Vehicle Detection in Aerial Drone Overhead Images based on YOLOv8
International Core Journal of Engineering, (2025), Vol.11, No.5, pp.147-156
Published: April 22, 2025
Abstract
Vehicle target detection technology is widely used in fields such as autonomous driving and intelligent traffic monitoring, but practical applications have strict requirements for its real-time detection, accuracy, and resource consumption. This article proposes the ACEW-YOLOv8 model for vehicle detection in drone overhead images. This model is based on YOLOv8n and replaces two convolutional layers with AKConv in the backbone network to enhance feature extraction capability; Add an ECA channel attention module to the Neck network to enhance feature expression and fusion capabilities; Adopting the Wise-IoUv3 loss function to reduce the impact of low-quality images on model training.
Keywords:
YOLOv8; Drone Aerial Photography; Vehicle Inspection; AKConv; ECA; Wise - IoUv3.
APA Citation:
Shengkai Feng, Xuejun Niu (2025). Vehicle Detection in Aerial Drone Overhead Images based on YOLOv8. International Core Journal of Engineering, 11(5), 147-156. https://doi.org/10.6919/ICJE.202505_11(5).0018
References
- Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and se- mantic segmentation[C]//Proceedings of the IEEE con- ference on computer vision and pattern recognition. 2014: 580-587.
- Girshick R. Fast r-cnn[C]//Proceedings of the IEEE international conference on computer vision. 2015: 1440-1448.
- Ren S. Faster r-cnn: Towards real-time object detection with region proposal networks[J]. arxiv preprint arxiv:1506.01497, 2015.
- Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detec- tion[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 779-788.
- Liu W, Anguelov D, Erhan D, et al. Ssd: Single shot multibox detector[C]//Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part I 14. Springer International Publishing, 2016: 21-37.
- Wang G, Chen Y, An P, et al. UAV-YOLOv8: A small-object-detection model based on improved YOLOv8 for UAV aerial photography scenarios[J]. Sensors, 2023, 23(16): 7190.
- Li Y, Fan Q, Huang H, et al. A modified YOLOv8 detection network for UAV aerial image recognition[J]. Drones, 2023, 7(5): 304.
- Zhai X, Huang Z, Li T, et al. YOLO-Drone: an optimized YOLOv8 network for tiny UAV object detec- tion[J]. Electronics, 2023, 12(17): 3664.
- Cao L, Wang Q, Luo Y, et al. YOLO-TSL: A lightweight target detection algorithm for UAV infrared images based on Triplet attention and Slim-neck[J]. In- frared Physics & Technology, 2024, 141: 105487.
- BangJun L, Small target detection algo- rithm for aerial photography based on location awareness and cross-layer feature fusion[J]. Electric Measurement Technology, 2024, 47(5): 112-123.