Automated Pavement Crack Segmentation Using U-Net-based Convolutional Neural Network

Abstract

Automated pavement crack image segmentation is challenging because of inherent irregular patterns, lighting conditions, and noise in images. Conventional approaches require a substantial amount of feature engineering to differentiate crack regions from non-affected regions. In this paper, we propose a deep learning technique based on a convolutional neural network to perform segmentation tasks on pavement crack images. Our approach requires minimal feature engineering compared to other machine learning techniques. We propose a U-Net-based network architecture in which we replace the encoder with a pretrained ResNet-34 neural network. We use a "one-cycle" training schedule based on cyclical learning rates to speed up the convergence. Our method achieves an F1 score of 96% on the CFD dataset and 73% on the Crack500 dataset, outperforming other algorithms tested on these datasets. We perform ablation studies on various techniques that helped us get marginal performance boosts, i.e., the addition of spatial and channel squeeze and excitation (SCSE) modules, training with gradually increasing image sizes, and training various neural network layers with different learning rates.

Accepted for publication in IEEE Access

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Decoupled Weight Decay Regularization
• How transferable are features in deep neural networks?
• fastai: A Layered API for Deep Learning
• A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay
• The Marginal Value of Adaptive Gradient Methods in Machine Learning
• ResNeSt: Split-Attention Networks
• Automatic Pavement Crack Detection Based on Structured Prediction with the Convolutional Neural Network

Cited by in corpus (10)

• Damage detection using in-domain and cross-domain transfer learning
• Deep Learning for Segmentation of Cracks in High-Resolution Images of Steel Bridges
• PaveSAM Segment Anything for Pavement Distress
• CrackNex: a Few-shot Low-light Crack Segmentation Model Based on Retinex Theory for UAV Inspections
• Crack Semantic Segmentation using the U-Net with Full Attention Strategy
• Automatic UAV-based Airport Pavement Inspection Using Mixed Real and Virtual Scenarios
• Segmentation method of U-net sheet metal engineering drawing based on CBAM attention mechanism
• Self-Supervised Multi-Scale Transformer with Attention-Guided Fusion for Efficient Crack Detection
• Convolutional neural networks for crack detection on flexible road pavements
• Minimizing Labeling Effort for Tree Skeleton Segmentation using an Automated Iterative Training Methodology