PERTANIKA JOURNAL OF SCIENCE AND TECHNOLOGY

Cracked and potholed roads frequently cause deadly accidents, posing serious safety risks and significant maintenance expenses. Vehicles hitting potholes can damage road furniture, increase maintenance costs, and leave road users with significant repair expenditures for their vehicles. Drivers feel insecure and uncomfortable when continually monitoring road conditions to avoid potholes, which detracts from their entire driving experience. This project seeks to create a Pothole Detection System that employs Convolutional Neural Network (CNN) algorithms to explore feature extraction approaches for identifying road potholes. The model was trained with CNN algorithms to identify photos as a pothole or normal, and You Only Look Once (YOLO) to detect and estimate pothole areas. Two datasets were joined to create a cohesive dataset with 681 images from the first and 4000 images from the second, for 4681 images. These pictures, divided between potholed and typical roads, were cleaned and resized to 256×256 pixels. The dataset was split into two groups: 70% training and 20% testing. Roboflow Annotate was used to annotate images. Following data preparation, the CNN and YOLO algorithms were created independently. The CNN-YOLO model had an accuracy rate of 92.85%. This project increases road safety, infrastructure upkeep, and traffic flow. The pothole detection technology warns drivers about potential road hazards, decreasing accidents and fatalities. Efficient detection allows for preventive, cost-effective road maintenance, optimises government resource allocation, and enhances the driving experience by lowering car maintenance costs and assuring safer roads.

• Arjapure, S., & Kalbande, D. R. (2021). Deep learning model for pothole detection and area computation. In 2021 International Conference on Communication Information and Computing Technology (ICCICT) (pp. 1-6). IEEE Publishing. https://doi.org/10.1109/ICCICT50803.2021.9510073
  
  Bhamare, L., Mitra, N., Varade, G., & Mehta, H. (2021). Study of types of road abnormalities and techniques used for their detection. In 2021 7th International Conference on Electrical, Electronics and Information Engineering (ICEEIE) (pp. 472-477). IEEE Publishing. https://doi.org/10.1109/ICEEIE52663.2021.9616755
  
  Chorada, R., Kriplani, H., & Acharya, B. (2023). CNN-based Real-time pothole detection for avoidance road accident. In 2023 7th International Conference on Intelligent Computing and Control Systems (ICICCS) (pp. 700-707). IEEE Publishing. https://doi.org/10.1109/ICICCS56967.2023.10142488
  
  Chu, H. H., Saeed, M. R., Rashid, J., Mehmood, M. T., Ahmad, I., Iqbal, R. S., & Ali, G. (2023). Deep learning method to detect the road cracks and potholes for smart cities. Computers, Materials & Continua, 75(1), 1863-1881. https://doi.org/10.32604/cmc.2023.035287
  
  Gangatharan, N., Reddy, S., Sathvik. I. V. S., & Sabarish, G. (2023). A comprehensive system for automated pothole detection and vehicle speed management using CNN technology. In 2023 8th International Conference on Communication and Electronics Systems (ICCES) (pp. 749-754). IEEE Publishing. https://doi.org/10.1109/ICCES57224.2023.10192629
  
  Gazawy, Q., Buyrukoğlu, S., & Yılmaz, Y. (2023). Convolutional neural network for pothole detection in different road and weather conditions. Journal of Computer & Electrical and Electronics Engineering Sciences, 1(1), 1-4. https://doi.org/10.51271/JCEEES-0001
  
  Golos, M. (2024). What Causes Potholes? Tensar International Corporation. https://www.tensar.co.uk/resources/articles/what-causes-potholes
  
  Halim, M. H. B. M., Ibrahim, A. B., Osman, M. K., Kader, M. M. M. A., Termizi, M. F. A., & Abu, A. E. M. (2022). Detection of pothole for repair works of asphalt flexible pavement optimization using YOLO. In AIP Conference Proceedings (Vol. 2532, No. 1). AIP Publishing. https://doi.org/10.1063/5.0109961
  
  Hossain, M. S., Angan, R. B., & Hasan, M. M. (2023). Pothole detection and estimation of repair cost in Bangladeshi street: AI-based multiple case analysis. In 2023 International Conference on Electrical, Computer and Communication Engineering (ECCE) (pp. 1-6). IEEE Publishing. https://doi.org/10.1109/ECCE57851.2023.10101579
  
  Kaushik, V., & Kalyan, B. S. (2022). Pothole detection system: A review of different methods used for detection. In 2022 Second International Conference on Computer Science, Engineering and Applications (ICCSEA) (pp. 1-4). IEEE Publishing. https://doi.org/10.1109/ICCSEA54677.2022.9936360
  
  Kim, Y. M., Kim, Y. G., Son, S. Y., Lim, S. Y., Choi, B. Y., & Choi, D. H. (2022). Review of recent automated pothole-detection methods. Applied Sciences, 12(11), Article 5320. https://doi.org/10.3390/app12115320
  
  KKR. (2023). Statistik Jalan Malaysia - Edisi 2023 [Malaysia Road Statistic - 2023 Edition]. KKR. https://www.kkr.gov.my/en/senarai-penerbitan-kkr/buku-statistik-jalan-2023
  
  Kumar, A. (2019). Labelled Image Dataset Containing 300+ Images of Roads Containing Potholes. kaggle. https://www.kaggle.com/datasets/atulyakumar98/pothole-detection-dataset
  
  Kumar, S., Kumar, N., & Barthwal, A. (2023). Road pothole detection using smartphone sensors. Journal of Harbin Engineering University, 44(7), 1341-1346.
  
  Lincy, A., Dhanarajan, G., Kumar, S. S., & Gobinath, B. (2023). Road pothole detection system. In ITM Web of Conferences (Vol. 53, p. 01008). EDP Sciences. https://doi.org/10.1051/itmconf/20235301008
  
  Manzor, Z. (2021, April 6). 206,570 Jalan Berlubang Tahun Lalu [206,570 potholes last year]. Kosmo Digital. https://www.kosmo.com.my/2021/04/06/206570-jalan-berlubang-tahun-lalu/
  
  Noh, N. C. (2021, January 6). 223 Kemalangan Akibat Fizikal Jalan Raya [223 accidents due to the physical condition of the road]. Berita Harian. https://www.bharian.com.my/berita/kes/2021/01/773051/223-kemalangan-akibat-fizikal-jalan-raya
  
  Othman, M. Z. (2023, May 15). Jalan Umpama di Bulan, ‘Korek Tampal’ Sampai Bila? [Like walking on the moon, how long will ‘lightning and patching’ last?] StraComm USIM. https://www.usim.edu.my/news/in-our-words/jalan-umpama-di-bulan-korek-tampal-sampai-bila/
  
  Pratama, I. D., Mahmudah, H., & Sudibyo, R. W. (2021). Design and implementation of real-time pothole detection using convolutional neural network for IoT smart environment. In 2021 International Electronics Symposium (IES) (pp. 675-679). IEEE Publishing. https://doi.org/10.1109/IES53407.2021.9594038
  
  Ranyal, E., Sadhu, A., & Jain, K. (2023). AI assisted pothole detection and depth estimation. In 2023 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing (MIGARS) (Vol. 1, pp. 1-4). IEEE Publishing. https://doi.org/10.1109/MIGARS57353.2023.10064547
  
  Saisree, C., & Kumaran, U. (2023). Pothole detection using deep learning classification method. Procedia Computer Science, 218, 2143-2152. https://doi.org/https://doi.org/10.1016/j.procs.2023.01.190
  
  Sartika, Zainuddin, Z., & Ilham, A. A. (2023). Detection and classification of road damage using camera with GLCM and SVM. In 2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT) (pp. 372-376). IEEE Publishing. https://doi.org/10.1109/IAICT59002.2023.10205539
  
  Sharma, M., Saripalli, S. R., Gupta, A. K., Talwar, R., Dadheech, P., & Kanike, U. K. (2023). Real-time pothole detection during rainy weather using dashboard cameras for driverless cars. In Handbook of Research on Thrust Technologies’ Effect on Image Processing (pp. 384-394). IGI Global. https://doi.org/10.4018/978-1-6684-8618-4.ch023
  
  Vinodhini, K. A., & Sidhaarth, K. R. A. (2024). Pothole detection in bituminous road using CNN with transfer learning. Measurement: Sensors, 31, Article 100940. https://doi.org/https://doi.org/10.1016/j.measen.2023.100940
  
  Wang, W., & Ho, Y. (2022). Pothole-related traffic safety detection based on deep learning. In 2022 15th International Conference on Human System Interaction (HSI) (pp. 1-6). IEEE Publishing. https://doi.org/10.1109/HSI55341.2022.9869460