Gray Brick Wall Surface Damage Detection of Traditional Chinese Buildings in Macau: Damage Quantification and Thermodynamic Analysis Method via YOLOv8 Technology
The historical Lingnan gray brick buildings in Macau, a World Heritage Site, are facing severe deterioration due to prolonged disrepair, manifesting as cracks, breakages, moss adhesion, and other types of surface damage. These issues threaten not only the structural stability of the buildings but al...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/12/6665 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839654935068672000 |
|---|---|
| author | Liang Zheng Jianyi Zheng Yile Chen Yuchan Zheng Wei Lao Shuaipeng Chen |
| author_facet | Liang Zheng Jianyi Zheng Yile Chen Yuchan Zheng Wei Lao Shuaipeng Chen |
| author_sort | Liang Zheng |
| collection | DOAJ |
| description | The historical Lingnan gray brick buildings in Macau, a World Heritage Site, are facing severe deterioration due to prolonged disrepair, manifesting as cracks, breakages, moss adhesion, and other types of surface damage. These issues threaten not only the structural stability of the buildings but also the conservation of cultural heritage. To address the inefficiencies and low accuracy of traditional manual inspections, this study proposes an automated recognition and quantitative detection method for wall surface damage based on the YOLOv8 deep learning object detection model. A dataset comprising 375 annotated images collected from 162 gray brick historical buildings in Macau was constructed, covering eight damage categories: crack, damage, missing, vandalism, moss, stain, plant, and intact. The model was trained and validated using a stratified sampling approach to maintain a balanced class distribution, and its performance was comprehensively evaluated through metrics such as the mean average precision (mAP), F1 score, and confusion matrices. The results indicate that the best-performing model (Model 3 at the 297th epoch) achieved a mAP of 61.51% and an F1 score up to 0.74 on the test set, with superior detection accuracy and stability. Heatmap analysis demonstrated the model’s ability to accurately focus on damaged regions in close-range images, while damage quantification tests showed high consistency with manual assessments, confirming the model’s practical viability. Furthermore, a portable, integrated device embedding the trained YOLOv8 model was developed and successfully deployed in real-world scenarios, enabling real-time damage detection and reporting. This study highlights the potential of deep learning technology for enhancing the efficiency and reliability of architectural heritage protection and provides a foundation for future research involving larger datasets and more refined classification strategies. |
| format | Article |
| id | doaj-art-af414bc4da6e439487e9d6b51a3bdb6f |
| institution | Matheson Library |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-af414bc4da6e439487e9d6b51a3bdb6f2025-06-25T13:25:41ZengMDPI AGApplied Sciences2076-34172025-06-011512666510.3390/app15126665Gray Brick Wall Surface Damage Detection of Traditional Chinese Buildings in Macau: Damage Quantification and Thermodynamic Analysis Method via YOLOv8 TechnologyLiang Zheng0Jianyi Zheng1Yile Chen2Yuchan Zheng3Wei Lao4Shuaipeng Chen5Heritage Conservation Laboratory, Faculty of Humanities and Arts, Macau University of Science and Technology, Taipa, Macau 999078, ChinaHeritage Conservation Laboratory, Faculty of Humanities and Arts, Macau University of Science and Technology, Taipa, Macau 999078, ChinaHeritage Conservation Laboratory, Faculty of Humanities and Arts, Macau University of Science and Technology, Taipa, Macau 999078, ChinaHeritage Conservation Laboratory, Faculty of Humanities and Arts, Macau University of Science and Technology, Taipa, Macau 999078, ChinaHeritage Conservation Laboratory, Faculty of Humanities and Arts, Macau University of Science and Technology, Taipa, Macau 999078, ChinaHeritage Conservation Laboratory, Faculty of Humanities and Arts, Macau University of Science and Technology, Taipa, Macau 999078, ChinaThe historical Lingnan gray brick buildings in Macau, a World Heritage Site, are facing severe deterioration due to prolonged disrepair, manifesting as cracks, breakages, moss adhesion, and other types of surface damage. These issues threaten not only the structural stability of the buildings but also the conservation of cultural heritage. To address the inefficiencies and low accuracy of traditional manual inspections, this study proposes an automated recognition and quantitative detection method for wall surface damage based on the YOLOv8 deep learning object detection model. A dataset comprising 375 annotated images collected from 162 gray brick historical buildings in Macau was constructed, covering eight damage categories: crack, damage, missing, vandalism, moss, stain, plant, and intact. The model was trained and validated using a stratified sampling approach to maintain a balanced class distribution, and its performance was comprehensively evaluated through metrics such as the mean average precision (mAP), F1 score, and confusion matrices. The results indicate that the best-performing model (Model 3 at the 297th epoch) achieved a mAP of 61.51% and an F1 score up to 0.74 on the test set, with superior detection accuracy and stability. Heatmap analysis demonstrated the model’s ability to accurately focus on damaged regions in close-range images, while damage quantification tests showed high consistency with manual assessments, confirming the model’s practical viability. Furthermore, a portable, integrated device embedding the trained YOLOv8 model was developed and successfully deployed in real-world scenarios, enabling real-time damage detection and reporting. This study highlights the potential of deep learning technology for enhancing the efficiency and reliability of architectural heritage protection and provides a foundation for future research involving larger datasets and more refined classification strategies.https://www.mdpi.com/2076-3417/15/12/6665wall surface damagetraditional Chinese buildingsYOLOv8 technologymachine learningidentification devicegray brick |
| spellingShingle | Liang Zheng Jianyi Zheng Yile Chen Yuchan Zheng Wei Lao Shuaipeng Chen Gray Brick Wall Surface Damage Detection of Traditional Chinese Buildings in Macau: Damage Quantification and Thermodynamic Analysis Method via YOLOv8 Technology Applied Sciences wall surface damage traditional Chinese buildings YOLOv8 technology machine learning identification device gray brick |
| title | Gray Brick Wall Surface Damage Detection of Traditional Chinese Buildings in Macau: Damage Quantification and Thermodynamic Analysis Method via YOLOv8 Technology |
| title_full | Gray Brick Wall Surface Damage Detection of Traditional Chinese Buildings in Macau: Damage Quantification and Thermodynamic Analysis Method via YOLOv8 Technology |
| title_fullStr | Gray Brick Wall Surface Damage Detection of Traditional Chinese Buildings in Macau: Damage Quantification and Thermodynamic Analysis Method via YOLOv8 Technology |
| title_full_unstemmed | Gray Brick Wall Surface Damage Detection of Traditional Chinese Buildings in Macau: Damage Quantification and Thermodynamic Analysis Method via YOLOv8 Technology |
| title_short | Gray Brick Wall Surface Damage Detection of Traditional Chinese Buildings in Macau: Damage Quantification and Thermodynamic Analysis Method via YOLOv8 Technology |
| title_sort | gray brick wall surface damage detection of traditional chinese buildings in macau damage quantification and thermodynamic analysis method via yolov8 technology |
| topic | wall surface damage traditional Chinese buildings YOLOv8 technology machine learning identification device gray brick |
| url | https://www.mdpi.com/2076-3417/15/12/6665 |
| work_keys_str_mv | AT liangzheng graybrickwallsurfacedamagedetectionoftraditionalchinesebuildingsinmacaudamagequantificationandthermodynamicanalysismethodviayolov8technology AT jianyizheng graybrickwallsurfacedamagedetectionoftraditionalchinesebuildingsinmacaudamagequantificationandthermodynamicanalysismethodviayolov8technology AT yilechen graybrickwallsurfacedamagedetectionoftraditionalchinesebuildingsinmacaudamagequantificationandthermodynamicanalysismethodviayolov8technology AT yuchanzheng graybrickwallsurfacedamagedetectionoftraditionalchinesebuildingsinmacaudamagequantificationandthermodynamicanalysismethodviayolov8technology AT weilao graybrickwallsurfacedamagedetectionoftraditionalchinesebuildingsinmacaudamagequantificationandthermodynamicanalysismethodviayolov8technology AT shuaipengchen graybrickwallsurfacedamagedetectionoftraditionalchinesebuildingsinmacaudamagequantificationandthermodynamicanalysismethodviayolov8technology |