Oriented Ship Detector for Remote Sensing Imagery Based on Pairwise Branch Detection Head and SAR Feature Enhancement
Recently, object detection in natural images has made a breakthrough, but it is still challenging in oriented ship detection for remote sensing imagery. Considering some limitations in this task, such as uncertain ship orientation, unspecific features for locating and classification in the complex o...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/9/2177 |
| _version_ | 1797503019571478528 |
|---|---|
| author | Bokun He Qingyi Zhang Ming Tong Chu He |
| author_facet | Bokun He Qingyi Zhang Ming Tong Chu He |
| author_sort | Bokun He |
| collection | DOAJ |
| description | Recently, object detection in natural images has made a breakthrough, but it is still challenging in oriented ship detection for remote sensing imagery. Considering some limitations in this task, such as uncertain ship orientation, unspecific features for locating and classification in the complex optical environment, and multiplicative speckle interference of synthetic aperture radar (SAR), we propose an oriented ship detector based on the pairwise branch detection head and adaptive SAR feature enhancement. The details are as follows: (1) Firstly, the ships with arbitrary directions are described with a rotated ground truth, and an oriented region proposal network (ORPN) is designed to study the transformation from the horizontal region of interest to the rotated region of interest. The ORPN effectively improved the quality of the candidate area while only introducing a few parameters. (2) In view of the existing algorithms that tend to perform classification and regression prediction on the same output feature, this paper proposes a pairwise detection head (PBH) to design parallel branches to decouple classification and locating tasks, so that each branch can learn more task-specific features. (3) Inspired by the ratio-of-average detector in traditional SAR image processing, the SAR edge enhancement (SEE) module is proposed, which adaptively enhances edge pixels, and the threshold of the edge is learned by the channel-shared adaptive thresholds block. Experiments were carried out on both optical and SAR datasets. In the optical dataset, PBH combined with ORPN improved recall by 5.03%, and in the SAR dataset, the overall method achieved a maximum F1 score improvement of 6.07%; these results imply the validity of our method. |
| first_indexed | 2024-03-10T03:44:31Z |
| format | Article |
| id | doaj.art-ff5e835a0b8b4c0781510b31b1c2c6e2 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T03:44:31Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-ff5e835a0b8b4c0781510b31b1c2c6e22023-11-23T09:11:48ZengMDPI AGRemote Sensing2072-42922022-05-01149217710.3390/rs14092177Oriented Ship Detector for Remote Sensing Imagery Based on Pairwise Branch Detection Head and SAR Feature EnhancementBokun He0Qingyi Zhang1Ming Tong2Chu He3Electronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaElectronic Information School, Wuhan University, Wuhan 430072, ChinaRecently, object detection in natural images has made a breakthrough, but it is still challenging in oriented ship detection for remote sensing imagery. Considering some limitations in this task, such as uncertain ship orientation, unspecific features for locating and classification in the complex optical environment, and multiplicative speckle interference of synthetic aperture radar (SAR), we propose an oriented ship detector based on the pairwise branch detection head and adaptive SAR feature enhancement. The details are as follows: (1) Firstly, the ships with arbitrary directions are described with a rotated ground truth, and an oriented region proposal network (ORPN) is designed to study the transformation from the horizontal region of interest to the rotated region of interest. The ORPN effectively improved the quality of the candidate area while only introducing a few parameters. (2) In view of the existing algorithms that tend to perform classification and regression prediction on the same output feature, this paper proposes a pairwise detection head (PBH) to design parallel branches to decouple classification and locating tasks, so that each branch can learn more task-specific features. (3) Inspired by the ratio-of-average detector in traditional SAR image processing, the SAR edge enhancement (SEE) module is proposed, which adaptively enhances edge pixels, and the threshold of the edge is learned by the channel-shared adaptive thresholds block. Experiments were carried out on both optical and SAR datasets. In the optical dataset, PBH combined with ORPN improved recall by 5.03%, and in the SAR dataset, the overall method achieved a maximum F1 score improvement of 6.07%; these results imply the validity of our method.https://www.mdpi.com/2072-4292/14/9/2177ship detectiondeep learningremote sensing imagerySAR feature enhancementpairwise head |
| spellingShingle | Bokun He Qingyi Zhang Ming Tong Chu He Oriented Ship Detector for Remote Sensing Imagery Based on Pairwise Branch Detection Head and SAR Feature Enhancement Remote Sensing ship detection deep learning remote sensing imagery SAR feature enhancement pairwise head |
| title | Oriented Ship Detector for Remote Sensing Imagery Based on Pairwise Branch Detection Head and SAR Feature Enhancement |
| title_full | Oriented Ship Detector for Remote Sensing Imagery Based on Pairwise Branch Detection Head and SAR Feature Enhancement |
| title_fullStr | Oriented Ship Detector for Remote Sensing Imagery Based on Pairwise Branch Detection Head and SAR Feature Enhancement |
| title_full_unstemmed | Oriented Ship Detector for Remote Sensing Imagery Based on Pairwise Branch Detection Head and SAR Feature Enhancement |
| title_short | Oriented Ship Detector for Remote Sensing Imagery Based on Pairwise Branch Detection Head and SAR Feature Enhancement |
| title_sort | oriented ship detector for remote sensing imagery based on pairwise branch detection head and sar feature enhancement |
| topic | ship detection deep learning remote sensing imagery SAR feature enhancement pairwise head |
| url | https://www.mdpi.com/2072-4292/14/9/2177 |
| work_keys_str_mv | AT bokunhe orientedshipdetectorforremotesensingimagerybasedonpairwisebranchdetectionheadandsarfeatureenhancement AT qingyizhang orientedshipdetectorforremotesensingimagerybasedonpairwisebranchdetectionheadandsarfeatureenhancement AT mingtong orientedshipdetectorforremotesensingimagerybasedonpairwisebranchdetectionheadandsarfeatureenhancement AT chuhe orientedshipdetectorforremotesensingimagerybasedonpairwisebranchdetectionheadandsarfeatureenhancement |