Deploying Edge AI for Road Surface Damage Detection Using TensorFlow Lite and Teachable Machine
DOI:
https://doi.org/10.57152/malcom.v5i4.2067Keywords:
Edge AI, Infrastructure Monitoring, Mobile Deployment, Teachable Machine, Tensorflow Lite, Road Damage DetectionAbstract
Road damage compromises transportation safety and drives high infrastructure maintenance costs. To address the limitations of traditional methods, which are expensive and non-scalable, this study proposes an Edge AI alternative utilizing widely available smartphones and machine learning capabilities. We present a real-time road damage detection system powered by TensorFlow Lite and Teachable Machine. The system architecture employs lightweight CNN models (such as MobileNet and EfficientNet Lite) optimized for edge deployment. This implementation enables the immediate detection of anomalies (cracks and potholes) directly on the mobile device without cloud dependency, ensuring low latency. Testing demonstrated robust model performance. For pothole detection, the system achieved an accuracy of 95%; for cracks, the accuracy was 92%. During real-time trials in daytime urban settings, the system achieved an average detection latency of 200 milliseconds with an accuracy of 94%. This user-friendly system also supports data collection via crowdsourcing, facilitating comprehensive infrastructure monitoring and proactive maintenance. This innovation offers a scalable, cost-effective, and user-friendly solution with significant potential to advance transportation safety and maintenance efficiency.
Downloads
References
G. Singh, D. Bansal, S. Sofat, and N. Aggarwal, “Smart patrolling: An efficient road surface monitoring using smartphone sensors and crowdsourcing,” Pervasive Mob. Comput., vol. 40, pp. 71–88, 2017, doi: 10.1016/j.pmcj.2017.06.002.
A. Ramesh et al., “Cloud-Based Collaborative Road-Damage Monitoring with Deep Learning and Smartphones,” Sustainability, 2022, doi: 10.3390/su14148682.
D. Dong and Z. Li, “Smartphone Sensing of Road Surface Condition and Defect Detection,” Sensors (Basel)., vol. 21, 2021, doi: 10.3390/s21165433.
C. Wu et al., “An Automated Machine-Learning Approach for Road Pothole Detection Using Smartphone Sensor Data,” Sensors (Basel)., vol. 20, 2020, doi: 10.3390/s20195564.
A. Allouch, A. Koubâa, T. Abbes, and A. Ammar, “RoadSense: Smartphone Application to Estimate Road Conditions Using Accelerometer and Gyroscope,” IEEE Sens. J., vol. 17, pp. 4231–4238, 2017, doi: 10.1109/JSEN.2017.2702739.
A. Basavaraju, J. Du, F. Zhou, and J. Ji, “A Machine Learning Approach to Road Surface Anomaly Assessment Using Smartphone Sensors,” IEEE Sens. J., vol. 20, no. 5, pp. 2635–2647, Mar. 2020, doi: 10.1109/JSEN.2019.2952857.
S. Ebadinezhad, K. A. Stanley, G. M. Engo, N. K. Osemeha, and A. S. Mayar, “The Impact of AI on Traffic Management and Safety in the Internet of Vehicles through Mobile Edge Computing,” 2024 Int. Conf. Inven. Comput. Technol., pp. 319–326, 2024, doi: 10.1109/ICICT60155.2024.10544636.
E. Ranyal, A. Sadhu, and K. Jain, “Road Condition Monitoring Using Smart Sensing and Artificial Intelligence: A Review,” Sensors (Basel)., vol. 22, 2022, doi: 10.3390/s22083044.
M. Hijji et al., “6G Connected Vehicle Framework to Support Intelligent Road Maintenance Using Deep Learning Data Fusion,” IEEE Trans. Intell. Transp. Syst., vol. 24, pp. 7726–7735, 2023, doi: 10.1109/TITS.2023.3235151.
M. Waseem Khan et al., “Real-Time Road Damage Detection and Infrastructure Evaluation Leveraging Unmanned Aerial Vehicles and Tiny Machine Learning,” IEEE Internet Things J., vol. 11, no. 12, pp. 21347–21358, Jun. 2024, doi: 10.1109/JIOT.2024.3385994.
S. Dhaiphule, “Review of AI based Techniques for Road Damage Detection,” Int. J. Res. Appl. Sci. Eng. Technol., 2023, doi: 10.22214/ijraset.2023.54532.
K.-Y. Liao, “Road Damage Intelligent Detection with Deep Learning Techniques,” 2022 IEEE 5th Int. Conf. Inf. Syst. Comput. Aided Educ., pp. 795–799, 2022, doi: 10.1109/ICISCAE55891.2022.9927635.
L. A. Silva, V. R. Q. Leithardt, V. F. L. Batista, G. Villarrubia González, and J. F. De Paz Santana, “Automated Road Damage Detection Using UAV Images and Deep Learning Techniques,” IEEE Access, vol. 11, pp. 62918–62931, 2023, doi: 10.1109/ACCESS.2023.3287770.
D. N. Puspita, D. K. Basuki, and B. S. B. Dewantara, “Road Damage Detection and Alert Application Using Smartphone’s Built-In Sensors,” in 2022 International Electronics Symposium (IES), IEEE, Aug. 2022, pp. 506–510. doi: 10.1109/IES55876.2022.9888366.
W.-C. Chiang, H.-S. Chiu, and J.-S. Lee, “Road Damage Detection Using Deep Learning and Cloud Platforms,” 2023 Int. Conf. Consum. Electron. - Taiwan, pp. 859–860, 2023, doi: 10.1109/ICCE-Taiwan58799.2023.10226984.
X. Dang, X. Shang, Z. Hao, and L. Su, “Collaborative Road Damage Classification and Recognition Based on Edge Computing,” Electronics, 2022, doi: 10.3390/electronics11203304.
H. Tahir and E.-S. Jung, “Comparative Study on Distributed Lightweight Deep Learning Models for Road Pothole Detection,” Sensors (Basel)., vol. 23, 2023, doi: 10.3390/s23094347.
H. Haniah, A. Musyafa, A. Siti Aisjah, S. Arifin, & C. A. Prastyanto. (2025). Detecting road damage utilizing RetinaNet and MobileNet models on edge devices. IAES International Journal of Artificial Intelligence (IJ-AI).
S. Swain, & A. K. Tripathy. (2024). Automatic detection of potholes and cracks in road surface using deep learning. International Journal of Computer Trends and Technology.
S. Zhang, X. He, B. Xue, T. Wu, K. Ren, & T. Zhao. (2024). Segment-anything embedding for pixel-level road damage extraction using high-resolution satellite images. Int. J. Appl. Earth Obs. Geoinf., 131.
I. Himmati, I. P. Prawesti, & A. A. Brahmantya. (2025). Real-Time Road Damage Detection on Mobile Devices using TensorFlow Lite and Teachable Machine. MALCOM: Journal of Information Systems and Management.
D. S. Triardhana. (2021). Road Damage Identification Using Deep Learning Method Convolutional Neural Networks Model. Jurnal Geodesi Undip, 164–173.
Y. Wang, Z. Fan, M. Zhao, Z. Wang, & Y. Lu. (2022). Automatic Recognition of Road Damage Based on Lightweight Attentional Convolutional Neural Network. Sensors, 22, 9599.
B. M. Alahmari, A. J. Alharbi, S. K. A. Alghamdi, M. S. Alsubaie, & M. K. Almutairi. (2023). Road Damage Detection Based on Deep Learning. International Journal of Advanced Computer Science and Applications.
M. Z. A. Sari, B. A. Setyono, T. R. Murti, & B. Y. Bima. (2023). Accuracy of Hybrid Models of Detection, Classification, and Quantification for Automatic Road Damage Evaluation. Jurnal Teknologi Informasi dan Ilmu Komputer.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Iren Damayanti, Zico Pratama Putra
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright © by Author; Published by Institut Riset dan Publikasi Indonesia (IRPI)
This Indonesian Journal of Machine Learning and Computer Science is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
