R-CNN-Based Ship Detection from High Resolution Remote Sensing Imagery
Offshore and inland river ship detection has been studied on both synthetic aperture radar (SAR) and optical remote sensing imagery. However, the classic ship detection methods based on SAR images can cause a high false alarm ratio and be influenced by the sea surface model, especially on inland riv...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-03-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | http://www.mdpi.com/2072-4292/11/6/631 |
id |
doaj-801f005916d84e099207fee7cfba1586 |
---|---|
record_format |
Article |
spelling |
doaj-801f005916d84e099207fee7cfba15862020-11-25T02:44:54ZengMDPI AGRemote Sensing2072-42922019-03-0111663110.3390/rs11060631rs11060631R-CNN-Based Ship Detection from High Resolution Remote Sensing ImageryShaoming Zhang0Ruize Wu1Kunyuan Xu2Jianmei Wang3Weiwei Sun4College of Surveying, Mapping and Geo-Informatics, Tongji University, Shanghai 200092, ChinaCollege of Surveying, Mapping and Geo-Informatics, Tongji University, Shanghai 200092, ChinaCollege of Surveying, Mapping and Geo-Informatics, Tongji University, Shanghai 200092, ChinaCollege of Surveying, Mapping and Geo-Informatics, Tongji University, Shanghai 200092, ChinaDepartment of Geography and Spatial Information Techniques, Ningbo University, Ningbo 315211, Zhejiang, ChinaOffshore and inland river ship detection has been studied on both synthetic aperture radar (SAR) and optical remote sensing imagery. However, the classic ship detection methods based on SAR images can cause a high false alarm ratio and be influenced by the sea surface model, especially on inland rivers and in offshore areas. The classic detection methods based on optical images do not perform well on small and gathering ships. This paper adopts the idea of deep networks and presents a fast regional-based convolutional neural network (R-CNN) method to detect ships from high-resolution remote sensing imagery. First, we choose GaoFen-2 optical remote sensing images with a resolution of 1 m and preprocess the images with a support vector machine (SVM) to divide the large detection area into small regions of interest (ROI) that may contain ships. Then, we apply ship detection algorithms based on a region-based convolutional neural network (R-CNN) on ROI images. To improve the detection result of small and gathering ships, we adopt an effective target detection framework, Faster-RCNN, and improve the structure of its original convolutional neural network (CNN), VGG16, by using multiresolution convolutional features and performing ROI pooling on a larger feature map in a region proposal network (RPN). Finally, we compare the most effective classic ship detection method, the deformable part model (DPM), another two widely used target detection frameworks, the single shot multibox detector (SSD) and YOLOv2, the original VGG16-based Faster-RCNN, and our improved Faster-RCNN. Experimental results show that our improved Faster-RCNN method achieves a higher recall and accuracy for small ships and gathering ships. Therefore, it provides a very effective method for offshore and inland river ship detection based on high-resolution remote sensing imagery.http://www.mdpi.com/2072-4292/11/6/631ship detectionregional convolutional neural networkGaoFen-2 remote sensing imagesmall shipgathering ship |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Shaoming Zhang Ruize Wu Kunyuan Xu Jianmei Wang Weiwei Sun |
spellingShingle |
Shaoming Zhang Ruize Wu Kunyuan Xu Jianmei Wang Weiwei Sun R-CNN-Based Ship Detection from High Resolution Remote Sensing Imagery Remote Sensing ship detection regional convolutional neural network GaoFen-2 remote sensing image small ship gathering ship |
author_facet |
Shaoming Zhang Ruize Wu Kunyuan Xu Jianmei Wang Weiwei Sun |
author_sort |
Shaoming Zhang |
title |
R-CNN-Based Ship Detection from High Resolution Remote Sensing Imagery |
title_short |
R-CNN-Based Ship Detection from High Resolution Remote Sensing Imagery |
title_full |
R-CNN-Based Ship Detection from High Resolution Remote Sensing Imagery |
title_fullStr |
R-CNN-Based Ship Detection from High Resolution Remote Sensing Imagery |
title_full_unstemmed |
R-CNN-Based Ship Detection from High Resolution Remote Sensing Imagery |
title_sort |
r-cnn-based ship detection from high resolution remote sensing imagery |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2019-03-01 |
description |
Offshore and inland river ship detection has been studied on both synthetic aperture radar (SAR) and optical remote sensing imagery. However, the classic ship detection methods based on SAR images can cause a high false alarm ratio and be influenced by the sea surface model, especially on inland rivers and in offshore areas. The classic detection methods based on optical images do not perform well on small and gathering ships. This paper adopts the idea of deep networks and presents a fast regional-based convolutional neural network (R-CNN) method to detect ships from high-resolution remote sensing imagery. First, we choose GaoFen-2 optical remote sensing images with a resolution of 1 m and preprocess the images with a support vector machine (SVM) to divide the large detection area into small regions of interest (ROI) that may contain ships. Then, we apply ship detection algorithms based on a region-based convolutional neural network (R-CNN) on ROI images. To improve the detection result of small and gathering ships, we adopt an effective target detection framework, Faster-RCNN, and improve the structure of its original convolutional neural network (CNN), VGG16, by using multiresolution convolutional features and performing ROI pooling on a larger feature map in a region proposal network (RPN). Finally, we compare the most effective classic ship detection method, the deformable part model (DPM), another two widely used target detection frameworks, the single shot multibox detector (SSD) and YOLOv2, the original VGG16-based Faster-RCNN, and our improved Faster-RCNN. Experimental results show that our improved Faster-RCNN method achieves a higher recall and accuracy for small ships and gathering ships. Therefore, it provides a very effective method for offshore and inland river ship detection based on high-resolution remote sensing imagery. |
topic |
ship detection regional convolutional neural network GaoFen-2 remote sensing image small ship gathering ship |
url |
http://www.mdpi.com/2072-4292/11/6/631 |
work_keys_str_mv |
AT shaomingzhang rcnnbasedshipdetectionfromhighresolutionremotesensingimagery AT ruizewu rcnnbasedshipdetectionfromhighresolutionremotesensingimagery AT kunyuanxu rcnnbasedshipdetectionfromhighresolutionremotesensingimagery AT jianmeiwang rcnnbasedshipdetectionfromhighresolutionremotesensingimagery AT weiweisun rcnnbasedshipdetectionfromhighresolutionremotesensingimagery |
_version_ |
1724765287598784512 |