01152489

Component

https://doi.org/10.3141/2153-12

http://scholar.google.com...reau&publication_year=2010

Algorithms for pavement distress image segmentation are crucial to developing an automatic pavement distress detection and classification system. Many algorithms for pavement distress segmentation have been developed in the past decade; however, the lack of good methods to evaluate their performance quantitatively hinders the focused development of better segmentation algorithms. In this paper, a novel method is developed to quantitatively evaluate the performance of different pavement distress segmentation algorithms. This method uses the buffered Hausdorff distance to estimate the deviation of the cracks in the automatically segmented image from the ground truth cracks. The proposed method captures the local effectiveness of segmentation methods around the crack region without compromising its robustness to isolated pixel deviations caused by noise. Besides real pavement images, synthetic images simulating extreme pavement distress conditions are used to evaluate the capability of the proposed method and show its merits. The proposed method outperforms four other possible quantification methods and demonstrates its superior capability in providing a better score separation to distinguish the performance of different segmentation algorithms.

01320944

10-3083

English

pp 106-113

2010

Transportation Research Record: Journal of the Transportation Research Board

9780309143004

Print

Figures (5) ; References (17) ; Tables (2)

Algorithms; Pavement distress; Pavement management systems

Automatic detection; Image segmentation

Highways; Maintenance and Preservation; Pavements; I23: Properties of Road Surfaces

TRIS, TRB, ATRI

Jan 25 2010 11:31AM

• CalME, a Mechanistic–Empirical Program to Analyze and Design Flexible Pavement Rehabilitation
• Characterization and Development of Truck Axle Load Spectra for Implementation of New Pavement Design Practices in Louisiana
• Comparison of Flexible Pavement Distresses Monitored by North Carolina Department of Transportation and Long-Term Pavement Performance Program
• Confidence Level and Efficient Sampling Size of Roughness Measurements for Pavement Management in Maryland
• Developing an Overall Combined Condition Index for Pervious Concrete Pavements Using a Specific Panel Rating Method
• Development of a Global Positioning System–Based Vehicle Tracking System for the Minnesota Road Research Facility
• Effect of Frequency of Pavement Condition Data Collection on Performance Prediction
• Evaluation Method for Transverse Cracking in Asphalt Pavements on Freeways
• Index of Foreign Object Damage in Airfield Pavement Management
• Integration of "Mechanistic–Empirical Pavement Design Guide" Distresses with Local Performance Indices
• Necessary Assessment of Use of State Pavement Management System Data in "Mechanistic–Empirical Pavement Design Guide" Calibration Process
• Optical Texture-Based Tools for Monitoring Pavement Surface Wear and Cracks Using Digital Images
• Pavement Performance Modeling Using Piecewise Approximation
• Pavement Rehabilitation Project Ranking Approach Using Probabilistic Long-Term Performance Indicators
• Runway Instrumentation and Response Measurements
• Use of Pavement Management Information System for Verification of "Mechanistic–Empirical Pavement Design Guide" Performance Predictions
• Validation and Implementation of Ontario, Canada, Network-Level Distress Guidelines and Condition Rating