A Deep Convolutional Neural Network for Semantic Pixel-Wise Segmentation of Road and Pavement Surface Cracks

Abstract

Deterioration of road and pavement surface conditions is an issue which directly affects the majority of the world today. The complex structure and textural similarities of surface cracks, as well as noise and image illumination variation makes automated detection a challenging task. In this paper, we propose a deep fully convolutional neural network to perform pixel-wise classification of surface cracks on road and pavement images. The network consists of an encoder layer which reduces the input image to a bank of lower level feature maps. This is followed by a corresponding decoder layer which maps the encoded features back to the resolution of the input data using the indices of the encoder pooling layers to perform efficient up-sampling. The network is finished with a classification layer to label individual pixels. Training time is minimal due to the small amount of training/validation data (80 training images and 20 validation images). This is important due to the lack of applicable public data available. Despite this lack of data, we are able to perform image segmentation (pixel-level classification) on a number of publicly available road crack datasets. The network was tested extensively and the results obtained indicate performance in direct competition with that of the current stateof-the-art methods.

Pavement Distress Detection with Deep Learning Using the Orthoframes Acquired by a Mobile Mapping System

“…While most neural network methods utilize custom made neural networks, there are papers that build on existing neural networks. For example, the work in [67] partly used a pretrained VGG; the work in [9] utilized YOLOv2 [68]; whereas the works in [7,8] built on U-Net [69]. Neural networks combined with image histograms and other separate feature extraction methods have been applied for these problems as well [70].…”

“…It is possible that some of the differences in results are due to the quality of input data. For example, the work in [7,8] used the publicly available CrackForest dataset with 117 images. The work in [14], on the other hand, used 3900 raw images captured by a NIKON digital camera with a resolution of 3456 × 4608 pixels where the camera took pictures between the ground and the camera with an approximate distance from 80 cm to 100 cm.…”

Regularized Auto-Encoder-Based Separation of Defects from Backgrounds for Inspecting Display Devices

“…Convolutional auto-encoder based pixel-wise segmentation methods have been successfully applied for several applications [20][21][22]. These methods predict the probability of each pixel belonging to some class that can be used to classify each pixel into different classes, naturally resulting in pixel-wise segmentation.…”

Dynamic Pavement Distress Image Stitching Based on Fine-Grained Feature Matching

“…Gopalakrishnan et al employed a deep CNN with transfer learning for pavement distress detection [19]. Jenkins et al proposed a deep fully CNN to perform pixel-wise classification of surface cracks on roads and pavement images with 92.46% precision [20].…”