2017
DOI: 10.1016/j.imavis.2016.11.018
|View full text |Cite
|
Sign up to set email alerts
|

An efficient and reliable coarse-to-fine approach for asphalt pavement crack detection

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
57
0
1

Year Published

2017
2017
2022
2022

Publication Types

Select...
7
2
1

Relationship

1
9

Authors

Journals

citations
Cited by 137 publications
(67 citation statements)
references
References 16 publications
0
57
0
1
Order By: Relevance
“…To overcome the drawbacks of human-based crack detection method, many image processing techniques (IPTs) are developed to detect concrete cracks [1][2][3], concrete spalling [4], and potholes and cracks in asphalt pavement [5][6][7]. e IPTs can not only recognize cracks from images [8] but also measure the width and orientation of the recognized cracks [9,10].…”
Section: Introductionmentioning
confidence: 99%
“…To overcome the drawbacks of human-based crack detection method, many image processing techniques (IPTs) are developed to detect concrete cracks [1][2][3], concrete spalling [4], and potholes and cracks in asphalt pavement [5][6][7]. e IPTs can not only recognize cracks from images [8] but also measure the width and orientation of the recognized cracks [9,10].…”
Section: Introductionmentioning
confidence: 99%
“…Zhang et al [5] adopted four-layer convolutional neural network (CNN) to realize crack detection, with an accuracy of 87%, which needs to be improved. Zhang et al [6] proposed a new region growth algorithm to detect road cracks, which is not suitable for detecting small and scattered cracks in the road. e extended finite element formula (XFEM) combined with the genetic algorithm (GA) has been proven to be effective in detecting structural defects [7][8][9], but this method also has many limitations.…”
Section: Introductionmentioning
confidence: 99%
“…In order to avoid illumination variations and shadows, the thresholding of the localized area has been applied [57,58]. In [59], automation of the threshold selection was proposed. For more complex cases, advanced image analysis such as Gabor filters [23] have been used.…”
Section: Source Input Data and Data Collectionmentioning
confidence: 99%