Automatic Pavement Crack Detection Based on Structured Prediction with the Convolutional Neural Network

Abstract

Automated pavement crack detection is a challenging task that has been researched for decades due to the complicated pavement conditions in real world. In this paper, a supervised method based on deep learning is proposed, which has the capability of dealing with different pavement conditions. Specifically, a convolutional neural network (CNN) is used to learn the structure of the cracks from raw images, without any preprocessing. Small patches are extracted from crack images as inputs to generate a large training database, a CNN is trained and crack detection is modeled as a multi-label classification problem. Typically, crack pixels are much fewer than non-crack pixels. To deal with the problem with severely imbalanced data, a strategy with modifying the ratio of positive to negative samples is proposed. The method is tested on two public databases and compared with five existing methods. Experimental results show that it outperforms the other methods.

References in corpus (2)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition

Cited by in corpus (19)

• Road Damage Detection Using Deep Neural Networks with Images Captured Through a Smartphone
• Deep Machine Learning Approach to Develop a New Asphalt Pavement Condition Index
• Automated Pavement Crack Segmentation Using U-Net-based Convolutional Neural Network
• Pavement Image Datasets: A New Benchmark Dataset to Classify and Densify Pavement Distresses
• Ensemble of Deep Convolutional Neural Networks for Automatic Pavement Crack Detection and Measurement
• Optimized Deep Encoder-Decoder Methods for Crack Segmentation
• Transfer Learning-based Road Damage Detection for Multiple Countries
• Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function
• FPCNet: Fast Pavement Crack Detection Network Based on Encoder-Decoder Architecture
• Deep Learning for Segmentation of Cracks in High-Resolution Images of Steel Bridges
• CrackCLF: Automatic Pavement Crack Detection based on Closed-Loop Feedback
• A Deep Neural Networks Approach for Pixel-Level Runway Pavement Crack Segmentation Using Drone-Captured Images
• Advances in deep learning methods for pavement surface crack detection and identification with visible light visual images
• Crack Detection as a Weakly-Supervised Problem: Towards Achieving Less Annotation-Intensive Crack Detectors
• Image-based reconstruction for the impact problems by using DPNNs
• Pushing the Envelope of Thin Crack Detection
• AnoNet: Weakly Supervised Anomaly Detection in Textured Surfaces
• Image-based Detection of Surface Defects in Concrete during Construction
• Application of Deep Convolutional Neural Networks for automated and rapid identification and characterization of thin cracks in SHCCs