Intelligent Ship Detection in Remote Sensing Images Based on Multi-Layer Convolutional Feature Fusion
Intelligent detection and recognition of ships from high-resolution remote sensing images is an extraordinarily useful task in civil and military reconnaissance. It is difficult to detect ships with high precision because various disturbances are present in the sea such as clouds, mist, islands, coa...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-10-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/12/20/3316 |
_version_ | 1797551301293244416 |
---|---|
author | Yulian Zhang Lihong Guo Zengfa Wang Yang Yu Xinwei Liu Fang Xu |
author_facet | Yulian Zhang Lihong Guo Zengfa Wang Yang Yu Xinwei Liu Fang Xu |
author_sort | Yulian Zhang |
collection | DOAJ |
description | Intelligent detection and recognition of ships from high-resolution remote sensing images is an extraordinarily useful task in civil and military reconnaissance. It is difficult to detect ships with high precision because various disturbances are present in the sea such as clouds, mist, islands, coastlines, ripples, and so on. To solve this problem, we propose a novel ship detection network based on multi-layer convolutional feature fusion (CFF-SDN). Our ship detection network consists of three parts. Firstly, the convolutional feature extraction network is used to extract ship features of different levels. Residual connection is introduced so that the model can be designed very deeply, and it is easy to train and converge. Secondly, the proposed network fuses fine-grained features from shallow layers with semantic features from deep layers, which is beneficial for detecting ship targets with different sizes. At the same time, it is helpful to improve the localization accuracy and detection accuracy of small objects. Finally, multiple fused feature maps are used for classification and regression, which can adapt to ships of multiple scales. Since the CFF-SDN model uses a pruning strategy, the detection speed is greatly improved. In the experiment, we create a dataset for ship detection in remote sensing images (DSDR), including actual satellite images from Google Earth and aerial images from electro-optical pod. The DSDR dataset contains not only visible light images, but also infrared images. To improve the robustness to various sea scenes, images under different scales, perspectives and illumination are obtained through data augmentation or affine transformation methods. To reduce the influence of atmospheric absorption and scattering, a dark channel prior is adopted to solve atmospheric correction on the sea scenes. Moreover, soft non-maximum suppression (NMS) is introduced to increase the recall rate for densely arranged ships. In addition, better detection performance is observed in comparison with the existing models in terms of precision rate and recall rate. The experimental results show that the proposed detection model can achieve the superior performance of ship detection in optical remote sensing image. |
first_indexed | 2024-03-10T15:42:36Z |
format | Article |
id | doaj.art-a189389a7e0342c1afa87e8ae5a92b50 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-10T15:42:36Z |
publishDate | 2020-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-a189389a7e0342c1afa87e8ae5a92b502023-11-20T16:44:19ZengMDPI AGRemote Sensing2072-42922020-10-011220331610.3390/rs12203316Intelligent Ship Detection in Remote Sensing Images Based on Multi-Layer Convolutional Feature FusionYulian Zhang0Lihong Guo1Zengfa Wang2Yang Yu3Xinwei Liu4Fang Xu5Key Laboratory of Airborne Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaKey Laboratory of Airborne Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaKey Laboratory of Airborne Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaKey Laboratory of Airborne Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaKey Laboratory of Airborne Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaKey Laboratory of Airborne Optical Imaging and Measurement, Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, ChinaIntelligent detection and recognition of ships from high-resolution remote sensing images is an extraordinarily useful task in civil and military reconnaissance. It is difficult to detect ships with high precision because various disturbances are present in the sea such as clouds, mist, islands, coastlines, ripples, and so on. To solve this problem, we propose a novel ship detection network based on multi-layer convolutional feature fusion (CFF-SDN). Our ship detection network consists of three parts. Firstly, the convolutional feature extraction network is used to extract ship features of different levels. Residual connection is introduced so that the model can be designed very deeply, and it is easy to train and converge. Secondly, the proposed network fuses fine-grained features from shallow layers with semantic features from deep layers, which is beneficial for detecting ship targets with different sizes. At the same time, it is helpful to improve the localization accuracy and detection accuracy of small objects. Finally, multiple fused feature maps are used for classification and regression, which can adapt to ships of multiple scales. Since the CFF-SDN model uses a pruning strategy, the detection speed is greatly improved. In the experiment, we create a dataset for ship detection in remote sensing images (DSDR), including actual satellite images from Google Earth and aerial images from electro-optical pod. The DSDR dataset contains not only visible light images, but also infrared images. To improve the robustness to various sea scenes, images under different scales, perspectives and illumination are obtained through data augmentation or affine transformation methods. To reduce the influence of atmospheric absorption and scattering, a dark channel prior is adopted to solve atmospheric correction on the sea scenes. Moreover, soft non-maximum suppression (NMS) is introduced to increase the recall rate for densely arranged ships. In addition, better detection performance is observed in comparison with the existing models in terms of precision rate and recall rate. The experimental results show that the proposed detection model can achieve the superior performance of ship detection in optical remote sensing image.https://www.mdpi.com/2072-4292/12/20/3316remote sensing imagesship detectionfeature fusionaffine transformation |
spellingShingle | Yulian Zhang Lihong Guo Zengfa Wang Yang Yu Xinwei Liu Fang Xu Intelligent Ship Detection in Remote Sensing Images Based on Multi-Layer Convolutional Feature Fusion Remote Sensing remote sensing images ship detection feature fusion affine transformation |
title | Intelligent Ship Detection in Remote Sensing Images Based on Multi-Layer Convolutional Feature Fusion |
title_full | Intelligent Ship Detection in Remote Sensing Images Based on Multi-Layer Convolutional Feature Fusion |
title_fullStr | Intelligent Ship Detection in Remote Sensing Images Based on Multi-Layer Convolutional Feature Fusion |
title_full_unstemmed | Intelligent Ship Detection in Remote Sensing Images Based on Multi-Layer Convolutional Feature Fusion |
title_short | Intelligent Ship Detection in Remote Sensing Images Based on Multi-Layer Convolutional Feature Fusion |
title_sort | intelligent ship detection in remote sensing images based on multi layer convolutional feature fusion |
topic | remote sensing images ship detection feature fusion affine transformation |
url | https://www.mdpi.com/2072-4292/12/20/3316 |
work_keys_str_mv | AT yulianzhang intelligentshipdetectioninremotesensingimagesbasedonmultilayerconvolutionalfeaturefusion AT lihongguo intelligentshipdetectioninremotesensingimagesbasedonmultilayerconvolutionalfeaturefusion AT zengfawang intelligentshipdetectioninremotesensingimagesbasedonmultilayerconvolutionalfeaturefusion AT yangyu intelligentshipdetectioninremotesensingimagesbasedonmultilayerconvolutionalfeaturefusion AT xinweiliu intelligentshipdetectioninremotesensingimagesbasedonmultilayerconvolutionalfeaturefusion AT fangxu intelligentshipdetectioninremotesensingimagesbasedonmultilayerconvolutionalfeaturefusion |