Automatic Detection of Cracks on Concrete Surfaces in the Presence of Shadows
Deep learning-based methods, especially convolutional neural networks, have been developed to automatically process the images of concrete surfaces for crack identification tasks. Although deep learning-based methods claim very high accuracy, they often ignore the complexity of the image collection...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/10/3662 |
| _version_ | 1827666697685827584 |
|---|---|
| author | Paulius Palevičius Mayur Pal Mantas Landauskas Ugnė Orinaitė Inga Timofejeva Minvydas Ragulskis |
| author_facet | Paulius Palevičius Mayur Pal Mantas Landauskas Ugnė Orinaitė Inga Timofejeva Minvydas Ragulskis |
| author_sort | Paulius Palevičius |
| collection | DOAJ |
| description | Deep learning-based methods, especially convolutional neural networks, have been developed to automatically process the images of concrete surfaces for crack identification tasks. Although deep learning-based methods claim very high accuracy, they often ignore the complexity of the image collection process. Real-world images are often impacted by complex illumination conditions, shadows, the randomness of crack shapes and sizes, blemishes, and concrete spall. Published literature and available shadow databases are oriented towards images taken in laboratory conditions. In this paper, we explore the complexity of image classification for concrete crack detection in the presence of demanding illumination conditions. Challenges associated with the application of deep learning-based methods for detecting concrete cracks in the presence of shadows are elaborated on in this paper. Novel shadow augmentation techniques are developed to increase the accuracy of automatic detection of concrete cracks. |
| first_indexed | 2024-03-10T01:55:22Z |
| format | Article |
| id | doaj.art-d2b3b0e535c04f8189e16ba0e45ac8c1 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T01:55:22Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-d2b3b0e535c04f8189e16ba0e45ac8c12023-11-23T12:59:02ZengMDPI AGSensors1424-82202022-05-012210366210.3390/s22103662Automatic Detection of Cracks on Concrete Surfaces in the Presence of ShadowsPaulius Palevičius0Mayur Pal1Mantas Landauskas2Ugnė Orinaitė3Inga Timofejeva4Minvydas Ragulskis5Centre for Nonlinear Systems, Department of Mathematical Modelling, Kaunas University of Technology, 51368 Kaunas, LithuaniaCentre for Nonlinear Systems, Department of Mathematical Modelling, Kaunas University of Technology, 51368 Kaunas, LithuaniaCentre for Nonlinear Systems, Department of Mathematical Modelling, Kaunas University of Technology, 51368 Kaunas, LithuaniaCentre for Nonlinear Systems, Department of Mathematical Modelling, Kaunas University of Technology, 51368 Kaunas, LithuaniaCentre for Nonlinear Systems, Department of Mathematical Modelling, Kaunas University of Technology, 51368 Kaunas, LithuaniaCentre for Nonlinear Systems, Department of Mathematical Modelling, Kaunas University of Technology, 51368 Kaunas, LithuaniaDeep learning-based methods, especially convolutional neural networks, have been developed to automatically process the images of concrete surfaces for crack identification tasks. Although deep learning-based methods claim very high accuracy, they often ignore the complexity of the image collection process. Real-world images are often impacted by complex illumination conditions, shadows, the randomness of crack shapes and sizes, blemishes, and concrete spall. Published literature and available shadow databases are oriented towards images taken in laboratory conditions. In this paper, we explore the complexity of image classification for concrete crack detection in the presence of demanding illumination conditions. Challenges associated with the application of deep learning-based methods for detecting concrete cracks in the presence of shadows are elaborated on in this paper. Novel shadow augmentation techniques are developed to increase the accuracy of automatic detection of concrete cracks.https://www.mdpi.com/1424-8220/22/10/3662concrete crack detectiondeep learningconvolution neural networksimage classificationimage augmentation |
| spellingShingle | Paulius Palevičius Mayur Pal Mantas Landauskas Ugnė Orinaitė Inga Timofejeva Minvydas Ragulskis Automatic Detection of Cracks on Concrete Surfaces in the Presence of Shadows Sensors concrete crack detection deep learning convolution neural networks image classification image augmentation |
| title | Automatic Detection of Cracks on Concrete Surfaces in the Presence of Shadows |
| title_full | Automatic Detection of Cracks on Concrete Surfaces in the Presence of Shadows |
| title_fullStr | Automatic Detection of Cracks on Concrete Surfaces in the Presence of Shadows |
| title_full_unstemmed | Automatic Detection of Cracks on Concrete Surfaces in the Presence of Shadows |
| title_short | Automatic Detection of Cracks on Concrete Surfaces in the Presence of Shadows |
| title_sort | automatic detection of cracks on concrete surfaces in the presence of shadows |
| topic | concrete crack detection deep learning convolution neural networks image classification image augmentation |
| url | https://www.mdpi.com/1424-8220/22/10/3662 |
| work_keys_str_mv | AT pauliuspalevicius automaticdetectionofcracksonconcretesurfacesinthepresenceofshadows AT mayurpal automaticdetectionofcracksonconcretesurfacesinthepresenceofshadows AT mantaslandauskas automaticdetectionofcracksonconcretesurfacesinthepresenceofshadows AT ugneorinaite automaticdetectionofcracksonconcretesurfacesinthepresenceofshadows AT ingatimofejeva automaticdetectionofcracksonconcretesurfacesinthepresenceofshadows AT minvydasragulskis automaticdetectionofcracksonconcretesurfacesinthepresenceofshadows |