A method for superfine pavement crack continuity detection based on topological loss
Abstract Deep convolutional neural networks have become a popular tool for the automatic detection of pavement cracks. Despite their widespread use, the models currently available tend to emphasize pixel‐level classification accuracy for cracks, often overlooking the critical aspect of crack continu...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-10-01
|
| Series: | Electronics Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ell2.12963 |
| _version_ | 1797661421400489984 |
|---|---|
| author | Guohui Jia Yang Lu Weidong Song Huan He Rongchen Ma |
| author_facet | Guohui Jia Yang Lu Weidong Song Huan He Rongchen Ma |
| author_sort | Guohui Jia |
| collection | DOAJ |
| description | Abstract Deep convolutional neural networks have become a popular tool for the automatic detection of pavement cracks. Despite their widespread use, the models currently available tend to emphasize pixel‐level classification accuracy for cracks, often overlooking the critical aspect of crack continuity. Addressing this gap, the authors’ research introduces a new method for the continuous detection of ultrafine pavement cracks, centred around the concept of topological loss. The authors’ novel approach hinges on expressing the disconnectivity between the background areas in an image through the connectivity of the cracks themselves. The proposed loss function accomplishes this by penalizing the unnecessary disconnection of the background areas, thereby minimizing the risk of false‐positive crack predictions. In this study, the authors trained and tested a crack‐detection network using the Crack500 dataset, as well as a new dataset specifically compiled for ultrafine crack analysis. The experimental outcomes indicate that the amalgamation of the mean squared error and the authors’ novel spatial topological loss function leads to a substantial improvement in the topological structure of ultrafine crack detection. |
| first_indexed | 2024-03-11T18:44:17Z |
| format | Article |
| id | doaj.art-f7f61631652243e3b7ffa51d32570379 |
| institution | Directory Open Access Journal |
| issn | 0013-5194 1350-911X |
| language | English |
| last_indexed | 2024-03-11T18:44:17Z |
| publishDate | 2023-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | Electronics Letters |
| spelling | doaj.art-f7f61631652243e3b7ffa51d325703792023-10-12T05:37:32ZengWileyElectronics Letters0013-51941350-911X2023-10-015919n/an/a10.1049/ell2.12963A method for superfine pavement crack continuity detection based on topological lossGuohui Jia0Yang Lu1Weidong Song2Huan He3Rongchen Ma4School of Resources and Civil Engineering Liaoning Institute of Science and Technology Benxi ChinaBeijing Xinxing Hua'an Intelligent Technology Co., Ltd Beijing ChinaSchool of Geomatics Liaoning Technical University Fuxin ChinaSchool of Geomatics Liaoning Technical University Fuxin ChinaSchool of Resources and Civil Engineering Liaoning Institute of Science and Technology Benxi ChinaAbstract Deep convolutional neural networks have become a popular tool for the automatic detection of pavement cracks. Despite their widespread use, the models currently available tend to emphasize pixel‐level classification accuracy for cracks, often overlooking the critical aspect of crack continuity. Addressing this gap, the authors’ research introduces a new method for the continuous detection of ultrafine pavement cracks, centred around the concept of topological loss. The authors’ novel approach hinges on expressing the disconnectivity between the background areas in an image through the connectivity of the cracks themselves. The proposed loss function accomplishes this by penalizing the unnecessary disconnection of the background areas, thereby minimizing the risk of false‐positive crack predictions. In this study, the authors trained and tested a crack‐detection network using the Crack500 dataset, as well as a new dataset specifically compiled for ultrafine crack analysis. The experimental outcomes indicate that the amalgamation of the mean squared error and the authors’ novel spatial topological loss function leads to a substantial improvement in the topological structure of ultrafine crack detection.https://doi.org/10.1049/ell2.12963convolutional neural netscrack detection |
| spellingShingle | Guohui Jia Yang Lu Weidong Song Huan He Rongchen Ma A method for superfine pavement crack continuity detection based on topological loss Electronics Letters convolutional neural nets crack detection |
| title | A method for superfine pavement crack continuity detection based on topological loss |
| title_full | A method for superfine pavement crack continuity detection based on topological loss |
| title_fullStr | A method for superfine pavement crack continuity detection based on topological loss |
| title_full_unstemmed | A method for superfine pavement crack continuity detection based on topological loss |
| title_short | A method for superfine pavement crack continuity detection based on topological loss |
| title_sort | method for superfine pavement crack continuity detection based on topological loss |
| topic | convolutional neural nets crack detection |
| url | https://doi.org/10.1049/ell2.12963 |
| work_keys_str_mv | AT guohuijia amethodforsuperfinepavementcrackcontinuitydetectionbasedontopologicalloss AT yanglu amethodforsuperfinepavementcrackcontinuitydetectionbasedontopologicalloss AT weidongsong amethodforsuperfinepavementcrackcontinuitydetectionbasedontopologicalloss AT huanhe amethodforsuperfinepavementcrackcontinuitydetectionbasedontopologicalloss AT rongchenma amethodforsuperfinepavementcrackcontinuitydetectionbasedontopologicalloss AT guohuijia methodforsuperfinepavementcrackcontinuitydetectionbasedontopologicalloss AT yanglu methodforsuperfinepavementcrackcontinuitydetectionbasedontopologicalloss AT weidongsong methodforsuperfinepavementcrackcontinuitydetectionbasedontopologicalloss AT huanhe methodforsuperfinepavementcrackcontinuitydetectionbasedontopologicalloss AT rongchenma methodforsuperfinepavementcrackcontinuitydetectionbasedontopologicalloss |