A Cost-Effective and Objective Full-Depth Patching Identification Method using 3D Sensing Technology with Automated Crack Detection and Classification

Abstract

Full-depth patching is one of the commonly used asphalt pavement maintenance and rehabilitation methods in which deteriorated base and surface layers are repaired to restore strength and improve ride quality. During resurfacing projects, areas requiring full-depth patching are identified and quantified as construction priorities because of the high costs associated with the labor and materials for the procedure. Currently, the manual surveys conducted to identify these locations are time-consuming and labor-intensive. Thus, large projects often cannot easily quantify the full-depth patching need because of the significant labor that would be required. This paper proposes a method that uses emerging 3D laser technology to identify the full-depth patching need by processing and analyzing the pavement distresses automatically extracted from 3D laser images. The proposed method consists of five steps: (1) 3D data acquisition, calibration, and validation, (2) crack detection, (3) crack classification, (4) rutting detection and measurement, and (5) determination of image-based patching need using the established decision tree. A case study of one mile of 3D pavement images, collected from US 80/S.R. 26, was conducted to demonstrate the use and feasibility of the proposed method. Results show the proposed method is capable of correctly classifying 95.4% of the images that show pavements requiring patching and 84.2% of the images showing pavements not requiring patching for a combined accuracy of 94.1%. The method shows promise for identifying patch locations in a cost-effective manner and will save money and time for transportation agencies.

Get full access to this article

View all access options for this article.

References

Timm

D. H.

McQueen

J. M.

A Study of Manual vs. Automated Pavement Condition Surveys. Alabama, EE. UU: Auburn University, 2004.

Federal Highway Administration. TechBrief: Variability of Pavement Distress Data from Manual Surveys. Publication FHWA-RD-00-160. Federal Highway Administration, U.S. Department of Transportation, 2000.

Prakash

Sharma

B. N.

Kazmierowski

T. J.

Investigation into Observational Variations in Pavement Condition Survey. Proc., 3rd International Conference on Managing Pavements. San Antonio, Texas, 1994.

Tsai

Y. J.

Jiang

Wang

Pavement Crack Detection using High-resolution 3D Line Laser Imaging Technology. Proc., 7th RILEM International Conference on Cracking in Pavements. Springer, Netherlands, 2012.

Tsai

Y. J.

Wang

Feng

. Assessment of Rut Depth Measurement using Emerging 3D Continuous Laser Profiling Technology. Journal of Marine Science and Technology, Vol. 23, No. 3, pp. 322–330, 2015.

Kaul

Yezzi

Tsai

Detecting Curves with Unknown Endpoints and Arbitrary Topology using Minimal Paths. IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 34, No. 10, 2012, pp. 1952–1965.

Wang

A Spatiotemporal Methodology for Pavement Rut Characterization and Deterioration Analysis Using Long-term 3D Pavement Data. PhD dissertation. Georgia Institute of Technology, 2016.

Jiang

A Crack Detection and Diagnosis Methodology for Automated Pavement Condition Evaluation. PhD dissertation. Georgia Institute of Technology, 2015.

Georgia Department of Transportation. Pavement Condition Evaluation System. Georgia Department of Transportation, Office of Maintenance, Atlanta, GA, 2007.

10.

Tsai

Y.-C.

Jiang

Huang

Multiscale Crack Fundamental Element Model for Real-world Pavement Crack Classification. Journal of Computing in Civil Engineering. Vol. 28, No. 4, 04014012, 2014.

11.

Prakash

Sharma

B. N.

Kazmierowski

T. J.

Investigation into Observational Variations in Pavement Condition Survey. Proceedings of the 3rd International Conference on Managing Pavements, Vol. 1, No. 2, 2003, pp. 290–301.