Pothole Detection in Asphalt: An Automated Approach to Threshold Computation Based on the Haar Wavelet Transform

With the increasing deployment of vehicles embedded technology and with the imminent availability of the autonomous vehicles on the market, solutions for detecting potholes in roads have gained attention from industry and academia. The current work proposes an automated system for pothole detection by the one dimensional Haar Wavelet Transform (HWT) applied to accelerometer signals. In this context, the proposed methodology explores the advantage of low cost processing in both stages, in the signal acquisition and during the analysis. The analysis of the wavelet coefficients is done through a two-step threshold procedure that enables the identification of strong variations within data, here related to the potholes. Since the threshold values are estimated adaptively, the detected variations can also identify the normal signal pattern, associated to the accepted road conditions. Thus, no manual threshold calibration is required. Overall, we found that our proposed methodology is efficient not only for a controlled environment scenario but also for a real scenario.

[1]  Michael E. Fitzpatrick,et al.  Detecting anomalies in time series data via a deep learning algorithm combining wavelets, neural networks and Hilbert transform , 2017, Expert Syst. Appl..

[2]  Taehyeong Kim,et al.  Review and Analysis of Pothole Detection Methods , 2014 .

[3]  Muhammad Haroon Yousaf,et al.  Computer vision based detection and localization of potholes in asphalt pavement images , 2016, 2016 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE).

[4]  Andrew Fox,et al.  Multi-Lane Pothole Detection from Crowdsourced Undersampled Vehicle Sensor Data , 2017, IEEE Transactions on Mobile Computing.

[5]  Yoshihide Sekimoto,et al.  Road Damage Detection and Classification Using Deep Neural Networks with Smartphone Images , 2018, Comput. Aided Civ. Infrastructure Eng..

[6]  Huaijun Wang,et al.  A Road Quality Detection Method Based on the Mahalanobis-Taguchi System , 2018, IEEE Access.

[7]  Purushottam Kulkarni,et al.  Pothole Detection and Warning System: Infrastructure Support and System Design , 2009, 2009 International Conference on Electronic Computer Technology.

[8]  Jin Lin,et al.  Potholes Detection Based on SVM in the Pavement Distress Image , 2010, 2010 Ninth International Symposium on Distributed Computing and Applications to Business, Engineering and Science.

[9]  Abiodun Musa Aibinu,et al.  New road anomaly detection and characterization algorithm for autonomous vehicles , 2018 .

[10]  Fábio M. Bayer,et al.  An iterative wavelet threshold for signal denoising , 2019, Signal Process..

[11]  Marcia Pasin,et al.  Indoor position tracking: An application using the Arduino mobile platform , 2017, 2017 10th IFIP Wireless and Mobile Networking Conference (WMNC).

[12]  A. Poularikas.  The transforms and applications handbook , 2000 .

[13]  Songnian Li,et al.  Road Surface Monitoring Using Smartphone Sensors: A Review , 2018, Sensors.

[14]  Christian E. Schaerer,et al.  URL query string anomaly sensor designed with the bidimensional Haar wavelet transform , 2015, International Journal of Information Security.

[15]  Ramachandran Ramjee,et al.  Nericell: rich monitoring of road and traffic conditions using mobile smartphones , 2008, SenSys '08.

[16]  Ryan Newton,et al.  The pothole patrol: using a mobile sensor network for road surface monitoring , 2008, MobiSys '08.

[17]  Girts Strazdins,et al.  Real time pothole detection using Android smartphones with accelerometers , 2011, 2011 International Conference on Distributed Computing in Sensor Systems and Workshops (DCOSS).

[18]  Jay A. Farrell,et al.  Computationally Efficient Carrier Integer Ambiguity Resolution in Multiepoch GPS/INS: A Common-Position-Shift Approach , 2016, IEEE Transactions on Control Systems Technology.

[19]  Su-il Choi,et al.  Pothole detection system using 2D LiDAR and camera , 2017, 2017 Ninth International Conference on Ubiquitous and Future Networks (ICUFN).

[20]  Soumya Jana,et al.  Laser-based detection and depth estimation of dry and water-filled potholes: A geometric approach , 2015, 2015 Twenty First National Conference on Communications (NCC).

[21]  Penghui Wang,et al.  Asphalt Pavement Pothole Detection and Segmentation Based on Wavelet Energy Field , 2017 .

[22]  Yoshihide Sekimoto,et al.  Road Damage Detection and Classification Using Deep Neural Networks with Smartphone Images , 2018, Comput. Aided Civ. Infrastructure Eng..

[23]  Chamath Keppitiyagama,et al.  A public transport system based sensor network for road surface condition monitoring , 2007, NSDR '07.

[24]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Marthinus J. Booysen,et al.  Detecting potholes using simple image processing techniques and real-world footage , 2015 .

[26]  Rajeshwari Madli,et al.  Automatic Detection and Notification of Potholes and Humps on Roads to Aid Drivers , 2015, IEEE Sensors Journal.

[27]  I. Johnstone,et al.  Adapting to Unknown Smoothness via Wavelet Shrinkage , 1995 .

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