FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object Detection
UAV-based object detection has recently attracted a lot of attention due to its diverse applications. Most of the existing convolution neural network based object detection models can perform well in common object detection cases. However, due to the fact that objects in UAV images are spatially dis...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/18/6993 |
| _version_ | 1797482449018552320 |
|---|---|
| author | Wenyu Xu Chaofan Zhang Qi Wang Pangda Dai |
| author_facet | Wenyu Xu Chaofan Zhang Qi Wang Pangda Dai |
| author_sort | Wenyu Xu |
| collection | DOAJ |
| description | UAV-based object detection has recently attracted a lot of attention due to its diverse applications. Most of the existing convolution neural network based object detection models can perform well in common object detection cases. However, due to the fact that objects in UAV images are spatially distributed in a very dense manner, these methods have limited performance for UAV-based object detection. In this paper, we propose a novel transformer-based object detection model to improve the accuracy of object detection in UAV images. To detect dense objects competently, an advanced foreground enhancement attention Swin Transformer (FEA-Swin) framework is designed by integrating context information into the original backbone of a Swin Transformer. Moreover, to avoid the loss of information of small objects, an improved weighted bidirectional feature pyramid network (BiFPN) is presented by designing the skip connection operation. The proposed method aggregates feature maps from four stages and keeps abundant information of small objects. Specifically, to balance the detection accuracy and efficiency, we introduce an efficient neck of the BiFPN network by removing a redundant network layer. Experimental results on both public datasets and a self-made dataset demonstrate the performance of our method compared to the state-of-the-art methods in terms of detection accuracy. |
| first_indexed | 2024-03-09T22:33:27Z |
| format | Article |
| id | doaj.art-0d364f56e18b4cc7b50518287af4ed38 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T22:33:27Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0d364f56e18b4cc7b50518287af4ed382023-11-23T18:52:40ZengMDPI AGSensors1424-82202022-09-012218699310.3390/s22186993FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object DetectionWenyu Xu0Chaofan Zhang1Qi Wang2Pangda Dai3Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaHefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaHefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaHefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, ChinaUAV-based object detection has recently attracted a lot of attention due to its diverse applications. Most of the existing convolution neural network based object detection models can perform well in common object detection cases. However, due to the fact that objects in UAV images are spatially distributed in a very dense manner, these methods have limited performance for UAV-based object detection. In this paper, we propose a novel transformer-based object detection model to improve the accuracy of object detection in UAV images. To detect dense objects competently, an advanced foreground enhancement attention Swin Transformer (FEA-Swin) framework is designed by integrating context information into the original backbone of a Swin Transformer. Moreover, to avoid the loss of information of small objects, an improved weighted bidirectional feature pyramid network (BiFPN) is presented by designing the skip connection operation. The proposed method aggregates feature maps from four stages and keeps abundant information of small objects. Specifically, to balance the detection accuracy and efficiency, we introduce an efficient neck of the BiFPN network by removing a redundant network layer. Experimental results on both public datasets and a self-made dataset demonstrate the performance of our method compared to the state-of-the-art methods in terms of detection accuracy.https://www.mdpi.com/1424-8220/22/18/6993object detectionaerial imagestransformer-basedforeground enhancement attentionimproved bidirectional feature pyramid network |
| spellingShingle | Wenyu Xu Chaofan Zhang Qi Wang Pangda Dai FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object Detection Sensors object detection aerial images transformer-based foreground enhancement attention improved bidirectional feature pyramid network |
| title | FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object Detection |
| title_full | FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object Detection |
| title_fullStr | FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object Detection |
| title_full_unstemmed | FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object Detection |
| title_short | FEA-Swin: Foreground Enhancement Attention Swin Transformer Network for Accurate UAV-Based Dense Object Detection |
| title_sort | fea swin foreground enhancement attention swin transformer network for accurate uav based dense object detection |
| topic | object detection aerial images transformer-based foreground enhancement attention improved bidirectional feature pyramid network |
| url | https://www.mdpi.com/1424-8220/22/18/6993 |
| work_keys_str_mv | AT wenyuxu feaswinforegroundenhancementattentionswintransformernetworkforaccurateuavbaseddenseobjectdetection AT chaofanzhang feaswinforegroundenhancementattentionswintransformernetworkforaccurateuavbaseddenseobjectdetection AT qiwang feaswinforegroundenhancementattentionswintransformernetworkforaccurateuavbaseddenseobjectdetection AT pangdadai feaswinforegroundenhancementattentionswintransformernetworkforaccurateuavbaseddenseobjectdetection |