Fine-Grained Ship Detection in High-Resolution Satellite Images With Shape-Aware Feature Learning
Fine-grained ship detection is an important task in high-resolution satellite remote sensing applications. However, large aspect ratios and severe category imbalance make fine-grained ship detection a challenging problem. Current methods usually extract square-like features that do not work well to...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10035980/ |
| _version_ | 1797902288300277760 |
|---|---|
| author | Bo Guo Ruixiang Zhang Haowen Guo Wen Yang Huai Yu Peng Zhang Tongyuan Zou |
| author_facet | Bo Guo Ruixiang Zhang Haowen Guo Wen Yang Huai Yu Peng Zhang Tongyuan Zou |
| author_sort | Bo Guo |
| collection | DOAJ |
| description | Fine-grained ship detection is an important task in high-resolution satellite remote sensing applications. However, large aspect ratios and severe category imbalance make fine-grained ship detection a challenging problem. Current methods usually extract square-like features that do not work well to detect ships with large aspect ratios, and the misalignments in feature representation will severely degrade the performance of ship localization and classification. To tackle this, we propose a shape-aware feature learning method to mitigate the misalignments during feature extraction. Furthermore, for the issue of category imbalance, we design a shape-aware instance switching to balance the quantity distribution of ships in different categories, which can greatly improve the network's learning ability for rare instances. To verify the effectiveness of the proposed method, we contribute a multicategory ship detection dataset (MCSD) that contains 4000 images carefully labeled with oriented bounding boxes, including 16 types of ship objects and nearly 18 000 instances. We conduct experiments on our MCSD and ShipRSImageNet, and extensive experimental results demonstrate the superiority of the proposed method over several state-of-the-art methods. |
| first_indexed | 2024-04-10T09:15:18Z |
| format | Article |
| id | doaj.art-64d8add0707c43a4bad70334ab3d3399 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-04-10T09:15:18Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-64d8add0707c43a4bad70334ab3d33992023-02-21T00:00:19ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352023-01-01161914192610.1109/JSTARS.2023.324196910035980Fine-Grained Ship Detection in High-Resolution Satellite Images With Shape-Aware Feature LearningBo Guo0https://orcid.org/0000-0002-7383-4992Ruixiang Zhang1https://orcid.org/0000-0003-0704-2484Haowen Guo2https://orcid.org/0000-0003-2328-642XWen Yang3https://orcid.org/0000-0002-3263-8768Huai Yu4https://orcid.org/0000-0001-6043-3412Peng Zhang5Tongyuan Zou6School of Electronic Information, Wuhan University, Wuhan, ChinaSchool of Electronic Information, Wuhan University, Wuhan, ChinaSchool of Electronic Information, Wuhan University, Wuhan, ChinaSchool of Electronic Information, Wuhan University, Wuhan, ChinaSchool of Electronic Information, Wuhan University, Wuhan, ChinaSpace Star Technology Co., Ltd. (SST), Beijing, ChinaSpace Star Technology Co., Ltd. (SST), Beijing, ChinaFine-grained ship detection is an important task in high-resolution satellite remote sensing applications. However, large aspect ratios and severe category imbalance make fine-grained ship detection a challenging problem. Current methods usually extract square-like features that do not work well to detect ships with large aspect ratios, and the misalignments in feature representation will severely degrade the performance of ship localization and classification. To tackle this, we propose a shape-aware feature learning method to mitigate the misalignments during feature extraction. Furthermore, for the issue of category imbalance, we design a shape-aware instance switching to balance the quantity distribution of ships in different categories, which can greatly improve the network's learning ability for rare instances. To verify the effectiveness of the proposed method, we contribute a multicategory ship detection dataset (MCSD) that contains 4000 images carefully labeled with oriented bounding boxes, including 16 types of ship objects and nearly 18 000 instances. We conduct experiments on our MCSD and ShipRSImageNet, and extensive experimental results demonstrate the superiority of the proposed method over several state-of-the-art methods.https://ieeexplore.ieee.org/document/10035980/Convolutional networkfeature learningoriented ship detectionsatellite image |
| spellingShingle | Bo Guo Ruixiang Zhang Haowen Guo Wen Yang Huai Yu Peng Zhang Tongyuan Zou Fine-Grained Ship Detection in High-Resolution Satellite Images With Shape-Aware Feature Learning IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Convolutional network feature learning oriented ship detection satellite image |
| title | Fine-Grained Ship Detection in High-Resolution Satellite Images With Shape-Aware Feature Learning |
| title_full | Fine-Grained Ship Detection in High-Resolution Satellite Images With Shape-Aware Feature Learning |
| title_fullStr | Fine-Grained Ship Detection in High-Resolution Satellite Images With Shape-Aware Feature Learning |
| title_full_unstemmed | Fine-Grained Ship Detection in High-Resolution Satellite Images With Shape-Aware Feature Learning |
| title_short | Fine-Grained Ship Detection in High-Resolution Satellite Images With Shape-Aware Feature Learning |
| title_sort | fine grained ship detection in high resolution satellite images with shape aware feature learning |
| topic | Convolutional network feature learning oriented ship detection satellite image |
| url | https://ieeexplore.ieee.org/document/10035980/ |
| work_keys_str_mv | AT boguo finegrainedshipdetectioninhighresolutionsatelliteimageswithshapeawarefeaturelearning AT ruixiangzhang finegrainedshipdetectioninhighresolutionsatelliteimageswithshapeawarefeaturelearning AT haowenguo finegrainedshipdetectioninhighresolutionsatelliteimageswithshapeawarefeaturelearning AT wenyang finegrainedshipdetectioninhighresolutionsatelliteimageswithshapeawarefeaturelearning AT huaiyu finegrainedshipdetectioninhighresolutionsatelliteimageswithshapeawarefeaturelearning AT pengzhang finegrainedshipdetectioninhighresolutionsatelliteimageswithshapeawarefeaturelearning AT tongyuanzou finegrainedshipdetectioninhighresolutionsatelliteimageswithshapeawarefeaturelearning |