A Novel Cargo Ship Detection and Directional Discrimination Method for Remote Sensing Image Based on Lightweight Network
Recently, cargo ship detection in remote sensing images based on deep learning is of great significance for cargo ship monitoring. However, the existing detection network is not only unable to realize autonomous operation on spaceborne platforms due to the limitation of computing and storage, but th...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-08-01
|
Series: | Journal of Marine Science and Engineering |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-1312/9/9/932 |
_version_ | 1797518669845102592 |
---|---|
author | Pan Wang Jianzhong Liu Yinbao Zhang Zhiyang Zhi Zhijian Cai Nannan Song |
author_facet | Pan Wang Jianzhong Liu Yinbao Zhang Zhiyang Zhi Zhijian Cai Nannan Song |
author_sort | Pan Wang |
collection | DOAJ |
description | Recently, cargo ship detection in remote sensing images based on deep learning is of great significance for cargo ship monitoring. However, the existing detection network is not only unable to realize autonomous operation on spaceborne platforms due to the limitation of computing and storage, but the detection result also lacks the directional information of the cargo ship. In order to address the above problems, we propose a novel cargo ship detection and directional discrimination method for remote sensing images based on a lightweight network. Specifically, we design an efficient and lightweight feature extraction network called the one-shot aggregation and depthwise separable network (OSADSNet), which is inspired by one-shot feature aggregation modules and depthwise separable convolutions. Additionally, we combine the RPN with the K-Mean++ algorithm to obtain the K-RPN, which can produce a more suitable region proposal for cargo ship detection. Furthermore, without introducing extra parameters, the directional discrimination of the cargo ship is transformed into a classification task, and the directional discrimination is completed when the detection task is completed. Experiments on a self-built remote sensing image cargo ship dataset indicate that our model can provide relatively accurate and fast detection for cargo ships (<i>mAP</i> of 91.96% and prediction time of 46 ms per image) and discriminate the directions (north, east, south, and west) of cargo ships, with fewer parameters (model size of 110 MB), which is more suitable for autonomous operation on spaceborne platforms. Therefore, the proposed method can meet the needs of cargo ship detection and directional discrimination in remote sensing images on spaceborne platforms. |
first_indexed | 2024-03-10T07:32:59Z |
format | Article |
id | doaj.art-879a7e9095c54d6fb8ea0bad59678156 |
institution | Directory Open Access Journal |
issn | 2077-1312 |
language | English |
last_indexed | 2024-03-10T07:32:59Z |
publishDate | 2021-08-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Marine Science and Engineering |
spelling | doaj.art-879a7e9095c54d6fb8ea0bad596781562023-11-22T13:45:33ZengMDPI AGJournal of Marine Science and Engineering2077-13122021-08-019993210.3390/jmse9090932A Novel Cargo Ship Detection and Directional Discrimination Method for Remote Sensing Image Based on Lightweight NetworkPan Wang0Jianzhong Liu1Yinbao Zhang2Zhiyang Zhi3Zhijian Cai4Nannan Song5School of Geoscience and Technology, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Geoscience and Technology, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Geoscience and Technology, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Geoscience and Technology, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Geoscience and Technology, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Geoscience and Technology, Zhengzhou University, Zhengzhou 450001, ChinaRecently, cargo ship detection in remote sensing images based on deep learning is of great significance for cargo ship monitoring. However, the existing detection network is not only unable to realize autonomous operation on spaceborne platforms due to the limitation of computing and storage, but the detection result also lacks the directional information of the cargo ship. In order to address the above problems, we propose a novel cargo ship detection and directional discrimination method for remote sensing images based on a lightweight network. Specifically, we design an efficient and lightweight feature extraction network called the one-shot aggregation and depthwise separable network (OSADSNet), which is inspired by one-shot feature aggregation modules and depthwise separable convolutions. Additionally, we combine the RPN with the K-Mean++ algorithm to obtain the K-RPN, which can produce a more suitable region proposal for cargo ship detection. Furthermore, without introducing extra parameters, the directional discrimination of the cargo ship is transformed into a classification task, and the directional discrimination is completed when the detection task is completed. Experiments on a self-built remote sensing image cargo ship dataset indicate that our model can provide relatively accurate and fast detection for cargo ships (<i>mAP</i> of 91.96% and prediction time of 46 ms per image) and discriminate the directions (north, east, south, and west) of cargo ships, with fewer parameters (model size of 110 MB), which is more suitable for autonomous operation on spaceborne platforms. Therefore, the proposed method can meet the needs of cargo ship detection and directional discrimination in remote sensing images on spaceborne platforms.https://www.mdpi.com/2077-1312/9/9/932deep learningremote sensing imagecargo shipdirectional discriminationfaster-RCNNlightweight |
spellingShingle | Pan Wang Jianzhong Liu Yinbao Zhang Zhiyang Zhi Zhijian Cai Nannan Song A Novel Cargo Ship Detection and Directional Discrimination Method for Remote Sensing Image Based on Lightweight Network Journal of Marine Science and Engineering deep learning remote sensing image cargo ship directional discrimination faster-RCNN lightweight |
title | A Novel Cargo Ship Detection and Directional Discrimination Method for Remote Sensing Image Based on Lightweight Network |
title_full | A Novel Cargo Ship Detection and Directional Discrimination Method for Remote Sensing Image Based on Lightweight Network |
title_fullStr | A Novel Cargo Ship Detection and Directional Discrimination Method for Remote Sensing Image Based on Lightweight Network |
title_full_unstemmed | A Novel Cargo Ship Detection and Directional Discrimination Method for Remote Sensing Image Based on Lightweight Network |
title_short | A Novel Cargo Ship Detection and Directional Discrimination Method for Remote Sensing Image Based on Lightweight Network |
title_sort | novel cargo ship detection and directional discrimination method for remote sensing image based on lightweight network |
topic | deep learning remote sensing image cargo ship directional discrimination faster-RCNN lightweight |
url | https://www.mdpi.com/2077-1312/9/9/932 |
work_keys_str_mv | AT panwang anovelcargoshipdetectionanddirectionaldiscriminationmethodforremotesensingimagebasedonlightweightnetwork AT jianzhongliu anovelcargoshipdetectionanddirectionaldiscriminationmethodforremotesensingimagebasedonlightweightnetwork AT yinbaozhang anovelcargoshipdetectionanddirectionaldiscriminationmethodforremotesensingimagebasedonlightweightnetwork AT zhiyangzhi anovelcargoshipdetectionanddirectionaldiscriminationmethodforremotesensingimagebasedonlightweightnetwork AT zhijiancai anovelcargoshipdetectionanddirectionaldiscriminationmethodforremotesensingimagebasedonlightweightnetwork AT nannansong anovelcargoshipdetectionanddirectionaldiscriminationmethodforremotesensingimagebasedonlightweightnetwork AT panwang novelcargoshipdetectionanddirectionaldiscriminationmethodforremotesensingimagebasedonlightweightnetwork AT jianzhongliu novelcargoshipdetectionanddirectionaldiscriminationmethodforremotesensingimagebasedonlightweightnetwork AT yinbaozhang novelcargoshipdetectionanddirectionaldiscriminationmethodforremotesensingimagebasedonlightweightnetwork AT zhiyangzhi novelcargoshipdetectionanddirectionaldiscriminationmethodforremotesensingimagebasedonlightweightnetwork AT zhijiancai novelcargoshipdetectionanddirectionaldiscriminationmethodforremotesensingimagebasedonlightweightnetwork AT nannansong novelcargoshipdetectionanddirectionaldiscriminationmethodforremotesensingimagebasedonlightweightnetwork |