Arbitrary-Oriented Inshore Ship Detection based on Multi-Scale Feature Fusion and Contextual Pooling on Rotation Region Proposals
Inshore ship detection plays an important role in many civilian and military applications. The complex land environment and the diversity of target sizes and distributions make it still challenging for us to obtain accurate detection results. In order to achieve precise localization and suppress fal...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-01-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/2/339 |
id |
doaj-d2758d7286e8418690d21221c76d17d8 |
---|---|
record_format |
Article |
spelling |
doaj-d2758d7286e8418690d21221c76d17d82020-11-25T02:33:56ZengMDPI AGRemote Sensing2072-42922020-01-0112233910.3390/rs12020339rs12020339Arbitrary-Oriented Inshore Ship Detection based on Multi-Scale Feature Fusion and Contextual Pooling on Rotation Region ProposalsTian Tian0Zhihong Pan1Xiangyu Tan2Zhengquan Chu3Key Laboratory of Geological Survey and Evaluation of Ministry of Education, School of Computer Science, China University of Geosciences, Wuhan 430074, ChinaSchool of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, ChinaKey Laboratory of Geological Survey and Evaluation of Ministry of Education, School of Computer Science, China University of Geosciences, Wuhan 430074, ChinaKey Laboratory of Geological Survey and Evaluation of Ministry of Education, School of Computer Science, China University of Geosciences, Wuhan 430074, ChinaInshore ship detection plays an important role in many civilian and military applications. The complex land environment and the diversity of target sizes and distributions make it still challenging for us to obtain accurate detection results. In order to achieve precise localization and suppress false alarms, in this paper, we propose a framework which integrates a multi-scale feature fusion network, rotation region proposal network and contextual pooling together. Specifically, in order to describe ships of various sizes, different convolutional layers are fused to obtain multi-scale features based on the baseline feature extraction network. Then, for the purpose of accurate target localization and arbitrary-oriented ship detection, a rotation region proposal network and skew non-maximum suppression are employed. Finally, on account of the disadvantages that the employment of a rotation bounding box usually causes more false alarms, we implement inclined context feature pooling on rotation region proposals. A dataset including port images collected from Google Earth and a public ship dataset HRSC2016 are employed in our experiments to test the proposed method. Experimental results of model analysis validate the contribution of each module mentioned above, and contrast results show that our proposed pipeline is able to achieve state-of-the-art performance of arbitrary-oriented inshore ship detection.https://www.mdpi.com/2072-4292/12/2/339inshore ship detectionmulti-scale feature fusionrotation regionregion proposal networkcontext feature pooling |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Tian Tian Zhihong Pan Xiangyu Tan Zhengquan Chu |
spellingShingle |
Tian Tian Zhihong Pan Xiangyu Tan Zhengquan Chu Arbitrary-Oriented Inshore Ship Detection based on Multi-Scale Feature Fusion and Contextual Pooling on Rotation Region Proposals Remote Sensing inshore ship detection multi-scale feature fusion rotation region region proposal network context feature pooling |
author_facet |
Tian Tian Zhihong Pan Xiangyu Tan Zhengquan Chu |
author_sort |
Tian Tian |
title |
Arbitrary-Oriented Inshore Ship Detection based on Multi-Scale Feature Fusion and Contextual Pooling on Rotation Region Proposals |
title_short |
Arbitrary-Oriented Inshore Ship Detection based on Multi-Scale Feature Fusion and Contextual Pooling on Rotation Region Proposals |
title_full |
Arbitrary-Oriented Inshore Ship Detection based on Multi-Scale Feature Fusion and Contextual Pooling on Rotation Region Proposals |
title_fullStr |
Arbitrary-Oriented Inshore Ship Detection based on Multi-Scale Feature Fusion and Contextual Pooling on Rotation Region Proposals |
title_full_unstemmed |
Arbitrary-Oriented Inshore Ship Detection based on Multi-Scale Feature Fusion and Contextual Pooling on Rotation Region Proposals |
title_sort |
arbitrary-oriented inshore ship detection based on multi-scale feature fusion and contextual pooling on rotation region proposals |
publisher |
MDPI AG |
series |
Remote Sensing |
issn |
2072-4292 |
publishDate |
2020-01-01 |
description |
Inshore ship detection plays an important role in many civilian and military applications. The complex land environment and the diversity of target sizes and distributions make it still challenging for us to obtain accurate detection results. In order to achieve precise localization and suppress false alarms, in this paper, we propose a framework which integrates a multi-scale feature fusion network, rotation region proposal network and contextual pooling together. Specifically, in order to describe ships of various sizes, different convolutional layers are fused to obtain multi-scale features based on the baseline feature extraction network. Then, for the purpose of accurate target localization and arbitrary-oriented ship detection, a rotation region proposal network and skew non-maximum suppression are employed. Finally, on account of the disadvantages that the employment of a rotation bounding box usually causes more false alarms, we implement inclined context feature pooling on rotation region proposals. A dataset including port images collected from Google Earth and a public ship dataset HRSC2016 are employed in our experiments to test the proposed method. Experimental results of model analysis validate the contribution of each module mentioned above, and contrast results show that our proposed pipeline is able to achieve state-of-the-art performance of arbitrary-oriented inshore ship detection. |
topic |
inshore ship detection multi-scale feature fusion rotation region region proposal network context feature pooling |
url |
https://www.mdpi.com/2072-4292/12/2/339 |
work_keys_str_mv |
AT tiantian arbitraryorientedinshoreshipdetectionbasedonmultiscalefeaturefusionandcontextualpoolingonrotationregionproposals AT zhihongpan arbitraryorientedinshoreshipdetectionbasedonmultiscalefeaturefusionandcontextualpoolingonrotationregionproposals AT xiangyutan arbitraryorientedinshoreshipdetectionbasedonmultiscalefeaturefusionandcontextualpoolingonrotationregionproposals AT zhengquanchu arbitraryorientedinshoreshipdetectionbasedonmultiscalefeaturefusionandcontextualpoolingonrotationregionproposals |
_version_ |
1724811422163009536 |