Fully Convolutional Networks for Automatic Pavement Crack Segmentation

Pavement cracks are an increasing threat to public safety. Automatic pavement crack segmentation remains a very challenging problem due to crack texture inhomogeneity, high outlier potential, large variability of topologies, and so on. Due to this, automatic pavement crack detection has captured the attention of the computer vision community, and a great quantity of algorithms for solving this task have been proposed. In this work, we study a U-Net network and two variants for automatic pavement crack detection. The main contributions of this research are: 1) two U-Net based network variations for automatic pavement crack detection, 2) a series of experiments to demonstrate that the proposed architectures outperform the state-of-the-art for automatic pavement crack detection using two public and well-known challenging datasets: CFD and AigleRN and 3) the code for this approach.

[1]  Fan Meng,et al.  Automatic Road Crack Detection Using Random Structured Forests , 2016, IEEE Transactions on Intelligent Transportation Systems.

[2]  Zhun Fan,et al.  Automatic Pavement Crack Detection Based on Structured Prediction with the Convolutional Neural Network , 2018, ArXiv.

[3]  Siddhartha Kumar Khaitan,et al.  Deep Convolutional Neural Networks with transfer learning for computer vision-based data-driven pavement distress detection , 2017 .

[4]  Norman W. Garrick,et al.  SEGMENTATION ALGORITHM USING ITERATIVE CLIPPING FOR PROCESSING NOISY PAVEMENT IMAGES , 1998 .

[5]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[7]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[8]  Oral Büyüköztürk,et al.  Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks , 2017, Comput. Aided Civ. Infrastructure Eng..

[9]  Yang Liu,et al.  Automated Pixel‐Level Pavement Crack Detection on 3D Asphalt Surfaces Using a Deep‐Learning Network , 2017, Comput. Aided Civ. Infrastructure Eng..

[10]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Hui-li Zhao,et al.  Improvement of canny algorithm based on pavement edge detection , 2010, 2010 3rd International Congress on Image and Signal Processing.

[12]  Mohamed S Kaseko,et al.  A neural network-based methodology for pavement crack detection and classification , 1993 .

[13]  S A Velinsky,et al.  Histogram‐Based Approach for Automated Pavement‐Crack Sensing , 1992 .

[14]  Graham W. Taylor,et al.  Adaptive deconvolutional networks for mid and high level feature learning , 2011, 2011 International Conference on Computer Vision.

[15]  S. Palanivel,et al.  An Efficient Framework to Detect Cracks in Rail Tracks Using Neural Network Classifier , 2018, Computación y Sistemas.

[16]  Jérôme Idier,et al.  Automatic Crack Detection on Two-Dimensional Pavement Images: An Algorithm Based on Minimal Path Selection , 2016, IEEE transactions on intelligent transportation systems (Print).

[17]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[18]  Manuel Avila,et al.  Automatic detection and classification of defect on road pavement using anisotropy measure , 2009, 2009 17th European Signal Processing Conference.

[19]  Manuel Avila,et al.  Free-form anisotropy: A new method for crack detection on pavement surface images , 2011, 2011 18th IEEE International Conference on Image Processing.

[20]  Qingquan Li,et al.  Novel Approach to Pavement Image Segmentation Based on Neighboring Difference Histogram Method , 2008, 2008 Congress on Image and Signal Processing.

[21]  Heng-Da Cheng,et al.  Novel Approach to Pavement Cracking Detection Based on Fuzzy Set Theory , 1999 .

[22]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[23]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.