Transfer-Learned Object Detection for Aerial Vehicle Counting: A Small-Dataset Case Study in Drone-Based Parking Management
Abstract
Urban parking management increasingly relies on automated occupancy counting, but fixed sensors and ground-level cameras suffer from installation cost and mutual vehicle occlusion, motivating aerial, drone-based alternatives. This study presents a drone-oriented vehicle counting system built around a YOLOv8s object detector, fine-tuned by transfer learning from COCO-pretrained weights on a small, single-class Aerial View Car Detection dataset comprising only 280 training images. The model was evaluated on a 19-image held-out test set, achieving a mean average precision at 50 percent intersection-over-union (mAP50) of 0.993, a stricter mAP50-95 of 0.813, a precision of 0.980, and a recall of 0.982, after 100 training epochs on a single cloud GPU. A standalone Python inference application was developed to process folders of aerial images, drawing bounding boxes around detected vehicles and reporting a total count per image, with per-image CPU inference measured at approximately 614 milliseconds. Qualitative inspection of annotated output confirmed reliable detection across varied vehicle colours, parking orientations, and partial edge-of-frame vehicles, with non-maximum suppression correctly resolving overlapping detections in densely packed rows. This study positions its central methodological contribution as an empirical demonstration that transfer learning from a general-purpose, 80-class pretrained detector permits strong single-class aerial detection performance from a training set roughly two orders of magnitude smaller than the datasets typically used to train aerial vehicle detectors from randomly initialised weights, a finding evaluated directly against comparable published work using the same public dataset and against drone-specific parking occupancy systems reported elsewhere in the literature. A genuine inconsistency in the underlying project documentation regarding total training duration is reported transparently rather than silently resolved.
References
Almeida, P., Oliveira, L. S., Britto Jr., A., & Koerich, A. (2013). Vehicle identification between non-overlapping cameras without direct feature matching. In Proceedings of the IEEE International Conference on Image Processing.
Ammour, N., Alhichri, H., Bazi, Y., Benjdira, B., Alajlan, N., & Zuair, M. (2017). Deep learning approach for car detection in UAV imagery. Remote Sensing, 9(4), Article 312.
Bochkovskiy, A., Wang, C. Y., & Liao, H. Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv. https://arxiv.org/abs/2004.10934
Bura, H., Lin, N., Kumar, N., & Manhimannan, G. (2018). Car park management with sensor networks and deep learning. In Proceedings of the IEEE International Conference on Edge Computing (pp. 1-6).
Dalal, N., & Triggs, B. (2005). Histograms of oriented gradients for human detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (Vol. 1, pp. 886-893).
De Almeida, P. R., Oliveira, L. S., Britto Jr., A. S., & Koerich, A. L. (2021). PKLot: A robust dataset for parking lot classification. Expert Systems with Applications, 42(11), 4937-4949.
Doshi, Y., Shah, K., Katre, N., Sawant, V., et al. (2024). Comparison of YOLO models for object detection from parking spot images. Educational Administration: Theory and Practice, 30(4), 10401-10411. https://doi.org/10.53555/kuey.v30i4.7025
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 580-587).
Girshick, R. (2015). Fast R-CNN. In Proceedings of the IEEE International Conference on Computer Vision (pp. 1440-1448).
Hasan, I., Liao, S., Li, J., Akram, S. U., & Shao, L. (2021). Pedestrian detection: The elephant in the room. arXiv. https://arxiv.org/abs/2003.08799
Refbacks
- There are currently no refbacks.