Pavement Crack Detection and Segmentation Method Based on Improved Deep Learning Fusion Model
Pavement damage is the main factor affecting road performance. Pavement cracking, a common type of road damage, is a key challenge in road maintenance. In order to achieve an accurate crack classification, segmentation, and geometric parameter calculation, this paper proposes a method based on a dee...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2020-01-01
|
Series: | Mathematical Problems in Engineering |
Online Access: | http://dx.doi.org/10.1155/2020/8515213 |
id |
doaj-45d2de1200854505b8a691131ea8d467 |
---|---|
record_format |
Article |
spelling |
doaj-45d2de1200854505b8a691131ea8d4672020-12-21T11:41:31ZengHindawi LimitedMathematical Problems in Engineering1024-123X1563-51472020-01-01202010.1155/2020/85152138515213Pavement Crack Detection and Segmentation Method Based on Improved Deep Learning Fusion ModelXiaoran Feng0Liyang Xiao1Wei Li2Lili Pei3Zhaoyun Sun4Zhidan Ma5Hao Shen6Huyan Ju7School of Information Engineering, Chang’an University, Xi’an 710064, Shaanxi, ChinaSchool of Information Engineering, Chang’an University, Xi’an 710064, Shaanxi, ChinaSchool of Information Engineering, Chang’an University, Xi’an 710064, Shaanxi, ChinaSchool of Information Engineering, Chang’an University, Xi’an 710064, Shaanxi, ChinaSchool of Information Engineering, Chang’an University, Xi’an 710064, Shaanxi, ChinaSchool of Information Engineering, Chang’an University, Xi’an 710064, Shaanxi, ChinaSchool of Information Engineering, Chang’an University, Xi’an 710064, Shaanxi, ChinaCentre for Pavement and Transportation Technology (CPATT), Department of Civil and Environmental Engineering, University of Waterloo, Waterloo, Ontario N2L 3G1, CanadaPavement damage is the main factor affecting road performance. Pavement cracking, a common type of road damage, is a key challenge in road maintenance. In order to achieve an accurate crack classification, segmentation, and geometric parameter calculation, this paper proposes a method based on a deep convolutional neural network fusion model for pavement crack identification, which combines the advantages of the multitarget single-shot multibox detector (SSD) convolutional neural network model and the U-Net model. First, the crack classification and detection model is applied to classify the cracks and obtain the detection confidence. Next, the crack segmentation network is applied to accurately segment the pavement cracks. By improving the feature extraction structure and optimizing the hyperparameters of the model, pavement crack classification and segmentation accuracy were improved. Finally, the length and width (for linear cracks) and the area (for alligator cracks) are calculated according to the segmentation results. Test results show that the recognition accuracy of the pavement crack identification method for transverse, longitudinal, and alligator cracks is 86.8%, 87.6%, and 85.5%, respectively. It is demonstrated that the proposed method can provide the category information for pavement cracks as well as the accurate positioning and geometric parameter information, which can be used directly for evaluating the pavement condition.http://dx.doi.org/10.1155/2020/8515213 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xiaoran Feng Liyang Xiao Wei Li Lili Pei Zhaoyun Sun Zhidan Ma Hao Shen Huyan Ju |
spellingShingle |
Xiaoran Feng Liyang Xiao Wei Li Lili Pei Zhaoyun Sun Zhidan Ma Hao Shen Huyan Ju Pavement Crack Detection and Segmentation Method Based on Improved Deep Learning Fusion Model Mathematical Problems in Engineering |
author_facet |
Xiaoran Feng Liyang Xiao Wei Li Lili Pei Zhaoyun Sun Zhidan Ma Hao Shen Huyan Ju |
author_sort |
Xiaoran Feng |
title |
Pavement Crack Detection and Segmentation Method Based on Improved Deep Learning Fusion Model |
title_short |
Pavement Crack Detection and Segmentation Method Based on Improved Deep Learning Fusion Model |
title_full |
Pavement Crack Detection and Segmentation Method Based on Improved Deep Learning Fusion Model |
title_fullStr |
Pavement Crack Detection and Segmentation Method Based on Improved Deep Learning Fusion Model |
title_full_unstemmed |
Pavement Crack Detection and Segmentation Method Based on Improved Deep Learning Fusion Model |
title_sort |
pavement crack detection and segmentation method based on improved deep learning fusion model |
publisher |
Hindawi Limited |
series |
Mathematical Problems in Engineering |
issn |
1024-123X 1563-5147 |
publishDate |
2020-01-01 |
description |
Pavement damage is the main factor affecting road performance. Pavement cracking, a common type of road damage, is a key challenge in road maintenance. In order to achieve an accurate crack classification, segmentation, and geometric parameter calculation, this paper proposes a method based on a deep convolutional neural network fusion model for pavement crack identification, which combines the advantages of the multitarget single-shot multibox detector (SSD) convolutional neural network model and the U-Net model. First, the crack classification and detection model is applied to classify the cracks and obtain the detection confidence. Next, the crack segmentation network is applied to accurately segment the pavement cracks. By improving the feature extraction structure and optimizing the hyperparameters of the model, pavement crack classification and segmentation accuracy were improved. Finally, the length and width (for linear cracks) and the area (for alligator cracks) are calculated according to the segmentation results. Test results show that the recognition accuracy of the pavement crack identification method for transverse, longitudinal, and alligator cracks is 86.8%, 87.6%, and 85.5%, respectively. It is demonstrated that the proposed method can provide the category information for pavement cracks as well as the accurate positioning and geometric parameter information, which can be used directly for evaluating the pavement condition. |
url |
http://dx.doi.org/10.1155/2020/8515213 |
work_keys_str_mv |
AT xiaoranfeng pavementcrackdetectionandsegmentationmethodbasedonimproveddeeplearningfusionmodel AT liyangxiao pavementcrackdetectionandsegmentationmethodbasedonimproveddeeplearningfusionmodel AT weili pavementcrackdetectionandsegmentationmethodbasedonimproveddeeplearningfusionmodel AT lilipei pavementcrackdetectionandsegmentationmethodbasedonimproveddeeplearningfusionmodel AT zhaoyunsun pavementcrackdetectionandsegmentationmethodbasedonimproveddeeplearningfusionmodel AT zhidanma pavementcrackdetectionandsegmentationmethodbasedonimproveddeeplearningfusionmodel AT haoshen pavementcrackdetectionandsegmentationmethodbasedonimproveddeeplearningfusionmodel AT huyanju pavementcrackdetectionandsegmentationmethodbasedonimproveddeeplearningfusionmodel |
_version_ |
1714988328684617728 |