Road surface condition monitoring is critical for ensuring safe and efficient transportation networks. This study presents a multi-sensor framework that integrates imagery, LiDAR, and accelerometer-based approaches for pavement anomaly detection. The analysis first focuses on a 5-mile urban roadway segment, where all sensing modalities are evaluated under identical survey conditions to compare detection accuracy, severity classification, and processing efficiency. Imagery-based analysis using a CT-CrackSeg network successfully identifies cracks and potholes but remains sensitive to environmental conditions such as lighting and shadows. LiDAR-based methods achieve centimeter-level precision in detecting surface deviations ≥ 2 cm at highway speeds, albeit with high acquisition and processing costs. Accelerometer-based monitoring using survey-, mapping-, and consumer-grade systems demonstrates strong potential as a low-cost alternative. Two detection strategies—Isolation Forest and Adaptive Threshold—are applied to vertical acceleration data, showing high consistency with LiDAR detections and general agreement with imagery-based results. Given its strong agreement with LiDAR and imagery, minimal processing requirements, and low deployment cost, the accelerometer-based approach is extended to a 36-mile network to evaluate scalability. Across the full route, spatial and method correlations exceed 0.91 and 0.96, respectively, with 962–996 surface defects detected depending on the sensor and method. Integrating anomaly detection results into a Potree-based web portal enabled interactive validation with geotagged imagery and point clouds, improving interpretability and diagnostic insight. The results demonstrate that accelerometer-based monitoring provides a practical, scalable, and cost-effective solution for pavement evaluation, while LiDAR and imagery serve as complementary tools for detailed verification and characterization.
Road surface condition monitoring is critical for ensuring safe and efficient transportation networks. This study presents a multi-sensor framework that integrates imagery, LiDAR, and accelerometer-based approaches for pavement anomaly detection. The analysis first focuses on a 5-mile urban roadway segment, where all sensing modalities are evaluated under identical survey conditions to compare detection accuracy, severity classification, and processing efficiency. Imagery-based analysis using a CT-CrackSeg network successfully identifies cracks and potholes but remains sensitive to environmental conditions such as lighting and shadows. LiDAR-based methods achieve centimeter-level precision in detecting surface deviations ≥ 2 cm at highway speeds, albeit with high acquisition and processing costs. Accelerometer-based monitoring using survey-, mapping-, and consumer-grade systems demonstrates strong potential as a low-cost alternative. Two detection strategies—Isolation Forest and Adaptive Threshold—are applied to vertical acceleration data, showing high consistency with LiDAR detections and general agreement with imagery-based results. Given its strong agreement with LiDAR and imagery, minimal processing requirements, and low deployment cost, the accelerometer-based approach is extended to a 36-mile network to evaluate scalability. Across the full route, spatial and method correlations exceed 0.91 and 0.96, respectively, with 962–996 surface defects detected depending on the sensor and method. Integrating anomaly detection results into a Potree-based web portal enabled interactive validation with geotagged imagery and point clouds, improving interpretability and diagnostic insight. The results demonstrate that accelerometer-based monitoring provides a practical, scalable, and cost-effective solution for pavement evaluation, while LiDAR and imagery serve as complementary tools for detailed verification and characterization.