This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
A Novel YOLOv10-DECA Model for Real-Time Detection of Concrete Cracks
by
Chaokai Zhang
Chaokai Zhang
Chaokai Zhang obtained his bachelor's degree from Fujian University of Technology in 2022 and is a [...]
Chaokai Zhang obtained his bachelor's degree from Fujian University of Technology in 2022 and is currently pursuing a master's degree at NanJing Tech University as a joint cultivated graduate student between NanJing Tech University and Huaiyin Institute of Technology. His research area focuses on the application of deep learning technologies in civil engineering.
1,2,
Ningbo Peng
Ningbo Peng
Ningbo Peng received his Ph.D. in Geotechnical Engineering from the School of Civil Engineering and [...]
Ningbo Peng received his Ph.D. in Geotechnical Engineering from the School of Civil Engineering and Mechanics at Lanzhou University in June 2014. He is currently conducting postdoctoral research at the Institute of Cultural Heritage Protection Basic Science Research at Shanghai University. He previously worked as a lecturer at the School of Architectural Engineering at Huaiyin Institute of Technology
(December 2014–August 2020). In September 2020, he was promoted to associate professor in the same school and became the deputy dean in April 2021. His main research topics include cultural heritage protection, rock mechanics, and geotechnical engineering.
1,2,3,4,*,
Jiaheng Yan
Jiaheng Yan
Jiaheng Yan obtained his Ph.D. in Geotechnical Engineering from the School of Civil Engineering at [...]
Jiaheng Yan obtained his Ph.D. in Geotechnical Engineering from the School of Civil Engineering and
Transportation at Hohai University in December 2022. He is currently working asa lecturer at the School of Architectural Engineering at Huaiyin Institute of Technology. He studied Geotechnical Engineering at the School of Civil Engineering and Transportation at Hohai University (September 2016–December 2022). In January 2023, he joined the School of Architectural Engineering at Huaiyin Institute of Technology as a lecturer. His research topics mainly include geotechnical engineering seepage tracing, isotope hydrological cycle processes, and watershed water environment evolution.
1,
Lixu Wang
Lixu Wang
Lixu Wang obtained his bachelor’s degree from Huaiyin Institute of Technology in 2023 and is his [...]
Lixu Wang obtained his bachelor’s degree from Huaiyin Institute of Technology in 2023 and is currently pursuing his master’s degree at the same institution. His research areas focus mainly on cultural heritage protection, cave temple preservation, and weathering experimental studies. In the field of cultural heritage protection, Wang Lixu is dedicated to exploring preservation methods that combine traditional and modern technologies. He is particularly interested in cave temple preservation, with research including structural stability assessments of cave temples and the impact of environmental factors on caves. In his weathering experimental studies, he simulates various environmental conditions to study the aging process of different materials, providing scientific basis for cultural relic protection.
1,
Yinjia Chen
Yinjia Chen
Yinjia Chen, graduated from Suqian University in 2023 with a bachelor’s degree. He is currently a [...]
Yinjia Chen, graduated from Suqian University in 2023 with a bachelor’s degree. He is currently pursuing a master’s degree at Huaiyin Institute of Technology, with his main research directions being cultural heritage protection, data analysis, and studies on the attractiveness of ancient architecture and cultural heritage sites. In the field of cultural heritage protection, Chen Yinjia focuses on applying modern data analysis techniques, using big data mining and analysis to support decision-making in cultural relic protection. He also pays attention to research on the attractiveness of ancient architecture and cultural heritage sites, exploring ways to enhance public appeal while preserving cultural relics. Chen Yinjia’s research aims to organically combine traditional cultural preservation with modern technology, contributing to the sustainable development of cultural heritage.
1,
Zhancheng Zhou
Zhancheng Zhou
Zhancheng Zhou received his bachelor's degree from Anhui Polytechnic University in 2021 and is a at [...]
Zhancheng Zhou received his bachelor's degree from Anhui Polytechnic University in 2021 and is currently pursuing a master's degree at Nanjing Tech University as a joint cultivated graduate
student between Nanjing Tech University and Huaiyin Institute of Technology. His research area focuses on the impact of nickel slag material addition on concrete properties.
1,2 and
Ye Zhu
Ye Zhu
Ye Zhu received her Ph.D. in Hydraulic Structure Engineering from Dalian University of Technology a [...]
Ye Zhu received her Ph.D. in Hydraulic Structure Engineering from Dalian University of Technology in June 2017 and is currently working as a lecturer at the School of Architectural Engineering at the Huaiyin
Institute of Technology. She pursued her master's and doctoral studies in Hydraulic Structure Engineering at Dalian University of Technology (September 2011–June 2017). In July 2017, she joined the School of Architectural Engineering at the Huaiyin Institute of Technology as a lecturer. Her main research topics include hydraulic structures, civil engineering, and stone cultural relic protection.
1,5,*
1
Faculty of Architecture and Civil Engineering, Huaiyin Institute of Technology, Huaian 223001, China
2
College of Civil Engineering, Nanjing Tech University, Nanjing 211816, China
3
Institute for the Conservation of Cultural Heritage, School of Cultural Heritage and Information Management, Shanghai University, Shanghai 200444, China
4
Key Laboratory of Silicate Cultural Relics Conservation, Shanghai University, Ministry of Education, Shanghai 200444, China
5
Key Scientific Research Base of the State Administration of Cultural Heritage for Integrated Technology and Application of Grotto Cultural Heritage Protection Engineering Department, Chengdu 610036, China
*
Authors to whom correspondence should be addressed.
Buildings 2024, 14(10), 3230; https://doi.org/10.3390/buildings14103230 (registering DOI)
Submission received: 5 September 2024
/
Revised: 6 October 2024
/
Accepted: 9 October 2024
/
Published: 11 October 2024
Abstract
The You Only Look Once (YOLO) series algorithms have been widely adopted in concrete crack detection, with attention mechanisms frequently being incorporated to enhance recognition accuracy and efficiency. However, existing research is confronted by two primary challenges: the suboptimal performance of attention mechanism modules and the lack of explanation regarding how these mechanisms influence the model’s decision-making process to improve accuracy. To address these issues, a novel Dynamic Efficient Channel Attention (DECA) module is proposed in this study, which is designed to enhance the performance of the YOLOv10 model in concrete crack detection, and the effectiveness of this module is visually demonstrated through the application of interpretable analysis algorithms. In this paper, a concrete dataset with a complex background is used. Experimental results indicate that the DECA module significantly improves the model’s accuracy in crack localization and the detection of discontinuous cracks, outperforming the existing Efficient Channel Attention (ECA). When compared to the similarly sized YOLOv10n model, the proposed YOLOv10-DECA model demonstrates improvements of 4.40%, 3.06%, 4.48%, and 5.56% in precision, recall, mAP50, and mAP50-95 metrics, respectively. Moreover, even when compared with the larger YOLOv10s model, these performance indicators are increased by 2.00%, 0.04%, 2.27%, and 1.12%, respectively. In terms of speed evaluation, owing to the lightweight design of the DECA module, the YOLOv10-DECA model achieves an inference speed of 78 frames per second, which is 2.5 times faster than YOLOv10s, thereby fully meeting the requirements for real-time detection. These results demonstrate that an optimized balance between accuracy and speed in concrete crack detection tasks has been achieved by the YOLOv10-DECA model. Consequently, this study provides valuable insights for future research and applications in this field.
Share and Cite
MDPI and ACS Style
Zhang, C.; Peng, N.; Yan, J.; Wang, L.; Chen, Y.; Zhou, Z.; Zhu, Y.
A Novel YOLOv10-DECA Model for Real-Time Detection of Concrete Cracks. Buildings 2024, 14, 3230.
https://doi.org/10.3390/buildings14103230
AMA Style
Zhang C, Peng N, Yan J, Wang L, Chen Y, Zhou Z, Zhu Y.
A Novel YOLOv10-DECA Model for Real-Time Detection of Concrete Cracks. Buildings. 2024; 14(10):3230.
https://doi.org/10.3390/buildings14103230
Chicago/Turabian Style
Zhang, Chaokai, Ningbo Peng, Jiaheng Yan, Lixu Wang, Yinjia Chen, Zhancheng Zhou, and Ye Zhu.
2024. "A Novel YOLOv10-DECA Model for Real-Time Detection of Concrete Cracks" Buildings 14, no. 10: 3230.
https://doi.org/10.3390/buildings14103230
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.