Object Detection in Smart Transportation Using YOLOv8

Monika Singh¹, Niharika Singh², Raunak Tomar³, Madhur Panwar⁴, Priyansh Aggarwal⁵

¹Department of Data Science, ABES Engineering College, Ghaziabad, India, monika@abes.ac.in

²Department of Data Science, ABES Engineering College, Ghaziabad, India, niharika.22b1541040@abes.ac.in

³Department of Data Science, ABES Engineering College , Ghaziabad, India, raunak.22b1541048@abes.ac.in

⁴Department of Data Science, ABES Engineering College, Ghaziabad, India, madhur.22b1541124@abes.ac.in

⁵Department of Data Science, ABES Engineering College, Ghaziabad, India, priyansh.22b1541040@abes.ac.in

Abstract— Ensuring safety and efficiency in nighttime driving is a critical aspect of smart transportation, as object detection models often struggle under low-light conditions. This study explores improvements to YOLO (You Only Look Once) algorithms for real-time detection of vehicles and pedestrians at night, addressing the challenges of accuracy and speed in such environments. While traditional YOLO models, like YOLOv3 and YOLOv5, perform well during the day, they require specific adaptations to function effectively in low-light scenarios.Recent innovations in YOLO adaptations have demonstrated the potential of network enhancements and fused detection systems for improving night vision capabilities. Building on these advancements, this research introduces optimized YOLO models equipped with advanced feature fusion and residual structures to minimize detail loss under low-light conditions. Techniques such as integrating visual data with millimeter-wave radar for better detection of obscured objects and using bio-inspired modules for adapting to varying lighting scenarios have been implemented.Using a custom low-light dataset, the optimized models achieved significant improvements in accuracy, reaching up to 94% without compromising real-time performance. These results highlight the enhanced robustness and precision of the proposed models, paving the way for safer and more efficient object detection systems in nighttime driving. This study contributes to the advancement of smart transportation technologies by presenting innovative solutions that enhance detection capabilities in challenging low-visibility environments, ultimately supporting safer road systems.

Keywords—YOLO, Deep Learning, Smart Transportation, Vehicle, Safety, Real time object detection

References

• Guo, Jun, MengZhen Shao, XinYu Chen, Yang Yang, and EnHui Sun. “Research on night-time vehicle target detection based on improved KSC-YOLO V5.” (2024).
• Huang, S., He, Y., & Chen, X. A. (2021, April). M-YOLO: a nighttime vehicle detection method combining mobilenet v2 and YOLO v3. In Journal of Physics: Conference Series (Vol. 1883, No. 1, p. 012094). IOP Publishing.
• Bhabad, D., Kadam, S., Malode, T., Shinde, G., & Bage, D. (2023). Object detection for night vision using deep learning algorithms. International Journal of Computer Trends and Technology, 71(2), 87-92.
• Hung KF, Lin KP. Bio-inspired dark adaptive nighttime object detection. Biomimetics. 2024 Mar 3;9(3):158.
• Song, Y., Xie, Z., Wang, X., & Zou, Y. (2022). MS-YOLO: Object detection based on YOLOv5 optimized fusion millimeter-wave radar and machine vision. IEEE Sensors journal, 22(15), 15435-15447.
• Ćorović, A., Ilić, V., Ðurić, S., Marijan, M., & Pavković, B. (2018, November). The real-time detection of traffic participants using YOLO algorithm. In 2018 26th Telecommunications Forum (TELFOR) (pp. 1-4). IEEE.
• Lavanya and S. D. Pande, “Enhancing real-time object detection with YOLO algorithm,” EAI Endorsed Transactions on Internet of Things, vol. 10, p. e4, Dec. 2023, doi: 10.4108/eetiot.4541.
• Diwan, G. Anirudh, and J. V. Tembhurne, “Object detection using YOLO: challenges, architectural successors, datasets and applications,” Multimedia Tools and Applications, vol. 82, no. 6, pp. 9243–9275, 2023, doi: 10.1007/s11042-022-13644-y.
• Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 779–788, doi: 10.1109/CVPR.2016.91.
• E. Selvi and P. J. Mercy, “Object detection in image using YOLO,” International Journal of Scientific Research in Computer Science, Engineering and Information Technology, vol. 5, no. 2, pp. 245–250, 2020.
• Geethapriya, N. Duraimurugan, and S. P. Chokkalingam, “Real-time object detection with YOLO,” International Journal of Engineering and Advanced Technology, vol. 8, no. 3S, pp. 578–581, 2019.
• Tang, C. Ye, X. Zhou, and L. Xu, “YOLO-Fusion and Internet of Things: Advancing object detection in smart transportation,” Alexandria Engineering Journal, vol. 107, p. 12, 2024, doi: 10.1016/j.aej.2024.09.012.
• Feng and T. Jin, “CEH-YOLO: A composite enhanced YOLO-based model for underwater object detection,” Ecological Informatics, vol. 82, p. 102758, 2024, doi: 10.1016/j.ecoinf.2024.102758.
• Han, J. Chang, and K. Wang, “Real-time object detection based on YOLO-v2 for tiny vehicle object,” Procedia Computer Science, vol. 183, pp. 61–72, 2021, doi: 10.1016/j.procs.2021.02.014.
• Z. Basha and G. S. R. B., “Real-time object detection in low-light environments using YOLOv8: A case study with a custom dataset,” International Journal of Engineering Research & Technology, vol. 13, no. 10, pp. 50–55, Oct. 2024, doi: 10.17577/IJERTV13IS100050.
• Al-refai, H. Elmoaqet, M. Ryalat, and M. Al-refai, “Object detection in low-light environment using YOLOv7,” Research Square, 2023, doi: 10.21203/rs.3.rs-3365905/v1.
• Sivasubramanian, A. J. Prakash, D. K. S. Kumar, V. R. Prashanth, V. Sowmya, and S. V. V. Variyar, “Object detection under low-lighting conditions using deep learning architectures: A comparative study,” in Advances in Data Science and Computing Technologies, Springer, 2023, pp. 269–276, doi: 10.1007/978-981-99-3656-4_27.
• Al-refai and M. Al-refai, “Road object detection using Yolov3 and Kitti dataset,” International Journal of Advanced Computer Science and Applications, vol. 11, no. 8, pp. 48–53, 2020, doi: 10.14569/IJACSA.2020.0110807.
• Du, “Understanding of object detection based on CNN family and YOLO,” Journal of Physics: Conference Series, vol. 1004, p. 012029, 2018, doi: 10.1088/1742-6596/1004/1/012029.
• Fang, L. Wang, and P. Ren, “Tinier-YOLO: A real-time object detection method for constrained environments,” IEEE Access, vol. 8, pp. 1935–1944, 2020, doi: 10.1109/ACCESS.2019.2961959.