An Improved ResNet50 Model for Predicting Pavement Condition Index (PCI) Directly from Pavement Images

2025-04-25

AI Summary

Direct regression of the Pavement Condition Index (PCI) from pavement images remains challenging due to the need for fine-grained localization of distress features without manual annotations or intermediate metrics. To address this, we propose an end-to-end attention-enhanced ResNet50 model, the first to integrate the Convolutional Block Attention Module (CBAM) into the ResNet50 backbone, enabling adaptive spatial-channel weighting to focus on critical distress regions—such as cracks and potholes—without handcrafted features or region proposals. The model is trained via end-to-end supervised regression. Evaluated on a real-world pavement image dataset, it achieves a mean absolute percentage error (MAPE) of 58.16%, outperforming baseline ResNet50 (70.76%) and DenseNet161 (65.48%). This demonstrates the efficacy of attention mechanisms in fine-grained PCI regression. Our approach establishes a new, interpretable, and high-accuracy paradigm for intelligent pavement inspection and infrastructure condition assessment.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Calibration & Uncertainty Quantification
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Accurately predicting the Pavement Condition Index (PCI), a measure of roadway conditions, from pavement images is crucial for infrastructure maintenance. This study proposes an enhanced version of the Residual Network (ResNet50) architecture, integrated with a Convolutional Block Attention Module (CBAM), to predict PCI directly from pavement images without additional annotations. By incorporating CBAM, the model autonomously prioritizes critical features within the images, improving prediction accuracy. Compared to the original baseline ResNet50 and DenseNet161 architectures, the enhanced ResNet50-CBAM model achieved a significantly lower mean absolute percentage error (MAPE) of 58.16%, compared to the baseline models that achieved 70.76% and 65.48% respectively. These results highlight the potential of using attention mechanisms to refine feature extraction, ultimately enabling more accurate and efficient assessments of pavement conditions. This study emphasizes the importance of targeted feature refinement in advancing automated pavement analysis through attention mechanisms.

Problem

• Predicting Pavement Condition Index from images accurately
• Improving ResNet50 with CBAM for better feature prioritization
• Reducing prediction error in automated pavement condition assessment

Innovation

• Enhanced ResNet50 with CBAM for PCI prediction
• CBAM prioritizes critical features autonomously
• Lower MAPE than baseline models achieved