A Tile-Based Image Processing Method Based on Crack Density for Detection and Classification of Pavement Cracks
This paper describes the development of a fast and cost-effective automatic crack assessment method for the detection and classification of cracks from acquired two-dimensional pavement images. Most methods are costly and require labor-intensive learning processes or only apply to specific pavement types, and therefore a fast and low-cost method is necessary for roadway health monitoring with a limited budget. The authors find that the method can contribute to the deterioration modeling of cracks for pavement management systems, but it was ineffective at identifying low-level cracks.
-
Corporate Authors:
Transportation Research Board
, -
Authors:
- Safaei, Nima
- Smadi, Omar
-
Conference:
- Transportation Research Board 98th Annual Meeting
- Location: Washington DC, United States
- Date: 2019-1-13 to 2019-1-17
- Publication Date: 2019
Language
- English
Media Info
- Media Type: Digital/other
- Features: References;
- Pagination: 7p
Subject/Index Terms
- TRT Terms: Computer vision; Cost effectiveness; Cracking; Detection and identification; Image analysis; Pavement management systems; Structural health monitoring
- Subject Areas: Highways; Pavements;
Filing Info
- Accession Number: 01699791
- Record Type: Publication
- Report/Paper Numbers: 19-02553
- Files: TRIS, TRB, ATRI
- Created Date: Mar 26 2019 10:21AM