ATBHC-YOLO: aggregate transformer and bidirectional hybrid convolution for small object detection
Abstract Object detection using UAV images is a current research focus in the field of computer vision, with frequent advancements in recent years. However, many methods are ineffective for challenging UAV images that feature uneven object scales, sparse spatial distribution, and dense occlusions. W...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-11-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01652-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571204151541760 |
|---|---|
| author | Dandan Liao Jianxun Zhang Ye Tao Xie Jin |
| author_facet | Dandan Liao Jianxun Zhang Ye Tao Xie Jin |
| author_sort | Dandan Liao |
| collection | DOAJ |
| description | Abstract Object detection using UAV images is a current research focus in the field of computer vision, with frequent advancements in recent years. However, many methods are ineffective for challenging UAV images that feature uneven object scales, sparse spatial distribution, and dense occlusions. We propose a new algorithm for detecting small objects in UAV images, called ATBHC-YOLO. Firstly, the MS-CET module has been introduced to enhance the model’s focus on global sparse features in the spatial distribution of small objects. Secondly, the BHC-FB module is proposed to address the large-scale variance of small objects and enhance the perception of local features. Finally, a more appropriate loss function, WIoU, is used to penalise the quality variance of small object samples and further enhance the model’s detection accuracy. Comparison experiments on the DIOR and VEDAI datasets validate the effectiveness and robustness of the improved method. By conducting experiments on the publicly available UAV benchmark dataset Visdrone, ATBHC-YOLO outperforms the state-of-the-art method(YOLOv7) by 3.5%. |
| format | Article |
| id | doaj-art-e291deafa1eb4f12ad93715c78769ea3 |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-e291deafa1eb4f12ad93715c78769ea32025-02-02T12:50:15ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-11-0111111510.1007/s40747-024-01652-4ATBHC-YOLO: aggregate transformer and bidirectional hybrid convolution for small object detectionDandan Liao0Jianxun Zhang1Ye Tao2Xie Jin3Department of Computer Science and Engineering, Chongqing University of TechnologyDepartment of Computer Science and Engineering, Chongqing University of TechnologyDepartment of Computer Science and Engineering, Chongqing University of TechnologyNorthern University of MalaysiaAbstract Object detection using UAV images is a current research focus in the field of computer vision, with frequent advancements in recent years. However, many methods are ineffective for challenging UAV images that feature uneven object scales, sparse spatial distribution, and dense occlusions. We propose a new algorithm for detecting small objects in UAV images, called ATBHC-YOLO. Firstly, the MS-CET module has been introduced to enhance the model’s focus on global sparse features in the spatial distribution of small objects. Secondly, the BHC-FB module is proposed to address the large-scale variance of small objects and enhance the perception of local features. Finally, a more appropriate loss function, WIoU, is used to penalise the quality variance of small object samples and further enhance the model’s detection accuracy. Comparison experiments on the DIOR and VEDAI datasets validate the effectiveness and robustness of the improved method. By conducting experiments on the publicly available UAV benchmark dataset Visdrone, ATBHC-YOLO outperforms the state-of-the-art method(YOLOv7) by 3.5%.https://doi.org/10.1007/s40747-024-01652-4Small object detectionAttention mechanismATBHC-YOLOCross-feature fusion |
| spellingShingle | Dandan Liao Jianxun Zhang Ye Tao Xie Jin ATBHC-YOLO: aggregate transformer and bidirectional hybrid convolution for small object detection Complex & Intelligent Systems Small object detection Attention mechanism ATBHC-YOLO Cross-feature fusion |
| title | ATBHC-YOLO: aggregate transformer and bidirectional hybrid convolution for small object detection |
| title_full | ATBHC-YOLO: aggregate transformer and bidirectional hybrid convolution for small object detection |
| title_fullStr | ATBHC-YOLO: aggregate transformer and bidirectional hybrid convolution for small object detection |
| title_full_unstemmed | ATBHC-YOLO: aggregate transformer and bidirectional hybrid convolution for small object detection |
| title_short | ATBHC-YOLO: aggregate transformer and bidirectional hybrid convolution for small object detection |
| title_sort | atbhc yolo aggregate transformer and bidirectional hybrid convolution for small object detection |
| topic | Small object detection Attention mechanism ATBHC-YOLO Cross-feature fusion |
| url | https://doi.org/10.1007/s40747-024-01652-4 |
| work_keys_str_mv | AT dandanliao atbhcyoloaggregatetransformerandbidirectionalhybridconvolutionforsmallobjectdetection AT jianxunzhang atbhcyoloaggregatetransformerandbidirectionalhybridconvolutionforsmallobjectdetection AT yetao atbhcyoloaggregatetransformerandbidirectionalhybridconvolutionforsmallobjectdetection AT xiejin atbhcyoloaggregatetransformerandbidirectionalhybridconvolutionforsmallobjectdetection |