AUTONOMOUS DRONE-BASED IMAGING SYSTEM FOR DETECTION OF POTHOLES IN RURAL ROAD
DOI:
https://doi.org/10.11113/aej.v16.23727Keywords:
YOLO, drone-based imaging, road pothole detection, road inspection, ultra-light droneAbstract
As a country with a high percentage of motorbikes, the appearance of potholes has a serious impact on people. Today, detecting and repairing potholes takes a long time. Therefore, this research paper aims to provide solutions for inspectors to save time in detecting potholes. In this study, the authors used drones to col-lect data combined with the common computer vision model YOLOv5 to pro-duce pothole detection models for images taken from drones. From the identifi-cation results, we calculate the size and location of the potholes so that the inspectors can identify the danger range and come up with a reasonable repair plan. The current model reached the precision, recall, and F1 score at 0.946, 0.961, and 0.95, respectively.
References
V. P. a. S. T. a. S. H. a. H. Fukai, 2018. "A Deep Learning-Based Approach for Road Pothole Detection in Timor Leste," 2018 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI), 279-284, DOI : https://doi.org/10.1109/SOLI.2018.8476795
E. B. a. S. O. A. Akagic, 2017. "Pothole detection: An efficient vision based method using RGB color space image segmentation," in 2017 40th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO) DOI: https://doi.org/10.23919/MIPRO.2017.7973589
A. A. a. A. K. a. T. A. a. A. Ammar, 2017. "RoadSense: Smartphone Application to Estimate Road Conditions Using Accelerometer and Gyroscope," IEEE Sensors Journal, 17: 4231-4238. DOI: https://doi.org/10.1109/JSEN.2017.2702739
J. M. a. H. T. a. H. X. a. J. S. a. J. Cao, 2024. "Reconstruction-based anomaly detection for multivariate time series using contrastive generative adversarial networks," Information Processing & Management, 61: 103569, DOI: https://doi.org/10.1016/j.ipm.2023.103569
J. M. a. H. T. a. H. X. a. J. S. a. J. Cao, 2024. "Reconstruction-based anomaly detection for multivariate time series using contrastive generative adversarial networks," Information Processing & Management. 61: 103569, DOI : https://doi.org/10.1109/ICASSP48485.2024.10446766
Young-Mok Kim, Young-Gil Kim, Seungjoo Son, S. Lim, Bong-Yeol Choi, Doo-Hyun Choi, 2022. Review of Recent Automated Pothole-Detection Methods. Applied Science 12: 5320. DOI: https://doi.org/10.3390/app12115320
Akhila Daniel Dana Mohammed Ali & Haval A. Sadeq, 2022. Road Pothole Detection Using Unmanned Aerial Vehicle Imagery and Deep Learning Technique. ZANCO Journal of Pure and Applied Sciences, 34: 107–115. DOI: https://doi.org/10.21271/zjpas.34.6.12
S. K. M. H. Y. M. O. U. A. A. Muhammad Haroon Asad, 2024. "Pothole Detection Using Deep Learning: A Real-Time and AI-on-the-Edge Perspective," in Proceedings of the 12th International Conference on Soft Computing for Problem Solving. SocProS 2023. Lecture Notes in Networks and Systems, DOI: https://doi.org/10.1007/978-981-97-3180-0_34
Ultralytics, 2022. Ultralytics. [Online] Available at: https://community.ultralytics.com/t/minimum-maximum-object-bounding-box-size/126
D. Thuan, 2021."Evolution of YOLO algorithm and YOLOv5: The state-of-the-art object detection algorithm," [Online] Available at: https://www.theseus.fi/handle/10024/452552
Abhishek Ranjan & Rajendra Machavaram, 2022. Detection and Localisation of Farm Mangoes using YOLOv5 Deep Learning Technique. 2022 IEEE 7th International conference for Convergence in Technology, 1-5. DOI : https://doi.org/10.1109/I2CT54291.2022.9825078
Ashit Patel, Lei Huang, Gustavo Vejerano, 2022. Pothole Detection from Dash Camera Images using YOLOv5. 26th International Conference on Image Processing, Computer Vision, & Pattern Recognition (IPCV'22). DOI: https://doi.org/10.1016/j.trpro.2023.11.255
Y. H. Y. Y. ,. M. G. a. R. L. Ruoli Yang, 2017. "Fruit Target Detection Based on BCo-YOLOv5 Model," Mobile Information Systems, DOI : https://doi.org/10.1155/2022/8457173
Abhishek Ranjan & Rajendra Machavaram, 2022. Detection and Localisation of Farm Mangoes using YOLOv5 Deep Learning Technique. 2022 IEEE 7th International conference for Convergence in Technology, 1-5. DOI : https://doi.org/10.1109/I2CT54291.2022.9825078
Ashit Patel, Lei Huang, Gustavo Vejerano, 2022. Pothole Detection from Dash Camera Images using YOLOv5. 26th International Conference on Image Processing, Computer Vision, & Pattern Recognition (IPCV'22). DOI: https://doi.org/10.1016/j.trpro.2023.11.255
A. E. K. A. B. &. S. K. Prabhat Singh, 2024. "Road pothole detection from smartphone sensor data using improved LSTM," Multimed Tools Application, 83: 26009–26030. DOI : https://doi.org/10.1007/s11042-023-16177-0
Robotics, A., 2021. Autel Robotics. [Online] Available at: https://www.autelrobotics.com/productdetail/evo-nano-series-drones.html#jsgg
