Ground-penetrating radar railroad ballast inspection with an unsupervised algorithm to boost the region of interest detection efficiency

Abstract. Railroad ballast inspection is critical for the safety of both passenger and freight rail. Ground-penetrating radar (GPR) has been utilized as a highly efficient nondestructive evaluation and structural health monitoring technique in bridge and roadway inspection for many years. However, the development of robust GPR technologies for railroad ballast inspection is still at its early stage due to the complex scattering characteristics of ballast and the lack of efficient algorithms to process big GPR data. An efficient unsupervised method for detecting the region of interest in ballast layer based on the Hilbert transform and Renyi entropy analysis is developed. Both laboratory test and field test are set up and conducted. The data interpretation results demonstrate that the developed region of interest detection algorithm is an efficient and valuable tool for GPR data processing.

[1]  Imad L. Al-Qadi,et al.  Content-based image retrieval approaches to interpret ground penetrating radar data , 2014 .

[2]  I. Al-Qadi,et al.  Dielectric Constant Measurement of Railroad Ballast and Application of STFT for GPR Data Analysis , 2009 .

[3]  Jiexin Pu,et al.  Feature Extraction and Automatic Material Classification of Underground Objects from Ground Penetrating Radar Data , 2014, J. Electr. Comput. Eng..

[4]  Guoan Wang,et al.  Data analysis technique to leverage ground penetrating radar ballast inspection performance , 2014, 2014 IEEE Radar Conference.

[5]  Tian Xia,et al.  A High-Performance Low-Ringing Ultrawideband Monocycle Pulse Generator , 2012, IEEE Transactions on Instrumentation and Measurement.

[6]  Imad L. Al-Qadi,et al.  Innovative Approach for Asphalt Pavement Compaction Monitoring with Ground-Penetrating Radar , 2013 .

[7]  Yu Zhang,et al.  Advanced signal processing method for ground penetrating radar feature detection and enhancement , 2014, Smart Structures.

[8]  Tian Xia,et al.  Development of a New High Speed Dual-Channel Impulse Ground Penetrating Radar , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[9]  Imad L. Al-Qadi,et al.  Data Analysis Techniques for GPR Used for Assessing Railroad Ballast in High Radio-Frequency Environment , 2010 .

[10]  Shan Ouyang,et al.  Matched filtering algorithm based on phase-shifting pursuit for ground-penetrating radar signal enhancement , 2014 .

[11]  Barry Haack,et al.  Supervised machine learning of fused RADAR and optical data for land cover classification , 2012 .

[12]  Abdesselam Bouzerdoum,et al.  Sparse Representation of GPR Traces With Application to Signal Classification , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[13]  Dryver R. Huston,et al.  GIMA ground penetrating radar system for monitoring concrete bridge decks , 2000 .

[14]  Emmanuel Duflos,et al.  Landmines Ground-Penetrating Radar Signal Enhancement by Digital Filtering , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Tian Xia,et al.  Development of High-Speed Ultrawideband Ground-Penetrating Radar for Rebar Detection , 2013 .

[16]  Yu Zhang,et al.  2-D Entropy and Short-Time Fourier Transform to Leverage GPR Data Analysis Efficiency , 2015, IEEE Transactions on Instrumentation and Measurement.

[17]  Francois P. S. Chin,et al.  Entropy-Based Time Window for Artifact Removal in UWB Imaging of Breast Cancer Detection , 2006, IEEE Signal Processing Letters.

[18]  Steven W. Smith,et al.  The Scientist and Engineer's Guide to Digital Signal Processing , 1997 .

[19]  Sabrina Hirsch,et al.  Digital Signal Processing A Computer Based Approach , 2016 .

[20]  Tian Xia,et al.  Development of a high speed UWB GPR for rebar detection , 2012, 2012 14th International Conference on Ground Penetrating Radar (GPR).

[21]  Robert A. Cheke,et al.  Soil moisture assessments for brown locust Locustana pardalina breeding potential using synthetic aperture radar , 2014 .

[22]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .