information of the ship image. The scene narrowing technique is used to construct the target regional positioning network and the Faster R-CNN convolutional neural network into a hierarchical narrowing network, aiming at reducing the target detection search scale and improving the computational speed of Faster R-CNN. Furthermore, deep cooperation between main network and subnet is realized to optimize network parameters after researching Faster R-CNN with subject narrowing function and selecting texture features and spatial difference features as narrowed sub-networks. The experimental results show that the proposed method can significantly shorten the detection time of the algorithm while improving the detection accuracy of Faster R-CNN algorithm.https://www.mdpi.com/2079-9292/8/9/959ship target detectionFaster R-CNNscene semantic narrowingtopic narrowing subnetwork |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Liang Qi Bangyu Li Liankai Chen Wei Wang Liang Dong Xuan Jia Jing Huang Chengwei Ge Ganmin Xue Dong Wang |
spellingShingle |
Liang Qi Bangyu Li Liankai Chen Wei Wang Liang Dong Xuan Jia Jing Huang Chengwei Ge Ganmin Xue Dong Wang Ship Target Detection Algorithm Based on Improved Faster R-CNN Electronics ship target detection Faster R-CNN scene semantic narrowing topic narrowing subnetwork |
author_facet |
Liang Qi Bangyu Li Liankai Chen Wei Wang Liang Dong Xuan Jia Jing Huang Chengwei Ge Ganmin Xue Dong Wang |
author_sort |
Liang Qi |
title |
Ship Target Detection Algorithm Based on Improved Faster R-CNN |
title_short |
Ship Target Detection Algorithm Based on Improved Faster R-CNN |
title_full |
Ship Target Detection Algorithm Based on Improved Faster R-CNN |
title_fullStr |
Ship Target Detection Algorithm Based on Improved Faster R-CNN |
title_full_unstemmed |
Ship Target Detection Algorithm Based on Improved Faster R-CNN |
title_sort |
ship target detection algorithm based on improved faster r-cnn |
publisher |
MDPI AG |
series |
Electronics |
issn |
2079-9292 |
publishDate |
2019-08-01 |
description |
Ship target detection has urgent needs and broad application prospects in military and marine transportation. In order to improve the accuracy and efficiency of the ship target detection, an improved Faster R-CNN (Faster Region-based Convolutional Neural Network) algorithm of ship target detection is proposed. In the proposed method, the image downscaling method is used to enhance the useful information of the ship image. The scene narrowing technique is used to construct the target regional positioning network and the Faster R-CNN convolutional neural network into a hierarchical narrowing network, aiming at reducing the target detection search scale and improving the computational speed of Faster R-CNN. Furthermore, deep cooperation between main network and subnet is realized to optimize network parameters after researching Faster R-CNN with subject narrowing function and selecting texture features and spatial difference features as narrowed sub-networks. The experimental results show that the proposed method can significantly shorten the detection time of the algorithm while improving the detection accuracy of Faster R-CNN algorithm. |
topic |
ship target detection Faster R-CNN scene semantic narrowing topic narrowing subnetwork |
url |
https://www.mdpi.com/2079-9292/8/9/959 |
work_keys_str_mv |
AT liangqi shiptargetdetectionalgorithmbasedonimprovedfasterrcnn AT bangyuli shiptargetdetectionalgorithmbasedonimprovedfasterrcnn AT liankaichen shiptargetdetectionalgorithmbasedonimprovedfasterrcnn AT weiwang shiptargetdetectionalgorithmbasedonimprovedfasterrcnn AT liangdong shiptargetdetectionalgorithmbasedonimprovedfasterrcnn AT xuanjia shiptargetdetectionalgorithmbasedonimprovedfasterrcnn AT jinghuang shiptargetdetectionalgorithmbasedonimprovedfasterrcnn AT chengweige shiptargetdetectionalgorithmbasedonimprovedfasterrcnn AT ganminxue shiptargetdetectionalgorithmbasedonimprovedfasterrcnn AT dongwang shiptargetdetectionalgorithmbasedonimprovedfasterrcnn |
_version_ |
1725138762184261632 |