Deep Learning-Based Semantic Segmentation Methods for Pavement Cracks
As road mileage continues to expand, the number of disasters caused by expanding pavement cracks is increasing. Two main methods, image processing and deep learning, are used to detect these cracks to improve the efficiency and quality of pavement crack segmentation. The classical segmentation netwo...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/14/3/182 |
| _version_ | 1797611128045436928 |
|---|---|
| author | Yu Zhang Xin Gao Hanzhong Zhang |
| author_facet | Yu Zhang Xin Gao Hanzhong Zhang |
| author_sort | Yu Zhang |
| collection | DOAJ |
| description | As road mileage continues to expand, the number of disasters caused by expanding pavement cracks is increasing. Two main methods, image processing and deep learning, are used to detect these cracks to improve the efficiency and quality of pavement crack segmentation. The classical segmentation network, UNet, has a poor ability to extract target edge information and small target segmentation, and is susceptible to the influence of distracting objects in the environment, thus failing to better segment the tiny cracks on the pavement. To resolve this problem, we propose a U-shaped network, ALP-UNet, which adds an attention module to each encoding layer. In the decoding phase, we incorporated the Laplacian pyramid to make the feature map contain more boundary information. We also propose adding a PAN auxiliary head to provide an additional loss for the backbone to improve the overall network segmentation effect. The experimental results show that the proposed method can effectively reduce the interference of other factors on the pavement and effectively improve the mIou and mPA values compared to the previous methods. |
| first_indexed | 2024-03-11T06:24:26Z |
| format | Article |
| id | doaj.art-cad6b0297fe34b8fabc9fda0e1f5aa2b |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-11T06:24:26Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-cad6b0297fe34b8fabc9fda0e1f5aa2b2023-11-17T11:44:14ZengMDPI AGInformation2078-24892023-03-0114318210.3390/info14030182Deep Learning-Based Semantic Segmentation Methods for Pavement CracksYu Zhang0Xin Gao1Hanzhong Zhang2College of Mechanical Engineering, Shenyang University of Technology, Shenyang 110870, ChinaCollege of Mechanical Engineering, Shenyang University of Technology, Shenyang 110870, ChinaHong Kong Community College, The Hong Kong Polytechnic University, Hong Kong 999077, ChinaAs road mileage continues to expand, the number of disasters caused by expanding pavement cracks is increasing. Two main methods, image processing and deep learning, are used to detect these cracks to improve the efficiency and quality of pavement crack segmentation. The classical segmentation network, UNet, has a poor ability to extract target edge information and small target segmentation, and is susceptible to the influence of distracting objects in the environment, thus failing to better segment the tiny cracks on the pavement. To resolve this problem, we propose a U-shaped network, ALP-UNet, which adds an attention module to each encoding layer. In the decoding phase, we incorporated the Laplacian pyramid to make the feature map contain more boundary information. We also propose adding a PAN auxiliary head to provide an additional loss for the backbone to improve the overall network segmentation effect. The experimental results show that the proposed method can effectively reduce the interference of other factors on the pavement and effectively improve the mIou and mPA values compared to the previous methods.https://www.mdpi.com/2078-2489/14/3/182attention moduleLaplacian pyramidPAN |
| spellingShingle | Yu Zhang Xin Gao Hanzhong Zhang Deep Learning-Based Semantic Segmentation Methods for Pavement Cracks Information attention module Laplacian pyramid PAN |
| title | Deep Learning-Based Semantic Segmentation Methods for Pavement Cracks |
| title_full | Deep Learning-Based Semantic Segmentation Methods for Pavement Cracks |
| title_fullStr | Deep Learning-Based Semantic Segmentation Methods for Pavement Cracks |
| title_full_unstemmed | Deep Learning-Based Semantic Segmentation Methods for Pavement Cracks |
| title_short | Deep Learning-Based Semantic Segmentation Methods for Pavement Cracks |
| title_sort | deep learning based semantic segmentation methods for pavement cracks |
| topic | attention module Laplacian pyramid PAN |
| url | https://www.mdpi.com/2078-2489/14/3/182 |
| work_keys_str_mv | AT yuzhang deeplearningbasedsemanticsegmentationmethodsforpavementcracks AT xingao deeplearningbasedsemanticsegmentationmethodsforpavementcracks AT hanzhongzhang deeplearningbasedsemanticsegmentationmethodsforpavementcracks |