Unsupervised Approach for Autonomous Pavement-Defect Detection and Quantification Using an Inexpensive Depth Sensor
- 1 November 2013
- journal article
- Published by American Society of Civil Engineers (ASCE) in Journal of Computing in Civil Engineering
- Vol. 27 (6), 743-754
- https://doi.org/10.1061/(asce)cp.1943-5487.0000245
Abstract
Current pavement condition–assessment procedures are extensively time consuming and laborious; in addition, these approaches pose safety threats to the personnel involved in the process. In this study, a RGB-D sensor is used to detect and quantify defects in pavements. This sensor system consists of a RGB color image, and an infrared projector and a camera that act as a depth sensor. An approach, which does not need any training, is proposed to interpret the data sensed by this inexpensive sensor. This system has the potential to be used for autonomous cost-effective assessment of road-surface conditions. Various road conditions including patching, cracks, and potholes are autonomously detected and, most importantly, quantified, using the proposed approach. Several field experiments have been carried out to evaluate the capabilities, as well as the limitations of the proposed system. The global positioning system information is incorporated with the proposed system to localize the detected defects. This approach has the potential to be deployed as a supplementary sensor system in pavement surface–assessment vehicles and reduce the operation cost.Keywords
This publication has 31 references indexed in Scilit:
- Adaptive Road Crack Detection System by Pavement ClassificationSensors, 2011
- Automatic Road Defect Detection by Textural Pattern Recognition Based on AdaBoostComputer-Aided Civil and Infrastructure Engineering, 2011
- Pothole detection in asphalt pavement imagesAdvanced Engineering Informatics, 2011
- Error analysis and implementation considerations of decoding algorithms for time-encoding machineEURASIP Journal on Advances in Signal Processing, 2011
- Beamlet Transform-Based Technique for Pavement Crack Detection and ClassificationComputer-Aided Civil and Infrastructure Engineering, 2010
- A real-time 3D scanning system for pavement distortion inspectionMeasurement Science and Technology, 2009
- Position‐Invariant Neural Network for Digital Pavement Crack AnalysisComputer-Aided Civil and Infrastructure Engineering, 2004
- Designs and Implementations of Automated Systems for Pavement Surface Distress SurveyJournal of Infrastructure Systems, 2000
- Automatic Pavement?Distress?Survey SystemJournal of Transportation Engineering, 1990
- Random sample consensusCommunications of the ACM, 1981