GPU-Enabled Pavement Distress Image Classification in Real Time

Pavement assessment is a crucial process for the maintenance of municipal roads. However, the detection of pavement distress is usually performed either manually or offline, which is not only time-consuming and subjective, but also results in an enormous amount of data being stored persistently before processing. State-of-the-art pavement image processing methods executed on a CPU are not able to analyse pavement images in real time. To compensate this limitation of the methods, we propose an automated approach for pavement distress detection. In particular, GPU implementations of a noise removal, a background correction and a pavement distress detection method were developed. The median filter and the top-hat transform are used to remove noise and shadows in the images. The wavelet transform is applied in order to calculate a descriptor value for classification purposes. The approach was tested on 1549 images. The results show that real-time pre-processing and analysis are possible.

[1]  Paul W. Fieguth,et al.  A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure , 2015, Adv. Eng. Informatics.

[2]  Khurram Kamal,et al.  Pavement crack detection using the Gabor filter , 2013, 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013).

[3]  Li Yao,et al.  Images Crack Detection Technology based on Improved K-means Algorithm , 2014, J. Multim..

[4]  Christoph Mertz,et al.  Vision for road inspection , 2014, IEEE Winter Conference on Applications of Computer Vision.

[5]  E. Buza,et al.  Pothole Detection with Image Processing and Spectral Clustering , 2013 .

[6]  Juan José Rodríguez Diez,et al.  Rotation Forest: A New Classifier Ensemble Method , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Li Li,et al.  AUTOMATIC PAVEMENT CRACK RECOGNITION BASED ON BP NEURAL NETWORK , 2014 .

[8]  Ingrid Daubechies,et al.  The wavelet transform, time-frequency localization and signal analysis , 1990, IEEE Trans. Inf. Theory.

[9]  H. D. Cheng,et al.  NOVEL SYSTEM FOR AUTOMATIC PAVEMENT DISTRESS DETECTION , 1998 .

[10]  Naoki Tanaka,et al.  A Crack Detection Method in Road Surface Images Using Morphology , 1998, MVA.

[11]  K H McGhee,et al.  AUTOMATED PAVEMENT DISTRESS COLLECTION TECHNIQUES , 2004 .

[12]  Lalit Kumar Das,et al.  Method for Automated Assessment of Potholes, Cracks and Patches from Road Surface Video Clips , 2013 .

[13]  Jian Zhou,et al.  Wavelet-based pavement distress detection and evaluation , 2003 .

[14]  Paulo Lobato Correia,et al.  Automatic Road Crack Detection and Characterization , 2013, IEEE Transactions on Intelligent Transportation Systems.

[15]  Russell M. Mersereau,et al.  Critical Assessment of Pavement Distress Segmentation Methods , 2010 .

[16]  Elmustafa S.Ali Ahmed,et al.  Median Filter Performance Based on Different Window Sizes for Salt and Pepper Noise Removal in Gray and RGB Images , 2015 .

[17]  Peggy Subirats,et al.  Automation of Pavement Surface Crack Detection using the Continuous Wavelet Transform , 2006, 2006 International Conference on Image Processing.

[18]  Qiang Wu,et al.  Microscope Image Processing , 2010 .

[19]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[20]  Qingquan Li,et al.  CrackTree: Automatic crack detection from pavement images , 2012, Pattern Recognit. Lett..

[21]  Christian Koch,et al.  Pothole detection in asphalt pavement images , 2011, Adv. Eng. Informatics.

[22]  Nagavijayalakshmi Vydyanathan,et al.  Parallel discrete wavelet transform using the Open Computing Language: a performance and portability study , 2010, 2010 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW).

[23]  Jens H. Krüger,et al.  A Survey of General‐Purpose Computation on Graphics Hardware , 2007, Eurographics.

[24]  Ulrich Rüde,et al.  Fast Wavelet Transform Utilizing a Multicore-Aware Framework , 2010, PARA.

[25]  Wilhelm Burger,et al.  Digital Image Processing - An Algorithmic Introduction using Java , 2008, Texts in Computer Science.

[26]  David R. Kaeli,et al.  Heterogeneous Computing with OpenCL - Revised OpenCL 1.2 Edition , 2012 .

[27]  D Navaneetha,et al.  Hough Transforms to Detect and Classify Road Cracks , 2014 .

[28]  Andreas Georgopoulos,et al.  Digital image processing as a tool for pavement distress evaluation , 1995 .

[29]  Sebastiano Battiato,et al.  Evaluation Of Pavement Surface Distress Using Digital Image Collection And Analysis , 2006 .

[30]  Intel ® SDK for OpenCL *-Median Filter Sample User ' s Guide , 2012 .

[31]  Jian Zhou,et al.  Wavelet-based pavement distress detection and evaluation , 2003 .

[32]  Fereidoon Moghadas Nejad,et al.  A comparison of multi-resolution methods for detection and isolation of pavement distress , 2011, Expert Syst. Appl..

[33]  A. Haar.  Zur Theorie der orthogonalen Funktionensysteme , 1910 .

[34]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[35]  Marcel Abendroth,et al.  Data Mining Practical Machine Learning Tools And Techniques With Java Implementations , 2016 .

[36]  E. Salari,et al.  Pavement pothole detection and severity measurement using laser imaging , 2011, 2011 IEEE INTERNATIONAL CONFERENCE ON ELECTRO/INFORMATION TECHNOLOGY.

[37]  L D Suits,et al.  NEW YORK STATE DEPARTMENT OF TRANSPORTATION'S (NYSDOT) BASIS OF ACCEPTANCE AND SPECIFICATION FOR PREFABRICATED WICK DRAINS , 1986 .

[38]  Ravishekhar Banger,et al.  OpenCL Programming by Example , 2013 .

[39]  Ghada S. Moussa,et al.  A New Technique for Automatic Detection and Parameters Estimation of Pavement Crack , 2011 .

[40]  Toby P. Breckon,et al.  Fundamentals of Digital Image Processing: A Practical Approach with Examples in Matlab , 2011 .

[41]  Bernd Jähne,et al.  Computer vision and applications: a guide for students and practitioners , 2000 .

[42]  Bugao Xu,et al.  Automatic inspection of pavement cracking distress , 2006, J. Electronic Imaging.

[43]  Christian Koch,et al.  Automated Pothole Distress Assessment Using Asphalt Pavement Video Data , 2013 .