Research on Crack Width Measurement Based on Binocular Vision and Improved DeeplabV3+
Crack width is the main manifestation of concrete material deterioration. To measure the crack information quickly and conveniently, a non-contact measurement method of concrete planar structure crack based on binocular vision is proposed. Firstly, an improved DeeplabV3+ semantic segmentation model...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/5/2752 |
| _version_ | 1797615771668447232 |
|---|---|
| author | Chaoxin Chen Peng Shen |
| author_facet | Chaoxin Chen Peng Shen |
| author_sort | Chaoxin Chen |
| collection | DOAJ |
| description | Crack width is the main manifestation of concrete material deterioration. To measure the crack information quickly and conveniently, a non-contact measurement method of concrete planar structure crack based on binocular vision is proposed. Firstly, an improved DeeplabV3+ semantic segmentation model is proposed, which uses L-MobileNetV2 as the backbone feature extraction network, adopts IDAM structure to extract high-level semantic information, introduces ECA attention mechanism, and optimizes the loss function of the model to achieve high-precision segmentation of crack areas. Secondly, the plane space coordinate equation of the concrete structure was constructed based on the principle of binocular vision and SIFT feature point matching, and the crack width was calculated by combining the segmented image. Finally, to verify the performance of the above method, a measurement test platform was built. The experimental results show that the RMSE of the crack measurement by using the algorithm is less than 0.2 mm, and the error rate is less than 4%, which has stable accuracy in different measurement angles. It solves the problem of fast and convenient measurement of the crack width of concrete planar structures in an outdoor environment. |
| first_indexed | 2024-03-11T07:31:32Z |
| format | Article |
| id | doaj.art-259d502dda0e4e64a30954a57dd9afab |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T07:31:32Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-259d502dda0e4e64a30954a57dd9afab2023-11-17T07:14:36ZengMDPI AGApplied Sciences2076-34172023-02-01135275210.3390/app13052752Research on Crack Width Measurement Based on Binocular Vision and Improved DeeplabV3+Chaoxin Chen0Peng Shen1School of Mechanical and Power Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Mechanical and Power Engineering, Zhengzhou University, Zhengzhou 450001, ChinaCrack width is the main manifestation of concrete material deterioration. To measure the crack information quickly and conveniently, a non-contact measurement method of concrete planar structure crack based on binocular vision is proposed. Firstly, an improved DeeplabV3+ semantic segmentation model is proposed, which uses L-MobileNetV2 as the backbone feature extraction network, adopts IDAM structure to extract high-level semantic information, introduces ECA attention mechanism, and optimizes the loss function of the model to achieve high-precision segmentation of crack areas. Secondly, the plane space coordinate equation of the concrete structure was constructed based on the principle of binocular vision and SIFT feature point matching, and the crack width was calculated by combining the segmented image. Finally, to verify the performance of the above method, a measurement test platform was built. The experimental results show that the RMSE of the crack measurement by using the algorithm is less than 0.2 mm, and the error rate is less than 4%, which has stable accuracy in different measurement angles. It solves the problem of fast and convenient measurement of the crack width of concrete planar structures in an outdoor environment.https://www.mdpi.com/2076-3417/13/5/2752crack widthnon-contact measurementbinocular visionimage processingDeeplabV3+ |
| spellingShingle | Chaoxin Chen Peng Shen Research on Crack Width Measurement Based on Binocular Vision and Improved DeeplabV3+ Applied Sciences crack width non-contact measurement binocular vision image processing DeeplabV3+ |
| title | Research on Crack Width Measurement Based on Binocular Vision and Improved DeeplabV3+ |
| title_full | Research on Crack Width Measurement Based on Binocular Vision and Improved DeeplabV3+ |
| title_fullStr | Research on Crack Width Measurement Based on Binocular Vision and Improved DeeplabV3+ |
| title_full_unstemmed | Research on Crack Width Measurement Based on Binocular Vision and Improved DeeplabV3+ |
| title_short | Research on Crack Width Measurement Based on Binocular Vision and Improved DeeplabV3+ |
| title_sort | research on crack width measurement based on binocular vision and improved deeplabv3 |
| topic | crack width non-contact measurement binocular vision image processing DeeplabV3+ |
| url | https://www.mdpi.com/2076-3417/13/5/2752 |
| work_keys_str_mv | AT chaoxinchen researchoncrackwidthmeasurementbasedonbinocularvisionandimproveddeeplabv3 AT pengshen researchoncrackwidthmeasurementbasedonbinocularvisionandimproveddeeplabv3 |