Advancing Road Safety: Pothole Detection Using Yolov8 And Wandb Deep Learning
Main Article Content
Abstract
Self-driving vehicles have emerged as a revolutionary breakthrough in modern transportation, promising unparalleled safety, efficiency, and convenience. However, navigating through unpredictable road conditions, especially in the presence of potholes, remains a significant challenge that poses potential safety risks. This study introduces an innovative cloud-powered next-generation self-driving safety system that harnesses the power of AI, specifically YOLOv8 (You Only Look Once version 8), in conjunction with the wandb (Weights & Biases) deep learning platform. This integration enables pothole detection and advanced navigation, elevating the safety standards of autonomous driving. The selection of YOLOv8, a cutting-edge object detection model, is by its exceptional accuracy and speed. YOLOv8 employs a singular neural network to predict object bounding boxes and class probabilities directly, allowing for rapid and precise object detection. This cloud-based architecture also supports continuous model updates and refinements, ensuring the system's adaptability to evolving road conditions and pothole variations. With potential applications extending beyond potholes, this system paves the way for safer and more reliable autonomous transportation, revolutionizing the landscape of self-driving technology.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
V. Pereira, S. Tamura, S. Hayamizu and H. Fukai, "A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste," 2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI), Singapore, 2018, pp. 279-284, doi: 10.1109/SOLI.2018.8476795.
P. Ping, X. Yang and Z. Gao, "A Deep Learning Approach for Street Pothole Detection," 2020 IEEE Sixth International Conference on Big Data Computing Service and Applications (BigDataService), Oxford, UK, 2020, pp. 198-204, doi: 10.1109/BigDataService49289.2020.00039.
D. R. Rajan, M. K. Faizan, R. Kundelu, N. Nandal and V. S. Gunda, "Deep Learning Based Pothole Detection," 2023 International Conference on Emerging Smart Computing and Informatics (ESCI), Pune, India, 2023, pp. 1-5, doi: 10.1109/ESCI56872.2023.10100020.
A. K. M. Jobayer Al Masud, S. T. Sharin, K. F. T. Shawon and Z. Zaman, "Pothole Detection Using Machine Learning Algorithms," 2021 15th International Conference on Signal Processing and Communication Systems (ICSPCS), Sydney, Australia, 2021, pp. 1-5, doi: 10.1109/ICSPCS53099.2021.9660216.
H. N. Srikanth, D. S. Reddy, D. K. Sonkar, R. Kumar and P. Rajalakshmi, "Pothole Detection for Autonomous Vehicles in Indian Scenarios using Deep Learning," 2023 IEEE 26th International Symposium on Real-Time Distributed Computing (ISORC), Nashville, TN, USA, 2023, pp. 184-189, doi: 10.1109/ISORC58943.2023.00033.
R. R, S. Shreya and A. R, "Intelligent Deep Learning based Pothole Detection and Reporting System," 2021 Fourth International Conference on Electrical, Computer and Communication Technologies (ICECCT), Erode, India, 2021, pp. 1-5, doi: 10.1109/ICECCT52121.2021.9616703.
S. Silvister et al., "Deep Learning Approach to Detect Potholes in Real-Time using Smartphone," 2019 IEEE Pune Section International Conference (PuneCon), Pune, India, 2019, pp. 1-4, doi: 10.1109/PuneCon46936.2019.9105737.
J. M. C. Manalo, A. S. Alon, Y. D. Austria, N. E. Merencilla, M. A. Misola and R. C. Sandil, "A Transfer Learning-Based System of Pothole Detection in Roads through Deep Convolutional Neural Networks," 2022 International Conference on Decision Aid Sciences and Applications (DASA), Chiangrai, Thailand, 2022, pp. 1469-1473, doi: 10.1109/DASA54658.2022.9765227.
Y. Bhatia Aparna, R. Rai, V. Gupta, N. Aggarwal and A. Akula, "Convolutional neural networks based potholes detection using thermal imaging", Journal of King Saud University - Computer and Information Sciences, 2019.
K. Wang, M. Liu and Z. Ye, "An advanced YOLOv3 method for small-scale road object detection", Applied Soft Computing, vol. 112, pp. 107846, 2021.
"Pothole and Object Detection for an Autonomous Vehicle Using YOLO", 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS), 2021.
Y. Bhatia Aparna, R. Rai, V. Gupta, N. Aggarwal and A. Akula, "Convolutional neural networks-based potholes detection using thermal imaging", Journal of King Saud University - Computer and Information Sciences, 2019.
V. Pereira, S. Tamura, S. Hayamizu and H. Fukai, "A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste", 2018 IEEE International Conference on Service Operations and Logistics and Informatics (SOLI), 2018.
R. R. S. Shreya and A. R, "Intelligent Deep Learning based Pothole Detection and Reporting System", 2021 Fourth International Conference on Electrical Computer and Communication Technologies (ICECCT), 2021.
X. Xi, Z. Huang, L. Ning and Y. Zhang, "Real-time Pedestrian Detection Algorithm Based on Improved YOLOv3", Journal of Physics: Conference Series, vol. 2002, no. 1, pp. 012075, 2021.
O. Moses, "Official English Documentation for ImageAI! — ImageAI 2.1.6 documentation", Imageai.readthedocs.io, 2021, [online] Available: https://imageai.readthedocs.io/en/latest/.
J. Macalisang, A. Alon, M. Jardiniano, D. Evangelista, J. Castro and M. Tria, "Drive-Awake: A YOLOv3 Machine Vision Inference Approach of Eyes Closure for Drowsy Driving Detection", 2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), 2021.
R. Sevilla, A. Alon, M. Melegrito, R. Reyes, B. Bastes and R. Cimagala, "Mask-Vision: A Machine Vision-Based Inference System of Face Mask Detection for Monitoring Health Protocol Safety", 2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), 2021.
M. Melegrito, A. Alon, S. Militante, Y. Austria, M. Polinar and M. Mirabueno, "Abandoned-Cart-Vision: Abandoned Cart Detection Using a Deep Object Detection Approach in a Shopping Parking Space", 2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), 2021.
P. Ping, X. Yang and Z. Gao, "A Deep Learning Approach for Street Pothole Detection", 2020 IEEE Sixth International Conference on Big Data Computing Service and Applications (BigDataService), 2020.