Performance evaluation of YOLOv5 and YOLOv8 models in car detection
Vol 6, Issue 2, 2023
VIEWS - 658 (Abstract) 324 (PDF)
Abstract
Vehicle detection stands out as a rapidly developing technology today and is further strengthened by deep learning algorithms. This technology is critical in traffic management, automated driving systems, security, urban planning, environmental impacts, transportation, and emergency response applications. Vehicle detection, which is used in many application areas such as monitoring traffic flow, assessing density, increasing security, and vehicle detection in automatic driving systems, makes an effective contribution to a wide range of areas, from urban planning to security measures. Moreover, the integration of this technology represents an important step for the development of smart cities and sustainable urban life. Deep learning models, especially algorithms such as You Only Look Once version 5 (YOLOv5) and You Only Look Once version 8 (YOLOv8), show effective vehicle detection results with satellite image data. According to the comparisons, the precision and recall values of the YOLOv5 model are 1.63% and 2.49% higher, respectively, than the YOLOv8 model. The reason for this difference is that the YOLOv8 model makes more sensitive vehicle detection than the YOLOv5. In the comparison based on the F1 score, the F1 score of YOLOv5 was measured as 0.958, while the F1 score of YOLOv8 was measured as 0.938. Ignoring sensitivity amounts, the increase in F1 score of YOLOv8 compared to YOLOv5 was found to be 0.06%.
Keywords
Full Text:
PDFReferences
1. Maity S, Bhattacharyya A, Singh PK, et al. Last Decade in Vehicle Detection and Classification: A Comprehensive Survey. Archives of Computational Methods in Engineering. 2022; 29(7): 5259-5296. doi: 10.1007/s11831-022-09764-1
2. Bautista CM, Dy CA, Manalac MI, et al. Convolutional neural network for vehicle detection in low resolution traffic videos. In: Proceedings of the 2016 IEEE Region 10 Symposium (TENSYMP).
3. Tsai YM, Huang KY, Tsai CC, et al. Learning-Based Vehicle Detection Using Up-Scaling Schemes and Predictive Frame Pipeline Structures. In: Proceedings of the 2010 20th International Conference on Pattern Recognition.
4. Javed AR, Shahzad F, Rehman S ur, et al. Future smart cities: requirements, emerging technologies, applications, challenges, and future aspects. Cities. 2022; 129: 103794. doi: 10.1016/j.cities.2022.103794
5. Badach J, Voordeckers D, Nyka L, et al. A framework for Air Quality Management Zones - Useful GIS-based tool for urban planning: Case studies in Antwerp and Gdańsk. Building and Environment. 2020; 174: 106743. doi: 10.1016/j.buildenv.2020.106743
6. Kashyap AA, Raviraj S, Devarakonda A, et al. Traffic flow prediction models – A review of deep learning techniques. Cogent Engineering. 2021; 9(1). doi: 10.1080/23311916.2021.2010510
7. Ammar A, Koubaa A, Ahmed M, et al. Aerial images processing for car detection using convolutional neural networks: Comparison between faster r-cnn and yolov3. arXiv. 2019; arXiv:1910.07234.
8. ölkesen IC, Yomralıo˘glu T. Use of worldview-2 satellite imagery and ancillary data for mapping land cover and use (Turkish). Harita Dergisi. 2014; 152(2): 12-24.
9. Liao L, Xiao J, Yang Y, et al. High temporal frequency vehicle counting from low-resolution satellite images. ISPRS Journal of Photogrammetry and Remote Sensing. 2023; 198: 45-59. doi: 10.1016/j.isprsjprs.2023.02.006
10. Komissarov V. AI applications for satellite imagery and satellite data. Available online: https://emerj.com/ai-sector-overviews/ai-applications-for-satellite-imagery-and-data/ (accessed on 23 May 2023).
11. Association AH. Social determinants of health series: Transportation and the role of hospitals. Available online: https://www.aha.org/ahahret-guides/2017-11-15-social-determinants-health-series-transportation-and-role-hospitals (accessed on 23 May 2023).
12. Vivian EO. Car park suitability mapping in federal polytechnic Oko, Anambra state, using geospatial techniques. Intemational Journal of Innovative Science and Research Technology. 2023; 8(2).
13. Gong H, Mu T, Li Q, et al. Swin-Transformer-Enabled YOLOv5 with Attention Mechanism for Small Object Detection on Satellite Images. Remote Sensing. 2022; 14(12): 2861. doi: 10.3390/rs14122861
14. Patel R, Meduri P. Car Detection Based Algorithm for Automatic Parking Space Detection. In: Proceedings of the 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA).
15. Putra M, Yussof Z, Lim K, Salim S. Convolutional neural network for person and car detection using yolo framework, Journal of Telecommunication, Electronic and Computer Engineering. 2018; 10(1-7): 67-71.
16. Arruda VF, Paixao TM, Berriel RF, et al. Cross-Domain Car Detection Using Unsupervised Image-to-Image Translation: From Day to Night. In: Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN). Published online July 2019. doi: 10.1109/ijcnn.2019.8852008
17. Wang L, Geng X, Ma X, et al. Ridesharing car detection by transfer learning. Artificial Intelligence. 2019; 273: 1-18. doi: 10.1016/j.artint.2018.12.008
18. Kashyap K, Miri R. An Optimal BDCNN ML Architecture for Car Make Model Prediction. Journal of Artificial Intelligence and Technology. 2023. doi: 10.37965/jait.2023.0268
19. Xu H, Lai S, Li X, et al. Cross-domain car detection model with integrated convolutional block attention mechanism. Image and Vision Computing. 2023; 140: 104834. doi: 10.1016/j.imavis.2023.104834
20. Citra DH, Jazman M, Afdal M, et al. Vector tile server in geographic information system in bapenda pekanbaru city, KLIK: Kajian Ilmiah Informatika dan Komputer. 2023; 3(6): 861-869.
21. Taşyürek M, Türkdamar MU, Öztürk C. DSHFS: a new hybrid approach that detects structures with their spatial location from large volume satellite images using CNN, GeoServer and TileCache. Neural Computing and Applications. 2023; 36(3): 1237-1259. doi: 10.1007/s00521-023-09092-w
22. Herzog DJ, Herzog NJ. Innovative frontiers: Post-quantum perspectives in healthcare and medical imaging. Imaging and Radiation Research. 2023; 6(1): 3852. doi: 10.24294/irr.v6i1.3852
23. Ortataş FN, Kaya M. Performance Evaluation of YOLOv5, YOLOv7, and YOLOv8 Models in Traffic Sign Detection. 2023 8th International Conference on Computer Science and Engineering (UBMK). Published online September 13, 2023. doi: 10.1109/ubmk59864.2023.10286611
24. Science D. Yolo object detection explained. Available online: https://www.datacamp.com/blog/yolo-object-detection-explained (accessed on 23 May 2023).
25. Terven J, Cordova-Esparza D. A comprehensive review of yolo: From yolov1 and beyond. arXiv. 2023; arXiv:2304.00501.
26. Sary IP, Andromeda S, Armin EU. Performance Comparison of YOLOv5 and YOLOv8 Architectures in Human Detection using Aerial Images. Ultima Computing: Jurnal Sistem Komputer. 2023; 15(1): 8-13.
27. Reis D, Kupec J, Hong J, Daoudi A. Real-time flying object detection with yolov8. arXiv. 2023; arXiv:2305.09972.
28. Liang H, Chen J, Xie W, et al. Defect detection of injection-molded parts based on improved-YOLOv5. Journal of Physics: Conference Series. 2022; 2390(1): 012049. doi: 10.1088/1742-6596/2390/1/012049
29. King R. Brief summary of YOLOv8 model structure. Available online: https://github.com/ultralytics/ultralytics/issues/189 (accessed on 23 May 2023).
DOI: https://doi.org/10.24294/irr.v6i2.5757
Refbacks
- There are currently no refbacks.
License URL: https://creativecommons.org/licenses/by-nc/4.0/
This site is licensed under a Creative Commons Attribution 4.0 International License.