A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
This paper presents a newly developed image-processing algorithm that was customized for high-speed, realtime inspection of pavement cracking. The algorithm was based on the 'grid cell' analysis, in which a pavement image is divided into grid cells of 8x8 pixels and each cell is classified as a non-crack cell or a crack cell based on the statistics of the grayscales of the cell pixels. Whether a crack cell can be regarded as a basic element (or seed) depends on its contrast to the neighboring cells. If a number of crack seeds can be called a crack cluster if they can form a linear string. A crack cluster should correspond to a dark strip in the original pavement image that may or may not be a section of a real crack. Additional conditions to verify a crack cluster include the requirements in the contrast, width and length of the strip. If verified crack clusters are oriented in similar directions, they can be joined to become one crack. Because many operations are performed on crack seeds rather than on the original image, crack detection can be done simultaneously when the frame grabber is forming a new image from the linescan camera. This high-speed process algorithm permits real-time, highway speed pavement survey. The trial test results show a good repeatability and accuracy when the system conducts multiple surveys and runs at different speeds and different weather conditions.
This paper presents a newly developed image-processing algorithm that was customized for high-speed, realtime inspection of pavement cracking. The algorithm was based on the 'grid cell' analysis, in which a pavement image is divided into grid cells of 8x8 pixels and each cell is classified as a non-crack cell or a crack cell based on the statistics of the grayscales of the cell pixels. Whether a crack cell can be regarded as a basic element (or seed) depends on its contrast to the neighboring cells. If a number of crack seeds can be called a crack cluster if they can form a linear string. A crack cluster should correspond to a dark strip in the original pavement image that may or may not be a section of a real crack. Additional conditions to verify a crack cluster include the requirements in the contrast, width and length of the strip. If verified crack clusters are oriented in similar directions, they can be joined to become one crack. Because many operations are performed on crack seeds rather than on the original image, crack detection can be done simultaneously when the frame grabber is forming a new image from the linescan camera. This high-speed process algorithm permits real-time, highway speed pavement survey. The trial test results show a good repeatability and accuracy when the system conducts multiple surveys and runs at different speeds and different weather conditions.
Development of an Automatic Pavement Surface Distress Inspection System
2003
32 pages
Report
No indication
English
Novel System for Automatic Pavement Distress Detection
| Online Contents | 1998
Novel System for Automatic Pavement Distress Detection
| British Library Online Contents | 1998
| Wiley | 1975
Crackscope-Automatic Pavement Cracking Inspection System
| NTIS | 2008
Automatic pavement distress severity detection using deep learning
| Taylor & Francis Verlag | 2024