Recognition of asphalt pavement crack length using deep convolutional neural networks

Crack length measurement is an important part of asphalt pavement detection. However, some crack measurement techniques cannot satisfy the needs of accuracy and efficiency. This study discusses application of deep convolutional neural networks (DCNN) in automatic recognition of pavement crack length in batches. Original red, green and blue images were transformed to grey-scale images to calculate their threshold and pre-extract cracks’ properties by k-means clustering analysis. Then the pre-extracted crack images were used as both training and testing samples. The process of accomplishing DCNN to recognise the crack length included the structure designing, training, and testing of the networks. The output results of well-trained DCNN were compared with those of the actual measurement to verify the accuracy of the networks. The result indicates that the training strategy including two processes overcomes the lack of crack labelled images and improves the accuracy of the network, combining with quadrature encoding and stochastic gradient descent. Recognition accuracy of DCNN is 94.36%, maximum length error is 1 cm and mean squared error is 0.2377. The error rates of length ranges 6–7 cm and 7–8 cm are bigger than other ranges Therefore, the networks can be adopted to measure the crack length accurately, but more 6–8 cm crack images should be used to improve the accuracy of the networks in future.

[1]  Shihong Du,et al.  Learning multiscale and deep representations for classifying remotely sensed imagery , 2016 .

[2]  G. Shafabakhsh,et al.  Artificial neural network modeling (ANN) for predicting rutting performance of nano-modified hot-mix asphalt mixtures containing steel slag aggregates , 2015 .

[3]  M. A. Khanesar,et al.  Gradient Descent Methods for Type-2 Fuzzy Neural Networks , 2016 .

[4]  Jason A Griggs,et al.  Three-dimensional finite element modelling of all-ceramic restorations based on micro-CT. , 2013, Journal of dentistry.

[5]  Razvan Pascanu,et al.  Learning Algorithms for the Classification Restricted Boltzmann Machine , 2012, J. Mach. Learn. Res..

[6]  F. Blais,et al.  Automated pavement distress data collection and analysis: a 3-D approach , 1997, Proceedings. International Conference on Recent Advances in 3-D Digital Imaging and Modeling (Cat. No.97TB100134).

[7]  Krzysztof Sopyla,et al.  Stochastic Gradient Descent with Barzilai-Borwein update step for SVM , 2015, Inf. Sci..

[8]  B. V. Venkatarama Reddy,et al.  Prediction of compressive strength of SCC and HPC with high volume fly ash using ANN , 2009 .

[9]  Chalavadi Krishna Mohan,et al.  Human action recognition using genetic algorithms and convolutional neural networks , 2016, Pattern Recognit..

[10]  Edward K. Wong,et al.  Dual many-to-one-encoder-based transfer learning for cross-dataset human action recognition , 2016, Image Vis. Comput..

[11]  Makoto Nagao,et al.  Automatic Pavement-Distress-Survey System , 1990 .

[12]  Haiyang Jiang,et al.  The relationships between asphalt ageing in lab and field based on the neural network , 2015 .

[13]  Xiang Bai,et al.  Script identification in the wild via discriminative convolutional neural network , 2016, Pattern Recognit..

[14]  Yan Wang,et al.  Dense crowd counting from still images with convolutional neural networks , 2016, J. Vis. Commun. Image Represent..

[15]  Ligang Liu,et al.  Upright orientation of 3D shapes with Convolutional Networks , 2016, Graph. Model..

[16]  Lei Si,et al.  Numerical and experimental study on liquid crystal optical phased array beam steering combined with stochastic parallel gradient descent algorithm , 2016 .

[17]  XiongZhang,et al.  3D object retrieval with stacked local convolutional autoencoder , 2015 .

[18]  Yuan Dong,et al.  Automatic age estimation based on deep learning algorithm , 2016, Neurocomputing.

[19]  Yoshua Bengio,et al.  Joint Training of Deep Boltzmann Machines , 2012, ArXiv.

[20]  Stéphan Clémençon,et al.  Scalability of Stochastic Gradient Descent based on "Smart" Sampling Techniques , 2015, INNS Conference on Big Data.

[21]  Kelvin C. P. Wang,et al.  Automated Pavement Horizontal Curve Measurement Methods Based on Inertial Measurement Unit and 3D Profiling Data , 2016 .

[22]  Zhang Xiong,et al.  3D object retrieval with stacked local convolutional autoencoder , 2015, Signal Process..

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

[24]  Xianming Shi,et al.  Applying artificial neural networks and virtual experimental design to quality improvement of two industrial processes , 2004 .

[25]  A. Senov.  Improving Distributed Stochastic Gradient Descent Estimate via Loss Function Approximation , 2015 .

[26]  Cécile Barat,et al.  String representations and distances in deep Convolutional Neural Networks for image classification , 2016, Pattern Recognit..

[27]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[28]  Anant Madabhushi,et al.  A Deep Convolutional Neural Network for segmenting and classifying epithelial and stromal regions in histopathological images , 2016, Neurocomputing.

[29]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[30]  Yu Zhang,et al.  Unsupervised 3D shape segmentation and co-segmentation via deep learning , 2016, Comput. Aided Geom. Des..

[31]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[32]  Yoshua Bengio,et al.  Joint Training Deep Boltzmann Machines for Classification , 2013, ICLR.

[33]  C. Hsein Juang,et al.  Prediction of Fatigue Life of Rubberized Asphalt Concrete Mixtures Containing Reclaimed Asphalt Pavement Using Artificial Neural Networks , 2009 .

[34]  Jun Wu,et al.  Pornographic image detection utilizing deep convolutional neural networks , 2016, Neurocomputing.

[35]  Qiang Guo,et al.  Convolutional feature learning and Hybrid CNN-HMM for scene number recognition , 2016, Neurocomputing.