A New Region-Based Minimal Path Selection Algorithm for Crack Detection and Ground Truth Labeling Exploiting Gabor Filters
Cracks are fractures or breaks that occur in materials such as concrete, metals, rocks, and other solids. Various methods are used to detect and monitor cracks; among many of them, image-based methodologies allow fast identification of the distress and easy quantification of the percentage of cracks...
| Autores principales: | , , , |
|---|---|
| Formato: | Artículo |
| Lenguaje: | English |
| Publicado: |
MDPI AG
2023-05-01
|
| Colección: | Remote Sensing |
| Materias: | |
| Acceso en línea: | https://www.mdpi.com/2072-4292/15/11/2722 |
| _version_ | 1827739285982281728 |
|---|---|
| author | Gonzalo de León Nicholas Fiorentini Pietro Leandri Massimo Losa |
| author_facet | Gonzalo de León Nicholas Fiorentini Pietro Leandri Massimo Losa |
| author_sort | Gonzalo de León |
| collection | DOAJ |
| description | Cracks are fractures or breaks that occur in materials such as concrete, metals, rocks, and other solids. Various methods are used to detect and monitor cracks; among many of them, image-based methodologies allow fast identification of the distress and easy quantification of the percentage of cracks in the scene. Two main categories can be identified: classical and deep learning approaches. In the last decade, the tendency has moved towards the use of the latter. Even though they have proven their outstanding predicting performance, they suffer some drawbacks: a “black-box” nature leaves the user blind and without the possibility of modifying any parameters, a huge amount of labeled data is generally needed, a process that requires expert judgment is always required, and, finally, they tend to be time-consuming. Accordingly, the present study details the methodology for a new algorithm for crack segmentation based on the theory of minimal path selection combined with a region-based approach obtained through the segmentation of texture features extracted using Gabor filters. A pre-processing step is described, enabling the equalization of brightness and shadows, which results in better detection of local minima. These local minimal are constrained by a minimum distance between adjacent points, enabling a better coverage of the cracks. Afterward, a region-based segmentation technique is introduced to determine two areas that are used to determine threshold values used for rejection. This step is critical to generalize the algorithm to images presenting close-up scenes or wide cracks. Finally, a geometrical thresholding step is presented, allowing the exclusion of rounded areas and small isolated cracks. The results showed a very competitive <i>F</i>1-score (0.839), close to state-of-the-art values achieved with deep learning techniques. The main advantage of this approach is the transparency of the workflow, contrary to what happens with deep learning frameworks. In the proposed approach, no prior information is required; however, the statistical parameters may have to be adjusted to the particular case and requirements of the situation. The proposed algorithm results in a useful tool for researchers and practitioners needing to validate their results against some reference or needing labeled data for their models. Moreover, the current study could establish the grounds to standardize the procedure for crack segmentation with a lower human bias and faster results. The direct application of the methodology to images obtained with any low-cost sensor makes the proposed algorithm an operational support tool for authorities needing crack detection systems in order to monitor and evaluate the current state of the infrastructures, such as roads, tunnels, or bridges. |
| first_indexed | 2024-03-11T02:58:37Z |
| format | Article |
| id | doaj.art-787840a732764798ad6b56f263566fbf |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T02:58:37Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-787840a732764798ad6b56f263566fbf2023-11-18T08:27:48ZengMDPI AGRemote Sensing2072-42922023-05-011511272210.3390/rs15112722A New Region-Based Minimal Path Selection Algorithm for Crack Detection and Ground Truth Labeling Exploiting Gabor FiltersGonzalo de León0Nicholas Fiorentini1Pietro Leandri2Massimo Losa3Department of Civil and Industrial Engineering (DICI), Largo Lucio Lazzarino 1, University of Pisa, 56122 Pisa, ItalyDepartment of Civil and Industrial Engineering (DICI), Largo Lucio Lazzarino 1, University of Pisa, 56122 Pisa, ItalyDepartment of Civil and Industrial Engineering (DICI), Largo Lucio Lazzarino 1, University of Pisa, 56122 Pisa, ItalyDepartment of Civil and Industrial Engineering (DICI), Largo Lucio Lazzarino 1, University of Pisa, 56122 Pisa, ItalyCracks are fractures or breaks that occur in materials such as concrete, metals, rocks, and other solids. Various methods are used to detect and monitor cracks; among many of them, image-based methodologies allow fast identification of the distress and easy quantification of the percentage of cracks in the scene. Two main categories can be identified: classical and deep learning approaches. In the last decade, the tendency has moved towards the use of the latter. Even though they have proven their outstanding predicting performance, they suffer some drawbacks: a “black-box” nature leaves the user blind and without the possibility of modifying any parameters, a huge amount of labeled data is generally needed, a process that requires expert judgment is always required, and, finally, they tend to be time-consuming. Accordingly, the present study details the methodology for a new algorithm for crack segmentation based on the theory of minimal path selection combined with a region-based approach obtained through the segmentation of texture features extracted using Gabor filters. A pre-processing step is described, enabling the equalization of brightness and shadows, which results in better detection of local minima. These local minimal are constrained by a minimum distance between adjacent points, enabling a better coverage of the cracks. Afterward, a region-based segmentation technique is introduced to determine two areas that are used to determine threshold values used for rejection. This step is critical to generalize the algorithm to images presenting close-up scenes or wide cracks. Finally, a geometrical thresholding step is presented, allowing the exclusion of rounded areas and small isolated cracks. The results showed a very competitive <i>F</i>1-score (0.839), close to state-of-the-art values achieved with deep learning techniques. The main advantage of this approach is the transparency of the workflow, contrary to what happens with deep learning frameworks. In the proposed approach, no prior information is required; however, the statistical parameters may have to be adjusted to the particular case and requirements of the situation. The proposed algorithm results in a useful tool for researchers and practitioners needing to validate their results against some reference or needing labeled data for their models. Moreover, the current study could establish the grounds to standardize the procedure for crack segmentation with a lower human bias and faster results. The direct application of the methodology to images obtained with any low-cost sensor makes the proposed algorithm an operational support tool for authorities needing crack detection systems in order to monitor and evaluate the current state of the infrastructures, such as roads, tunnels, or bridges.https://www.mdpi.com/2072-4292/15/11/2722minimal pathGabor filterautomatic crack detectionground truthlabelingdeep learning |
| spellingShingle | Gonzalo de León Nicholas Fiorentini Pietro Leandri Massimo Losa A New Region-Based Minimal Path Selection Algorithm for Crack Detection and Ground Truth Labeling Exploiting Gabor Filters Remote Sensing minimal path Gabor filter automatic crack detection ground truth labeling deep learning |
| title | A New Region-Based Minimal Path Selection Algorithm for Crack Detection and Ground Truth Labeling Exploiting Gabor Filters |
| title_full | A New Region-Based Minimal Path Selection Algorithm for Crack Detection and Ground Truth Labeling Exploiting Gabor Filters |
| title_fullStr | A New Region-Based Minimal Path Selection Algorithm for Crack Detection and Ground Truth Labeling Exploiting Gabor Filters |
| title_full_unstemmed | A New Region-Based Minimal Path Selection Algorithm for Crack Detection and Ground Truth Labeling Exploiting Gabor Filters |
| title_short | A New Region-Based Minimal Path Selection Algorithm for Crack Detection and Ground Truth Labeling Exploiting Gabor Filters |
| title_sort | new region based minimal path selection algorithm for crack detection and ground truth labeling exploiting gabor filters |
| topic | minimal path Gabor filter automatic crack detection ground truth labeling deep learning |
| url | https://www.mdpi.com/2072-4292/15/11/2722 |
| work_keys_str_mv | AT gonzalodeleon anewregionbasedminimalpathselectionalgorithmforcrackdetectionandgroundtruthlabelingexploitinggaborfilters AT nicholasfiorentini anewregionbasedminimalpathselectionalgorithmforcrackdetectionandgroundtruthlabelingexploitinggaborfilters AT pietroleandri anewregionbasedminimalpathselectionalgorithmforcrackdetectionandgroundtruthlabelingexploitinggaborfilters AT massimolosa anewregionbasedminimalpathselectionalgorithmforcrackdetectionandgroundtruthlabelingexploitinggaborfilters AT gonzalodeleon newregionbasedminimalpathselectionalgorithmforcrackdetectionandgroundtruthlabelingexploitinggaborfilters AT nicholasfiorentini newregionbasedminimalpathselectionalgorithmforcrackdetectionandgroundtruthlabelingexploitinggaborfilters AT pietroleandri newregionbasedminimalpathselectionalgorithmforcrackdetectionandgroundtruthlabelingexploitinggaborfilters AT massimolosa newregionbasedminimalpathselectionalgorithmforcrackdetectionandgroundtruthlabelingexploitinggaborfilters |