Automated Detection of Road Defects Using LSTM and Random Forest
Open Access
- 24 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 76857-76867
Abstract
Road networks represent an essential factor in economic prosperity and well-being. The transporta-tion efficiency and driving safety of road networks are mainly impacted by assorted damages and defects on the road surface. In current traditions, it may take weeks or even months before competent government departments repair such road conditions, fundamentally due to the lack of timely awareness of them. This research proposes a framework for collecting data and analysis using supervised machine learning (ML) techniques, more specifically Long/Short-Term Memory (LSTM), Random Forest (RF), and networked sensor-enhanced vehicles for effective and efficient monitor-ing and assessment of road surface conditions. Data collected in four different scenarios and multiple vehicle data help to discover abnormal defects and verify automated detection. ML techniques were developed to identify bumps and potholes automatically, which are the two significant types of road defects. The experiment results of both LSTM and RF models can automatically identify the bumps and potholes defects with an accuracy rate of up to 99.8%, using a good detection effect. Cross-validation was set to validate the accuracy of the two decision-making strategies, LSTM and RF. It is expected that automation technology can provide both qualitative and quantitative information about road defect conditions and hence enable timely maintenance to improve transportation efficiency and driving safety.Keywords
This publication has 22 references indexed in Scilit:
- Determination of threshold of asphalt pavement structure crack damage rate to quantify the severity of structural crack damageInternational Journal of Pavement Engineering, 2024
- Deep learning-based intelligent detection of pavement distressAutomation in Construction, 2024
- A Review on Applications of Drones in Geotechnical EngineeringIndian Geotechnical Journal, 2024
- Automatic detection and location of pavement internal distresses from ground penetrating radar images based on deep learningConstruction and Building Materials, 2023
- Deep Learning–Based Autonomous Road Condition Assessment Leveraging Inexpensive RGB and Depth Sensors and Heterogeneous Data Fusion: Pothole Detection and QuantificationJournal of Transportation Engineering, Part B: Pavements, 2023
- Machine learning techniques for pavement condition evaluationAutomation in Construction, 2022
- Do Vehicles Sense, Detect and Locate Speed Bumps?Transportation Research Procedia, 2021
- Automated pavement distress detection using region based convolutional neural networksInternational Journal of Pavement Engineering, 2020
- Automated Detection of Multiple Pavement DefectsJournal of Computing in Civil Engineering, 2017
- Structural Health Monitoring: State of the Art and PerspectivesJOM, 2012