The week's pick
Random Articles
Reseach Article
Improving Road Safety through Deep Learning-based Approaches for Road Damage Detection and Classification
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 186 - Number 76 |
| Year of Publication: 2025 |
| Authors: Md. Mahadi Hasan, Boshir Ahmed |
10.5120/ijca2025924660
|
Md. Mahadi Hasan, Boshir Ahmed . Improving Road Safety through Deep Learning-based Approaches for Road Damage Detection and Classification. International Journal of Computer Applications. 186, 76 ( Apr 2025), 1-8. DOI=10.5120/ijca2025924660
Abstract
Transportation heavily depends on roads, which require proper maintenance for safe and efficient travel. Traditional manual inspection methods are time consuming, labor-intensive and pose safety risks. To address these challenges, Deep learning models are presented for road damage detection using two benchmark datasets: RDD-2020 and RDD-2022. This study compares five models integrating feature extractors such as ResNet-50, ResNet-101, and MobileNetv3 with detection frameworks like Faster R-CNN, SSD, and YOLO. Among them, YOLOv10 achieved the best performance. Fine-tuning with the Adam optimizer and a batch size of four improved its F1 scores to 0.67 for RDD-2022 and 0.63 for RDD-2020. Additionally, the CrackBD-2024 dataset was developed, consisting of 2,038 images with 5,060 instances from Bangladeshi roads, to enhance the generalization of the models. This work contributes to advancing road damage detection, improving monitoring, and facilitating better maintenance planning.
References
- Md Mahadi Hasan, Saadman Sakib, and Kaushik Deb. Road damage detection and classification using deep neural network. In 2022 4th International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE), pages 1–6. IEEE, 2022.
- Yingchao Zhang and Cheng Liu. Real-time pavement damage detection with damage shape adaptation. IEEE Transactions on Intelligent Transportation Systems, 2024.
- Dipankar Dutta and Rudranath Banerjee. Indian road damage detection using deep learning. In Advancements in Intelligent Process Automation, pages 223–262. IGI Global, 2025.
- Nik Ahmad Farihin Mohd Zulkifli, Zuriani Mustaffa, and Mohd Herwan Sulaiman. Road damage detection for autonomous driving vehicles using yolov8 and salp swarm algorithm. Applications of Modelling and Simulation, 9:1–11, 2025.
- Devesh Mothilall and Terence van Zyl. Improving road damage maintenance in south africa using deep learning. In 2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA), pages 1–5. IEEE, 2024.
- Yiwen Jiang. Road damage detection and classification using deep neural networks. Discover Applied Sciences, 6(8):421, 2024.
- Yue Li, Chang Yin, Yutian Lei, Jiale Zhang, and Yiting Yan. Rdd-yolo: Road damage detection algorithm based on improved you only look once version 8. Applied Sciences, 14(8):3360, 2024.
- Tian-Yi Jiang, Zhi-Yang Liu, and Guang-Zhu Zhang. Yolov5s-road: Road surface defect detection under engineering environments based on cnn-transformer and adaptively spatial feature fusion. Measurement, 242:115990, 2025.
- Qihan He, Zhongxu Li, and Wenyuan Yang. Lsf-rdd: a local sensing feature network for road damage detection. Pattern Analysis and Applications, 27(3):99, 2024.
- Vaishnavee V Rathod, Dipti P Rana, and Rupa G Mehta. Deep learning-driven uav vision for automated road crack detection and classification. Nondestructive Testing and Evaluation, pages 1–30, 2025.
- Robert G De Luna, Mariano G Abejo, Beatriz M Aldave, Ruth Hannah P Barrete, Jewel L Lim, Hazel M Mendoza, Myka Sydney Morcoso, and Karina L Enriquez. Enhancing road safety: A cnn-based approach to road damage classification. In 2024 IEEE International Conference on Imaging Systems and Techniques (IST), pages 1–6. IEEE, 2024.
- Muhammad Waseem Khan, Mohammad S Obaidat, Khalid Mahmood, Dania Batool, Hafiz Muhammad Sanaullah Badar, Muhammad Aamir, and Wu Gao. Real-time road damage detection and infrastructure evaluation leveraging unmanned aerial vehicles and tiny machine learning. IEEE Internet of Things Journal, 2024.
- Deeksha Arya, Hiroya Maeda, Sanjay Kumar Ghosh, Durga Toshniwal, and Yoshihide Sekimoto. Rdd2020: An annotated image dataset for automatic road damage detection using deep learning. Data in brief, 36:107133, 2021.
- Deeksha Arya, Hiroya Maeda, Sanjay Kumar Ghosh, Durga Toshniwal, and Yoshihide Sekimoto. Rdd2022: A multinational image dataset for automatic road damage detection. Geoscience Data Journal, 11(4):846–862, 2024.
- Brett Koonce and B Efficientnet Koonce. Convolutional neural networks with swift for tensorflow: Image recognition and dataset categorization. Springer, 2021.
- Qi Zhang. A novel resnet101 model based on dense dilated convolution for image classification. SN Applied Sciences, 4:1–13, 2022.
- Prasad SP Kavyashree and Mohamed El-Sharkawy. Compressed mobilenet v3: a light weight variant for resourceconstrained platforms. In 2021 IEEE 11th annual computing and communication workshop and conference (CCWC), pages 0104–0107. IEEE, 2021.
- Alexander Womg, Mohammad Javad Shafiee, Francis Li, and Brendan Chwyl. Tiny ssd: A tiny single-shot detection deep convolutional neural network for real-time embedded object detection. In 2018 15th Conference on computer and robot vision (CRV), pages 95–101. IEEE, 2018.
- Mujadded Al Rabbani Alif and Muhammad Hussain. Yolov1 to yolov10: A comprehensive review of yolo variants and their application in the agricultural domain. arXiv preprint arXiv:2406.10139, 2024.
Index Terms
Keywords