Improving Tiny Object Detection in Aerial Images with Yolov5
DOI:
https://doi.org/10.31272/jeasd.2682Keywords:
Aerial Images, Computer Vision, Object Detection, You Only Look OnceAbstract
Object detection is a major area of computer vision work, particularly for aerial surveillance and traffic control applications, where detecting vehicles from aerial images is essential. However, such images often lack semantic detail and struggle to identify small, densely packed objects accurately. This paper proposes improvements to the You Only Look Once version 5 (YOLOv5) model to enhance small object detection. Key modifications include adding a new prediction head with a 160×160 feature map, replacing the Sigmoid Linear Unit (SiLU) activation function with the Exponential Linear Unit (ELU), and swapping the Spatial Pyramid Pooling – Fast (SPPF) module with the Spatial Pyramid Pooling (SPP) module. The enhanced model was tested on two datasets: Dataset for Object Detection in Aerial Images (DOTA) v1.5 and CarJet, which focused on vehicle and plane detection. Results showed a 7.1% increase in mean Average Precision (mAP) on the DOTA dataset and a 2.3% improvement on the CarJet dataset, measured with an Intersection over Union (IoU) threshold of 0.5. These architectural changes to YOLOv5 notably improve small object detection accuracy, offering valuable potential for aerial surveillance and traffic control tasks.
References
K. Li, G. Wan, G. Cheng, L. Meng, and J. Han, “Object detection in optical remote sensing images: A survey and a new benchmark,” ISPRS journal of photogrammetry and remote sensing, vol. 159, no. 1, pp. 296–307, 2020, https://doi.org/10.1016/j.isprsjprs.2019.11.023.
J. Wang, W. Yang, H. Guo, R. Zhang, and G. S. Xia, “Tiny object detection in aerial images,” in Proceedings - International Conference on Pattern Recognition, Institute of Electrical and Electronics Engineers Inc., 2020, pp. 3791–3798. doi: https://doi.org/10.1109/ICPR48806.2021.9413340.
K. Tong and Y. Wu, “Deep learning-based detection from the perspective of small or tiny objects: A survey,” Image Vis Comput, vol. 123, no. 1, p. 104471, 2022, doi: https://doi.org/10.1016/j.imavis.2022.104471.
L. W. Sommer, T. Schuchert, and J. Beyerer, “Fast deep vehicle detection in aerial images,” in Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017, Institute of Electrical and Electronics Engineers Inc., May 2017, pp. 311–319. doi: https://doi.org/10.1109/WACV.2017.41.
K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask r-cnn,” in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2961–2969. doi: https://doi.org/10.1109/ICCV.2017.322.
S. Ren, K. He, R. Girshick, and J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” Adv Neural Inf Process Syst, vol. 28, no. 6, 2015, doi: https://doi.org/10.1109/TPAMI.2016.2577031.
R. Girshick, “Fast r-cnn,” in Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 1440–1448. doi: https://doi.org/10.1109/ICCV.2015.169.
P. Jiang, D. Ergu, F. Liu, Y. Cai, and B. Ma, “A Review of Yolo algorithm developments,” Procedia Comput Sci, vol. 199, no. 1, pp. 1066–1073, 2022, doi: https://doi.org/10.1016/j.procs.2022.01.135.
X. Lu, X. Kang, S. Nishide, and F. Ren, “Object detection based on SSD-ResNet,” in 2019 IEEE 6th International Conference on Cloud Computing and Intelligence Systems (CCIS), IEEE, 2019, pp. 89–92. doi: https://doi.org/10.1109/CCIS48116.2019.9073753.
V. Pandey, K. Anand, A. Kalra, A. Gupta, P. P. Roy, and B. G. Kim, “Enhancing object detection in aerial images,” Mathematical Biosciences and Engineering, vol. 19, no. 8, pp. 7920–7932, 2022, doi: https://doi.org/10.3934/mbe.2022370.
H. Zhang, F. Shao, X. He, Z. Zhang, Y. Cai, and S. Bi, “Research on Object Detection and Recognition Method for UAV Aerial Images Based on Improved YOLOv5,” Drones, vol. 7, no. 6, p. 402, 2023, doi: https://doi.org/10.3390/drones7060402.
M. C. Hansen et al., “High-resolution global maps of 21st-century forest cover change,” Science (1979), vol. 342, no. 6160, pp. 850–853, 2013, doi: https://doi.org/10.1126/science.1244693.
J. Linchant, J. Lisein, J. Semeki, P. Lejeune, and C. Vermeulen, “Are unmanned aircraft systems (UAS s) the future of wildlife monitoring? A review of accomplishments and challenges,” Mamm Rev, vol. 45, no. 4, pp. 239–252, 2015, doi: https://doi.org/10.1111/mam.12046.
C. Huyck, E. Verrucci, and J. Bevington, “Remote sensing for disaster response: A rapid, image-based perspective,” in Earthquake hazard, risk, and disasters, Elsevier, 2014, ch. 1, pp. 1–24. doi: https://doi.org/10.1016/B978-0-12-394848-9.00001-8.
R. Wang, Y. Murayama, and T. Morimoto, “Scenario simulation studies of urban development using remote sensing and GIS: review,” Remote Sens Appl, vol. 22, no. 1, pp. 1–10, Apr. 2021, doi: https://doi.org/10.1016/j.rsase.2021.100474.
S. K. Seelan, S. Laguette, G. M. Casady, and G. A. Seielstad, “Remote sensing applications for precision agriculture: A learning community approach,” Remote Sens Environ, vol. 88, no. 1–2, pp. 157–169, 2003, doi: https://doi.org/10.1016/j.rse.2003.04.007.
E. N. Ganesh, V. Rajendran, D. Ravikumar, P. S. Kumar, G. Revathy, and P. Harivardhan, “Remote sensing analysis framework for maritime surveillance application,” International Journal of Oceans and Oceanography, vol. 15, no. 1, pp. 11–17, 2021, Accessed: Oct. 01, 2024. [Online]. Available: https://www.researchgate.net/publication/358549812_Remote_Sensing_Analysis_Framework_for_Maritime_Surveillance_Application
Y. Fang, X. Guo, K. Chen, Z. Zhou, and Q. Ye, “Accurate and automated detection of surface knots on sawn timbers using YOLO-V5 model,” Bioresources, vol. 16, no. 3, p. 5390, 2021, doi: https://doi.org/10.15376/biores.16.3.5390-5406.
F. Zhou, H. Deng, Q. Xu, and X. Lan, “CNTR-YOLO: Improved YOLOv5 Based on ConvNext and Transformer for Aircraft Detection in Remote Sensing Images,” Electronics (Basel), vol. 12, no. 12, p. 2671, 2023, doi: https://doi.org/10.3390/electronics12122671.
L. W. Sommer, T. Schuchert, and J. Beyerer, “Deep learning based multi-category object detection in aerial images,” in Automatic Target Recognition XXVII, SPIE, May 2017, p. 1020209. doi: https://doi.org/10.1117/12.2262083.
F. Yang, H. Fan, P. Chu, E. Blasch, and H. Ling, “Clustered Object Detection in Aerial Images,” in 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 8311–8320. doi: https://doi.org/10.1109/ICCV.2019.00840.
J. Su, J. Liao, D. Gu, Z. Wang, and G. Cai, “Object detection in aerial images using a multiscale keypoint detection network,” IEEE J Sel Top Appl Earth Obs Remote Sens, vol. 14, no. 1, pp. 1389–1398, 2020, doi: https://doi.org/10.1109/JSTARS.2020.3044733.
I. Singh and G. Munjal, “Improved Yolov5 for small target detection in aerial images,” Available at SSRN 4049533, vol. 3, no. 4049533, pp. 1–27, 2022, doi: https://doi.org/10.2139/ssrn.4049533.
L. Deng et al., “Lightweight aerial image object detection algorithm based on improved YOLOv5s,” Sci Rep, vol. 13, no. 1, p. 7817, 2023, doi: https://doi.org/10.1038/s41598-023-34892-4.
G.-S. Xia et al., “DOTA: A large-scale dataset for object detection in aerial images,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 3974–3983. doi: https://doi.org/10.1109/CVPR.2018.00418.
P. Chen et al., “A cascaded deep learning approach for detecting pipeline defects via pretrained YOLOv5 and ViT models based on MFL data,” Mech Syst Signal Process, vol. 206, no. 1, pp. 110919–110935, 2024, doi: https://doi.org/10.1016/j.ymssp.2023.110919.
R. Huang, J. Pedoeem, and C. Chen, “YOLO-LITE: a real-time object detection algorithm optimized for non-GPU computers,” in 2018 IEEE international conference on big data (big data), IEEE, 2018, pp. 2503–2510. doi: https://doi.org/10.1109/BigData.2018.8621865.
M. B. Ullah, "CPU based YOLO: A real-time object detection algorithm," in 2020 IEEE Region 10 Symposium (TENSYMP), IEEE, 2020, pp. 552–555. doi: https://doi.org/10.1109/TENSYMP50017.2020.9230778.
T. Jiang, C. Li, M. Yang, and Z. Wang, “An improved YOLOv5s algorithm for object detection with an attention mechanism,” Electronics (Basel), vol. 11, no. 16, pp. 2494–2505, 2022, doi: https://doi.org/10.3390/electronics11162494.
J. Zhang, Z. Chen, G. Yan, Y. Wang, and B. Hu, “Faster and Lightweight: An Improved YOLOv5 Object Detector for Remote Sensing Images,” Remote Sens (Basel), vol. 15, no. 20, pp. 4974–5001, 2023, doi: https://doi.org/10.3390/rs15204974.
M. Qiu, L. Huang, and B.-H. Tang, “ASFF-YOLOv5: Multielement detection method for road traffic in UAV images based on multiscale feature fusion,” Remote Sens (Basel), vol. 14, no. 14, pp. 3498–3517, 2022, doi: https://doi.org/10.3390/rs14143498.
Downloads
Key Dates
Received
Revised
Accepted
Published Online First
Published
Issue
Section
License
Copyright (c) 2025 Ahmed Sharba, Hussain Kanaan (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
