Sar Ship Detection Based on Convnext with Multi-Pooling Channel Attention and Feature Intensification Pyramid Network
The advancements in ship detection technology using convolutional neural networks (CNNs) regarding synthetic aperture radar (SAR) images have been significant. Yet, there are still some limitations in the existing detection algorithms. First, the backbones cannot generate high-quality multiscale fea...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/17/7641 |
| _version_ | 1827727751752187904 |
|---|---|
| author | Fanming Wei Xiao Wang |
| author_facet | Fanming Wei Xiao Wang |
| author_sort | Fanming Wei |
| collection | DOAJ |
| description | The advancements in ship detection technology using convolutional neural networks (CNNs) regarding synthetic aperture radar (SAR) images have been significant. Yet, there are still some limitations in the existing detection algorithms. First, the backbones cannot generate high-quality multiscale feature maps. Second, there is a lack of suitable attention mechanisms to suppress false alarms. Third, the current feature intensification algorithms are unable to effectively enhance the shallow feature’s semantic information, which hinders the detection of small ships. Fourth, top-level feature maps have rich semantic information; however, as a result of the reduction of channels, the semantic information is weakened. These four problems lead to poor performance in SAR ship detection and recognition. To address the mentioned issues, we put forward a new approach that has the following characteristics. First, we use Convnext as the backbone to generate high-quality multiscale feature maps. Second, to suppress false alarms, the multi-pooling channel attention (MPCA) is designed to generate a corresponding weight for each channel, suppressing redundant feature maps, and further optimizing the feature maps generated by Convnext. Third, a feature intensification pyramid network (FIPN) is specifically designed to intensify the feature maps, especially the shallow feature maps. Fourth, a top-level feature intensification (TLFI) is also proposed to compensate for semantic information loss within the top-level feature maps by utilizing semantic information from different spaces. The experimental dataset employed is the SAR Ship Detection Dataset (SSDD), and the experimental findings display that our approach exhibits superiority compared to other advanced approaches. The overall Average Precision (AP) reaches up to 95.6% on the SSDD, which improves the accuracy by at least 1.7% compared to the current excellent methods. |
| first_indexed | 2024-03-10T23:12:25Z |
| format | Article |
| id | doaj.art-75590b7e0cb94900afb54360296e63e1 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T23:12:25Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-75590b7e0cb94900afb54360296e63e12023-11-19T08:52:35ZengMDPI AGSensors1424-82202023-09-012317764110.3390/s23177641Sar Ship Detection Based on Convnext with Multi-Pooling Channel Attention and Feature Intensification Pyramid NetworkFanming Wei0Xiao Wang1College of Computer and Information Engineering, Nanjing Tech University, Nanjing 211816, ChinaCollege of Computer and Information Engineering, Nanjing Tech University, Nanjing 211816, ChinaThe advancements in ship detection technology using convolutional neural networks (CNNs) regarding synthetic aperture radar (SAR) images have been significant. Yet, there are still some limitations in the existing detection algorithms. First, the backbones cannot generate high-quality multiscale feature maps. Second, there is a lack of suitable attention mechanisms to suppress false alarms. Third, the current feature intensification algorithms are unable to effectively enhance the shallow feature’s semantic information, which hinders the detection of small ships. Fourth, top-level feature maps have rich semantic information; however, as a result of the reduction of channels, the semantic information is weakened. These four problems lead to poor performance in SAR ship detection and recognition. To address the mentioned issues, we put forward a new approach that has the following characteristics. First, we use Convnext as the backbone to generate high-quality multiscale feature maps. Second, to suppress false alarms, the multi-pooling channel attention (MPCA) is designed to generate a corresponding weight for each channel, suppressing redundant feature maps, and further optimizing the feature maps generated by Convnext. Third, a feature intensification pyramid network (FIPN) is specifically designed to intensify the feature maps, especially the shallow feature maps. Fourth, a top-level feature intensification (TLFI) is also proposed to compensate for semantic information loss within the top-level feature maps by utilizing semantic information from different spaces. The experimental dataset employed is the SAR Ship Detection Dataset (SSDD), and the experimental findings display that our approach exhibits superiority compared to other advanced approaches. The overall Average Precision (AP) reaches up to 95.6% on the SSDD, which improves the accuracy by at least 1.7% compared to the current excellent methods.https://www.mdpi.com/1424-8220/23/17/7641Convnextfeature intensification pyramid network (FIPN)SAR ship detectionmulti-pooling channel attention (MPCA)top-level feature intensification (TLFI) module |
| spellingShingle | Fanming Wei Xiao Wang Sar Ship Detection Based on Convnext with Multi-Pooling Channel Attention and Feature Intensification Pyramid Network Sensors Convnext feature intensification pyramid network (FIPN) SAR ship detection multi-pooling channel attention (MPCA) top-level feature intensification (TLFI) module |
| title | Sar Ship Detection Based on Convnext with Multi-Pooling Channel Attention and Feature Intensification Pyramid Network |
| title_full | Sar Ship Detection Based on Convnext with Multi-Pooling Channel Attention and Feature Intensification Pyramid Network |
| title_fullStr | Sar Ship Detection Based on Convnext with Multi-Pooling Channel Attention and Feature Intensification Pyramid Network |
| title_full_unstemmed | Sar Ship Detection Based on Convnext with Multi-Pooling Channel Attention and Feature Intensification Pyramid Network |
| title_short | Sar Ship Detection Based on Convnext with Multi-Pooling Channel Attention and Feature Intensification Pyramid Network |
| title_sort | sar ship detection based on convnext with multi pooling channel attention and feature intensification pyramid network |
| topic | Convnext feature intensification pyramid network (FIPN) SAR ship detection multi-pooling channel attention (MPCA) top-level feature intensification (TLFI) module |
| url | https://www.mdpi.com/1424-8220/23/17/7641 |
| work_keys_str_mv | AT fanmingwei sarshipdetectionbasedonconvnextwithmultipoolingchannelattentionandfeatureintensificationpyramidnetwork AT xiaowang sarshipdetectionbasedonconvnextwithmultipoolingchannelattentionandfeatureintensificationpyramidnetwork |