Detection of road defects with weak small samples based on multiple deep learning models
DOI:
https://doi.org/10.62051/vx1gcb89Keywords:
Road Defects Detection; YOLO; Segment Anything.Abstract
Potholes on roads not only jeopardize traffic safety and driving comfort but also necessitate efficient detection and maintenance measures. Traditional manual detection methods are labor-intensive and time-consuming. Thus, developing automated solutions is imperative. This study addresses this challenge by constructing a dataset and evaluating various deep learning models, including GoogleNet, VGG16, ResNet50, AlexNet, YOLOV5, and YOLOV8, for pothole detection. YOLOV8 emerges as the optimal choice due to its superior accuracy. However, accurately estimating pothole areas proves challenging due to their irregular shapes. To mitigate this, an innovative algorithm is proposed, integrating YOLO with a pre-trained segmentation model. This enables precise pixel-level delineation of pothole areas. Additionally, the algorithm incorporates the intersection over union (IOU) metric to calculate the ratio of pothole area to the total image area. By enhancing both detection and area estimation, this approach holds promise for improving road safety and facilitating maintenance efforts. Automated detection and accurate area estimation not only save time and resources but also provide crucial data for prioritizing and planning road repair and maintenance tasks.
Downloads
References
[1] Yao S, Guan R, Huang X, et al. Radar-camera fusion for object detection and semantic segmentation in autonomous driving: A comprehensive review [J]. IEEE Transactions on Intelligent Vehicles, 2023. DOI: https://doi.org/10.1109/TIV.2023.3307157
[2] Méndez M, Merayo M G, Núñez M. Machine learning algorithms to forecast air quality: a survey [J]. Artificial Intelligence Review, 2023, 56 (9): 10031 - 10066. DOI: https://doi.org/10.1007/s10462-023-10424-4
[3] Ali Y A, Awwad E M, Al-Razgan M, et al. Hyperparameter search for machine learning algorithms for optimizing the computational complexity [J]. Processes, 2023, 11 (2): 349. K. Elissa, “Title of paper if known,” unpublished. DOI: https://doi.org/10.3390/pr11020349
[4] Song H, Huang S, Dong Y, et al. Robustness and generalizability of deepfake detection: A study with diffusion models [J]. arXiv preprint arXiv:2309.02218, 2023.
[5] Jakubec M, Lieskovská E, Bučko B, et al. Comparison of CNN-based models for pothole detection in real-world adverse conditions: overview and evaluation[J]. Applied Sciences, 2023, 13 (9): 5810. DOI: https://doi.org/10.3390/app13095810
[6] Wang Z, Cai Z, Wu Y. An improved YOLOX approach for low-light and small object detection: PPE on tunnel construction sites [J]. Journal of Computational Design and Engineering, 2023, 10 (3): 1158 - 1175. DOI: https://doi.org/10.1093/jcde/qwad042
[7] A. Cord, S. Chambon, Automatic Road defect detection by textural pattern recognition based on adaboost, Computer-Aided Civil and Infrastructure Engineering 27 (4) (2012) 244 – 259. DOI: https://doi.org/10.1111/j.1467-8667.2011.00736.x
[8] X. Wang, H. Gao, Z. Jia, Z. Li, Bl-yolov8: An improved road defect detection model based on yolov8, Sensors 23 (20) (2023) 8361. DOI: https://doi.org/10.3390/s23208361
[9] S. Chatterjee, P. Saeedfar, S. Tofangchi, L. M. Kolbe, Intelligent Road maintenance: a machine learning approach for surface defect detection., in: ECIS, 2018, p. 194.
[10] A. Mednis, G. Strazdins, R. Zviedris, G. Kanonirs, L. Selavo, Real time pothole detection using android smartphones with accelerometers, in: 2011 International conference on distributed computing in sensor systems and workshops (DCOSS), IEEE, 2011, pp. 1 – 6. DOI: https://doi.org/10.1109/DCOSS.2011.5982206
[11] V. Pereira, S. Tamura, S. Hayamizu, H. Fukai, A deep learning-based approach for road pothole detection in timor leste, in: 2018 IEEE Interna- tional Conference on Service Operations and Logistics, and Informatics (SOLI), IEEE, 2018, pp. 279 – 284. DOI: https://doi.org/10.1109/SOLI.2018.8476795
[12] A. Dhiman, R. Klette, Pothole detection using computer vision and learn- ing, IEEE Transactions on Intelligent Transportation Systems 21 (8) (2019) 3536 – 3550. DOI: https://doi.org/10.1109/TITS.2019.2931297
[13] M. Al-Qizwini, I. Barjasteh, H. Al-Qassab, H. Radha, Deep learning algo- rithm for autonomous driving using googlenet, in: 2017 IEEE intelligent vehicles symposium (IV), IEEE, 2017, pp. 89 – 96. DOI: https://doi.org/10.1109/IVS.2017.7995703
[14] A. Sengupta, Y. Ye, R. Wang, C. Liu, K. Roy, Going deeper in spik- ing neural networks: Vgg and residual architectures, Frontiers in neuro- science 13 (2019) 95. DOI: https://doi.org/10.3389/fnins.2019.00095
[15] Kirillov A, Mintun E, Ravi N, et al. Segment anything [C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2023: 4015 - 4026. DOI: https://doi.org/10.1109/ICCV51070.2023.00371
Downloads
Published
Conference Proceedings Volume
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.