Aero-YOLO: An Efficient Vehicle and Pedestrian Detection Algorithm Based on Unmanned Aerial Imagery
The cost-effectiveness, compact size, and inherent flexibility of UAV technology have garnered significant attention. Utilizing sensors, UAVs capture ground-based targets, offering a novel perspective for aerial target detection and data collection. However, traditional UAV aerial image recognition...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/13/7/1190 |
| _version_ | 1797212738684977152 |
|---|---|
| author | Yifan Shao Zhaoxu Yang Zhongheng Li Jun Li |
| author_facet | Yifan Shao Zhaoxu Yang Zhongheng Li Jun Li |
| author_sort | Yifan Shao |
| collection | DOAJ |
| description | The cost-effectiveness, compact size, and inherent flexibility of UAV technology have garnered significant attention. Utilizing sensors, UAVs capture ground-based targets, offering a novel perspective for aerial target detection and data collection. However, traditional UAV aerial image recognition techniques suffer from various drawbacks, including limited payload capacity, resulting in insufficient computing power, low recognition accuracy due to small target sizes in images, and missed detections caused by dense target arrangements. To address these challenges, this study proposes a lightweight UAV image target detection method based on YOLOv8, named Aero-YOLO. The specific approach involves replacing the original Conv module with GSConv and substituting the C2f module with C3 to reduce model parameters, extend the receptive field, and enhance computational efficiency. Furthermore, the introduction of the CoordAtt and shuffle attention mechanisms enhances feature extraction, which is particularly beneficial for detecting small vehicles from a UAV perspective. Lastly, three new parameter specifications for YOLOv8 are proposed to meet the requirements of different application scenarios. Experimental evaluations were conducted on the UAV-ROD and VisDrone2019 datasets. The results demonstrate that the algorithm proposed in this study improves the accuracy and speed of vehicle and pedestrian detection, exhibiting robust performance across various angles, heights, and imaging conditions. |
| first_indexed | 2024-04-24T10:47:09Z |
| format | Article |
| id | doaj.art-dd97138f0c024fb3a348e24541406254 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-04-24T10:47:09Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-dd97138f0c024fb3a348e245414062542024-04-12T13:17:01ZengMDPI AGElectronics2079-92922024-03-01137119010.3390/electronics13071190Aero-YOLO: An Efficient Vehicle and Pedestrian Detection Algorithm Based on Unmanned Aerial ImageryYifan Shao0Zhaoxu Yang1Zhongheng Li2Jun Li3School of Computer and Communication Technology, Lanzhou University of Technology, Lanzhou 730050, ChinaSchool of Computer and Communication Technology, Lanzhou University of Technology, Lanzhou 730050, ChinaSchool of Computer and Communication Technology, Lanzhou University of Technology, Lanzhou 730050, ChinaDepartment of Applied Mathematics, Lanzhou University of Technology, Lanzhou 730050, ChinaThe cost-effectiveness, compact size, and inherent flexibility of UAV technology have garnered significant attention. Utilizing sensors, UAVs capture ground-based targets, offering a novel perspective for aerial target detection and data collection. However, traditional UAV aerial image recognition techniques suffer from various drawbacks, including limited payload capacity, resulting in insufficient computing power, low recognition accuracy due to small target sizes in images, and missed detections caused by dense target arrangements. To address these challenges, this study proposes a lightweight UAV image target detection method based on YOLOv8, named Aero-YOLO. The specific approach involves replacing the original Conv module with GSConv and substituting the C2f module with C3 to reduce model parameters, extend the receptive field, and enhance computational efficiency. Furthermore, the introduction of the CoordAtt and shuffle attention mechanisms enhances feature extraction, which is particularly beneficial for detecting small vehicles from a UAV perspective. Lastly, three new parameter specifications for YOLOv8 are proposed to meet the requirements of different application scenarios. Experimental evaluations were conducted on the UAV-ROD and VisDrone2019 datasets. The results demonstrate that the algorithm proposed in this study improves the accuracy and speed of vehicle and pedestrian detection, exhibiting robust performance across various angles, heights, and imaging conditions.https://www.mdpi.com/2079-9292/13/7/1190vehicle detectionUAV imageryYOLOGSConvC3 moduleCoordAtt mechanism |
| spellingShingle | Yifan Shao Zhaoxu Yang Zhongheng Li Jun Li Aero-YOLO: An Efficient Vehicle and Pedestrian Detection Algorithm Based on Unmanned Aerial Imagery Electronics vehicle detection UAV imagery YOLO GSConv C3 module CoordAtt mechanism |
| title | Aero-YOLO: An Efficient Vehicle and Pedestrian Detection Algorithm Based on Unmanned Aerial Imagery |
| title_full | Aero-YOLO: An Efficient Vehicle and Pedestrian Detection Algorithm Based on Unmanned Aerial Imagery |
| title_fullStr | Aero-YOLO: An Efficient Vehicle and Pedestrian Detection Algorithm Based on Unmanned Aerial Imagery |
| title_full_unstemmed | Aero-YOLO: An Efficient Vehicle and Pedestrian Detection Algorithm Based on Unmanned Aerial Imagery |
| title_short | Aero-YOLO: An Efficient Vehicle and Pedestrian Detection Algorithm Based on Unmanned Aerial Imagery |
| title_sort | aero yolo an efficient vehicle and pedestrian detection algorithm based on unmanned aerial imagery |
| topic | vehicle detection UAV imagery YOLO GSConv C3 module CoordAtt mechanism |
| url | https://www.mdpi.com/2079-9292/13/7/1190 |
| work_keys_str_mv | AT yifanshao aeroyoloanefficientvehicleandpedestriandetectionalgorithmbasedonunmannedaerialimagery AT zhaoxuyang aeroyoloanefficientvehicleandpedestriandetectionalgorithmbasedonunmannedaerialimagery AT zhonghengli aeroyoloanefficientvehicleandpedestriandetectionalgorithmbasedonunmannedaerialimagery AT junli aeroyoloanefficientvehicleandpedestriandetectionalgorithmbasedonunmannedaerialimagery |