An Evaluation of Image Slicing and YOLO Architectures for Object Detection in UAV Images
Source abstract
Abstract
Object detection in aerial images poses significant challenges due to the high dimensions of the images, requiring efficient handling and resizing to fit object detection models. The image-slicing approach for object detection in aerial images can increase detection accuracy by eliminating pixel loss in high-resolution image data. However, determining the proper dimensions to slice is essential for the integrity of the objects and their learning by the model. This study presents an evaluation of the image-slicing approach for alternative sizes of images to optimize efficiency. For this purpose, a dataset of high-resolution images collected with Unmanned Aerial Vehicles (UAV) has been used. The experiments evaluated using alternative YOLO architectures like YOLOv7, YOLOv8, and YOLOv9 show that the image dimensions significantly change the performance results. According to the experiments, the best mAP@05 accuracy was obtained by slicing 1280×1280 for YOLOv7 producing 88.2. Results show that edge-related objects are better preserved as the overlap and slicing sizes increase, resulting in improved model performance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Neural Network Applications · Advanced Image and Video Retrieval Techniques · Visual Attention and Saliency Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Sakarya University Technology Development Zones Management CO, Sakarya 54050, Turkey
Computer Engineering Department, Sakarya University of Applied Sciences, Sakarya 54050, Turkey
Software Engineering Department, Sakarya University, Sakarya 54050, Turkey
Electrical and Electronics Engineering Department, Sakarya University of Applied Sciences, Sakarya 54050, Turkey
References (28)
Show source-provided references
1. Li, X., Wei, Y., Li, J., Duan, W., Zhang, X., and Huang, Y. (2024). Improved YOLOv7 Algorithm for Small Object Detection in Unmanned Aerial Vehicle Image Scenarios. Appl. Sci., 14.10.3390/app14041664 ↗
2. Liu, M., Wang, X., Zhou, A., Fu, X., Ma, Y., and Piao, C. (2020). UAV-YOLO: Small Object Detection on Unmanned Aerial Vehicle Perspective. Sensors, 20.10.3390/s20082238 ↗
3. Small object detection based on YOLOv8 in UAV perspective10.1007/s10044-024-01323-7 ↗
4. Li, Y., Li, Q., Pan, J., Zhou, Y., Zhu, H., Wei, H., and Liu, C. (2024). Small-Object-Detection Algorithm Based on Improved YOLOv8 for UAV Images. Remote Sens., 16.10.3390/rs16163057 ↗
5. Telçeken, M., Akgun, D., Kacar, S., and Bingol, B. (2024). A New Approach for Super Resolution Object Detection Using an Image Slicing Algorithm and the Segment Anything Model. Sensors, 24.10.3390/s24144526 ↗
6. Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2023, January 17–24). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.10.1109/CVPR52729.2023.00721 ↗
7. Reis, D., Kupec, J., Hong, J., and Daoudi, A. (2023). Real-Time Flying Object Detection with YOLOv8. arXiv.
8. Wang, C.Y., Yeh, I.H., and Liao, H.Y.M. (2024). Yolov9: Learning what you want to learn using programmable gradient information. arXiv.10.1007/978-3-031-72751-1_1 ↗
9. Wang, G., Chen, Y., An, P., Hong, H., Hu, J., and Huang, T. (2024). UAV-YOLOv8: A small-object-detection model based on improved YOLOv8 for UAV aerial photography scenarios. Sensors, 23.10.3390/s23167190 ↗
10. Small Object Detection in UAV Images Based on YOLOv8n10.1007/s44196-024-00632-3 ↗
11. Qian, R., and Ding, Y. (2024). An Efficient UAV Image Object Detection Algorithm Based on Global Attention and Multi-Scale Feature Fusion. Electronics, 13.10.3390/electronics13203989 ↗
12. Ke, H., Fan, Z., Yafeng, S., Wenzhang, Z., and Mingnan, S. (2023, January 8–10). Improved YOLOv4-Based Object Detection Method for UAVs. Proceedings of the 8th IEEE International Conference on Signal and Image Processing (ICSIP), Wuxi, China.10.1109/ICSIP57908.2023.10270983 ↗
13. YOLO-ERF: Lightweight object detector for UAV aerial images10.1007/s00530-023-01182-y ↗
14. Yu, M., and Leung, H. (2023, January 17–20). Small-object detection for UAV-based images. Proceedings of the IEEE International Systems Conference (SysCon), Vancouver, BC, Canada.10.1109/SysCon53073.2023.10131084 ↗
15. YOLOv7-P: A lighter and more effective UAV aerial photography object detection algorithm10.1007/s11760-024-03476-8 ↗
16. SCA-YOLO: A new small object detection model for UAV images10.1007/s00371-023-02886-y ↗
17. SCA-YOLO: Towards Generalized UAV Object Detection: A Novel Perspective from Frequency Domain Disentanglement10.1007/s11263-024-02108-5 ↗
18. Zhang, Y., Ye, M., Zhu, G., Liu, Y., Guo, P., and Yan, J. (2024). FFCA-YOLO for small object detection in remote sensing images. IEEE Trans. Geosci. Remote Sens., 62.10.1109/TGRS.2024.3363057 ↗
19. Discriminative features enhancement for low-altitude UAV object detection10.1016/j.patcog.2023.110041 ↗
20. LUD-YOLO: A novel lightweight object detection network for unmanned aerial vehicle10.1016/j.ins.2024.121366 ↗
21. Improved Detection of Fundus Lesions Using YOLOR-CSP Architecture and Slicing Aided Hyper Inference10.1109/TLA.2023.10244179 ↗
22. Detecting animals in UAV images: Best practices to address a substantially imbalanced dataset with deep learning10.1016/j.rse.2018.06.028 ↗
23. Redmon, J., and Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv.
24. sda-yolo: Semi-supervised domain adaptive yolo for cross-domain object detection10.1016/j.cviu.2023.103649 ↗
25. Deep learning based whale detection from satellite imagery
26. Wildect-yolo: An efficient and robust computer vision-based accurate object localization model for automated endangered wildlife detection10.1016/j.ecoinf.2022.101919 ↗
27. Chen, X., Zhu, G., and Liu, M. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
28. Johnson, J.M., and Khoshgoftaar, T.M. (2022). Remote sensing image scene classification with self-supervised learning based on partially unlabeled datasets. Remote Sens., 14.10.3390/rs14225838 ↗