SDMSEAF-YOLOv8: a framework to significantly improve the detection performance of unmanned aerial vehicle images
The detailed, high-resolution images captured by drones pose challenges to target detection algorithms with complex scenes and small-sized targets. Moreover, targets in unmanned aerial vehicle images are usually affected by factors such as viewing perspective, occlusion, and light, which increase th...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2024-01-01
|
| Series: | Geocarto International |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/10106049.2024.2339294 |
| _version_ | 1826938997023178752 |
|---|---|
| author | Linxuan Li Xiaoyu Liu Xuan Chen Fengjuan Yin Bin Chen Yufeng Wang Fanbin Meng |
| author_facet | Linxuan Li Xiaoyu Liu Xuan Chen Fengjuan Yin Bin Chen Yufeng Wang Fanbin Meng |
| author_sort | Linxuan Li |
| collection | DOAJ |
| description | The detailed, high-resolution images captured by drones pose challenges to target detection algorithms with complex scenes and small-sized targets. Moreover, targets in unmanned aerial vehicle images are usually affected by factors such as viewing perspective, occlusion, and light, which increase the difficulty of target detection. In response to the above issues, we propose an improved SDMSEAF-YOLOv8 for target detection based on YOLOv8, combined with a Bi-directional Feature Pyramid Network, to improve the sensing ability of the model for multiscale targets. A Space-to-depth layer replaces the traditional strided convolution layer to enhance the extraction of fine-grained information and small-sized target features. A Multi-Separated and Enhancement Attention module enhances the feature learning ability of the occluded target region, thus reducing missed and false detections. Four detection heads are employed for tiny target detection, each responsible for different size ranges, so as to improve the accuracy and robustness of small target detection. The conventional non-maximum suppression algorithm is improved, so as to reduce the problem of missed detections under a densely occluded scene by setting the attenuation function to adjust the confidence of the treated box based on the overlap between it and the highest-scoring box. Experiments demonstrate that the accuracy of SDMSEAF-YOLOv8 exceeds that of state-of-the-art models on the VisDrone2019-DET-val dataset, with a mAP of 42.9% at 640-pixel resolution, 14.8% over the baseline YOLOv8-x algorithm model, and 6.0% over the known state-of-the-art Fine-Grained Target Focusing Network model and with twice as fast detection. |
| first_indexed | 2024-04-24T11:24:37Z |
| format | Article |
| id | doaj.art-7cca6b427c4e44e8aed0ff7ab7a2cf0e |
| institution | Directory Open Access Journal |
| issn | 1010-6049 1752-0762 |
| language | English |
| last_indexed | 2025-02-17T19:07:21Z |
| publishDate | 2024-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geocarto International |
| spelling | doaj.art-7cca6b427c4e44e8aed0ff7ab7a2cf0e2024-12-10T08:23:09ZengTaylor & Francis GroupGeocarto International1010-60491752-07622024-01-0139110.1080/10106049.2024.2339294SDMSEAF-YOLOv8: a framework to significantly improve the detection performance of unmanned aerial vehicle imagesLinxuan Li0Xiaoyu Liu1Xuan Chen2Fengjuan Yin3Bin Chen4Yufeng Wang5Fanbin Meng6School of Medical Information Engineering, Jining Medical University, Rizhao, ChinaSchool of Medical Information Engineering, Jining Medical University, Rizhao, ChinaSchool of Medical Information Engineering, Jining Medical University, Rizhao, ChinaSchool of Medical Information Engineering, Jining Medical University, Rizhao, ChinaSchool of Mechanical and Electronic Engineering, Shandong Agriculture and Engineering University, Zibo, ChinaSchool of Medical Information Engineering, Jining Medical University, Rizhao, ChinaSchool of Medical Information Engineering, Jining Medical University, Rizhao, ChinaThe detailed, high-resolution images captured by drones pose challenges to target detection algorithms with complex scenes and small-sized targets. Moreover, targets in unmanned aerial vehicle images are usually affected by factors such as viewing perspective, occlusion, and light, which increase the difficulty of target detection. In response to the above issues, we propose an improved SDMSEAF-YOLOv8 for target detection based on YOLOv8, combined with a Bi-directional Feature Pyramid Network, to improve the sensing ability of the model for multiscale targets. A Space-to-depth layer replaces the traditional strided convolution layer to enhance the extraction of fine-grained information and small-sized target features. A Multi-Separated and Enhancement Attention module enhances the feature learning ability of the occluded target region, thus reducing missed and false detections. Four detection heads are employed for tiny target detection, each responsible for different size ranges, so as to improve the accuracy and robustness of small target detection. The conventional non-maximum suppression algorithm is improved, so as to reduce the problem of missed detections under a densely occluded scene by setting the attenuation function to adjust the confidence of the treated box based on the overlap between it and the highest-scoring box. Experiments demonstrate that the accuracy of SDMSEAF-YOLOv8 exceeds that of state-of-the-art models on the VisDrone2019-DET-val dataset, with a mAP of 42.9% at 640-pixel resolution, 14.8% over the baseline YOLOv8-x algorithm model, and 6.0% over the known state-of-the-art Fine-Grained Target Focusing Network model and with twice as fast detection.https://www.tandfonline.com/doi/10.1080/10106049.2024.2339294SDMSEAF-YOLOv8VisDrone2019SPDBiFPNMultiSEAM |
| spellingShingle | Linxuan Li Xiaoyu Liu Xuan Chen Fengjuan Yin Bin Chen Yufeng Wang Fanbin Meng SDMSEAF-YOLOv8: a framework to significantly improve the detection performance of unmanned aerial vehicle images Geocarto International SDMSEAF-YOLOv8 VisDrone2019 SPD BiFPN MultiSEAM |
| title | SDMSEAF-YOLOv8: a framework to significantly improve the detection performance of unmanned aerial vehicle images |
| title_full | SDMSEAF-YOLOv8: a framework to significantly improve the detection performance of unmanned aerial vehicle images |
| title_fullStr | SDMSEAF-YOLOv8: a framework to significantly improve the detection performance of unmanned aerial vehicle images |
| title_full_unstemmed | SDMSEAF-YOLOv8: a framework to significantly improve the detection performance of unmanned aerial vehicle images |
| title_short | SDMSEAF-YOLOv8: a framework to significantly improve the detection performance of unmanned aerial vehicle images |
| title_sort | sdmseaf yolov8 a framework to significantly improve the detection performance of unmanned aerial vehicle images |
| topic | SDMSEAF-YOLOv8 VisDrone2019 SPD BiFPN MultiSEAM |
| url | https://www.tandfonline.com/doi/10.1080/10106049.2024.2339294 |
| work_keys_str_mv | AT linxuanli sdmseafyolov8aframeworktosignificantlyimprovethedetectionperformanceofunmannedaerialvehicleimages AT xiaoyuliu sdmseafyolov8aframeworktosignificantlyimprovethedetectionperformanceofunmannedaerialvehicleimages AT xuanchen sdmseafyolov8aframeworktosignificantlyimprovethedetectionperformanceofunmannedaerialvehicleimages AT fengjuanyin sdmseafyolov8aframeworktosignificantlyimprovethedetectionperformanceofunmannedaerialvehicleimages AT binchen sdmseafyolov8aframeworktosignificantlyimprovethedetectionperformanceofunmannedaerialvehicleimages AT yufengwang sdmseafyolov8aframeworktosignificantlyimprovethedetectionperformanceofunmannedaerialvehicleimages AT fanbinmeng sdmseafyolov8aframeworktosignificantlyimprovethedetectionperformanceofunmannedaerialvehicleimages |