An Automatic Concrete Crack-Detection Method Fusing Point Clouds and Images Based on Improved Otsu’s Algorithm
Cracks are one of the main distresses that occur on concrete surfaces. Traditional methods for detecting cracks based on two-dimensional (2D) images can be hampered by stains, shadows, and other artifacts, while various three-dimensional (3D) crack-detection techniques, using point clouds, are less...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/5/1581 |
| _version_ | 1797395401934897152 |
|---|---|
| author | Xiaolong Chen Jian Li Shuowen Huang Hao Cui Peirong Liu Quan Sun |
| author_facet | Xiaolong Chen Jian Li Shuowen Huang Hao Cui Peirong Liu Quan Sun |
| author_sort | Xiaolong Chen |
| collection | DOAJ |
| description | Cracks are one of the main distresses that occur on concrete surfaces. Traditional methods for detecting cracks based on two-dimensional (2D) images can be hampered by stains, shadows, and other artifacts, while various three-dimensional (3D) crack-detection techniques, using point clouds, are less affected in this regard but are limited by the measurement accuracy of the 3D laser scanner. In this study, we propose an automatic crack-detection method that fuses 3D point clouds and 2D images based on an improved Otsu algorithm, which consists of the following four major procedures. First, a high-precision registration of a depth image projected from 3D point clouds and 2D images is performed. Second, pixel-level image fusion is performed, which fuses the depth and gray information. Third, a rough crack image is obtained from the fusion image using the improved Otsu method. Finally, the connected domain labeling and morphological methods are used to finely extract the cracks. Experimentally, the proposed method was tested at multiple scales and with various types of concrete crack. The results demonstrate that the proposed method can achieve an average precision of 89.0%, recall of 84.8%, and F1 score of 86.7%, performing significantly better than the single image (average F1 score of 67.6%) and single point cloud (average F1 score of 76.0%) methods. Accordingly, the proposed method has high detection accuracy and universality, indicating its wide potential application as an automatic method for concrete-crack detection. |
| first_indexed | 2024-03-09T00:35:01Z |
| format | Article |
| id | doaj.art-e32c2e2919774137b1097a643b287fc8 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T00:35:01Z |
| publishDate | 2021-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e32c2e2919774137b1097a643b287fc82023-12-11T18:17:04ZengMDPI AGSensors1424-82202021-02-01215158110.3390/s21051581An Automatic Concrete Crack-Detection Method Fusing Point Clouds and Images Based on Improved Otsu’s AlgorithmXiaolong Chen0Jian Li1Shuowen Huang2Hao Cui3Peirong Liu4Quan Sun5School of Water Conservancy Science & Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Geo-Science & Technology, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Geo-Science & Technology, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Geo-Science & Technology, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Water Conservancy Science & Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Water Conservancy Science & Engineering, Zhengzhou University, Zhengzhou 450001, ChinaCracks are one of the main distresses that occur on concrete surfaces. Traditional methods for detecting cracks based on two-dimensional (2D) images can be hampered by stains, shadows, and other artifacts, while various three-dimensional (3D) crack-detection techniques, using point clouds, are less affected in this regard but are limited by the measurement accuracy of the 3D laser scanner. In this study, we propose an automatic crack-detection method that fuses 3D point clouds and 2D images based on an improved Otsu algorithm, which consists of the following four major procedures. First, a high-precision registration of a depth image projected from 3D point clouds and 2D images is performed. Second, pixel-level image fusion is performed, which fuses the depth and gray information. Third, a rough crack image is obtained from the fusion image using the improved Otsu method. Finally, the connected domain labeling and morphological methods are used to finely extract the cracks. Experimentally, the proposed method was tested at multiple scales and with various types of concrete crack. The results demonstrate that the proposed method can achieve an average precision of 89.0%, recall of 84.8%, and F1 score of 86.7%, performing significantly better than the single image (average F1 score of 67.6%) and single point cloud (average F1 score of 76.0%) methods. Accordingly, the proposed method has high detection accuracy and universality, indicating its wide potential application as an automatic method for concrete-crack detection.https://www.mdpi.com/1424-8220/21/5/1581concrete crack detectionthe fusion of point clouds and images3D laser point cloudOtsu’s algorithm |
| spellingShingle | Xiaolong Chen Jian Li Shuowen Huang Hao Cui Peirong Liu Quan Sun An Automatic Concrete Crack-Detection Method Fusing Point Clouds and Images Based on Improved Otsu’s Algorithm Sensors concrete crack detection the fusion of point clouds and images 3D laser point cloud Otsu’s algorithm |
| title | An Automatic Concrete Crack-Detection Method Fusing Point Clouds and Images Based on Improved Otsu’s Algorithm |
| title_full | An Automatic Concrete Crack-Detection Method Fusing Point Clouds and Images Based on Improved Otsu’s Algorithm |
| title_fullStr | An Automatic Concrete Crack-Detection Method Fusing Point Clouds and Images Based on Improved Otsu’s Algorithm |
| title_full_unstemmed | An Automatic Concrete Crack-Detection Method Fusing Point Clouds and Images Based on Improved Otsu’s Algorithm |
| title_short | An Automatic Concrete Crack-Detection Method Fusing Point Clouds and Images Based on Improved Otsu’s Algorithm |
| title_sort | automatic concrete crack detection method fusing point clouds and images based on improved otsu s algorithm |
| topic | concrete crack detection the fusion of point clouds and images 3D laser point cloud Otsu’s algorithm |
| url | https://www.mdpi.com/1424-8220/21/5/1581 |
| work_keys_str_mv | AT xiaolongchen anautomaticconcretecrackdetectionmethodfusingpointcloudsandimagesbasedonimprovedotsusalgorithm AT jianli anautomaticconcretecrackdetectionmethodfusingpointcloudsandimagesbasedonimprovedotsusalgorithm AT shuowenhuang anautomaticconcretecrackdetectionmethodfusingpointcloudsandimagesbasedonimprovedotsusalgorithm AT haocui anautomaticconcretecrackdetectionmethodfusingpointcloudsandimagesbasedonimprovedotsusalgorithm AT peirongliu anautomaticconcretecrackdetectionmethodfusingpointcloudsandimagesbasedonimprovedotsusalgorithm AT quansun anautomaticconcretecrackdetectionmethodfusingpointcloudsandimagesbasedonimprovedotsusalgorithm AT xiaolongchen automaticconcretecrackdetectionmethodfusingpointcloudsandimagesbasedonimprovedotsusalgorithm AT jianli automaticconcretecrackdetectionmethodfusingpointcloudsandimagesbasedonimprovedotsusalgorithm AT shuowenhuang automaticconcretecrackdetectionmethodfusingpointcloudsandimagesbasedonimprovedotsusalgorithm AT haocui automaticconcretecrackdetectionmethodfusingpointcloudsandimagesbasedonimprovedotsusalgorithm AT peirongliu automaticconcretecrackdetectionmethodfusingpointcloudsandimagesbasedonimprovedotsusalgorithm AT quansun automaticconcretecrackdetectionmethodfusingpointcloudsandimagesbasedonimprovedotsusalgorithm |