Building Surface Defect Detection Based on Improved YOLOv8
In intelligent building, efficient surface defect detection is crucial for structural safety and maintenance quality. Traditional methods face three challenges in complex scenarios: locating defect features accurately due to multi-scale texture and background interference, missing fine cracks becaus...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Buildings |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-5309/15/11/1865 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850158884803575808 |
|---|---|
| author | Xiaoxia Lin Yingzhou Meng Lin Sun Xiaodong Yang Chunwei Leng Yan Li Zhenyu Niu Weihao Gong Xinyue Xiao |
| author_facet | Xiaoxia Lin Yingzhou Meng Lin Sun Xiaodong Yang Chunwei Leng Yan Li Zhenyu Niu Weihao Gong Xinyue Xiao |
| author_sort | Xiaoxia Lin |
| collection | DOAJ |
| description | In intelligent building, efficient surface defect detection is crucial for structural safety and maintenance quality. Traditional methods face three challenges in complex scenarios: locating defect features accurately due to multi-scale texture and background interference, missing fine cracks because of their tiny size and low contrast, and the insufficient generalization of irregular defects due to complex geometric deformation. To address these issues, an improved version of the You Only Look Once (YOLOv8) algorithm is proposed for building surface defect detection. The dataset used in this study contains six common building surface defects, and the images are captured in diverse scenarios with different lighting conditions, building structures, and ages of material. Methodologically, the first step involves a normalization-based attention module (NAM). This module minimizes irrelevant features and redundant information and enhances the salient feature expression of cracks, delamination, and other defects, improving feature utilization. Second, for bottlenecks in fine crack detection, an explicit vision center (EVC) feature fusion module is introduced. It focuses on integrating specific details and overall context, improving the model’s effectiveness. Finally, the backbone network integrates deformable convolution net v2 (DCNV2) to capture the contour deformation features of targets like mesh cracks and spalling. Our experimental results indicate that the improved model outperforms YOLOv8, achieving a 3.9% higher mAP50 and a 4.2% better mAP50-95. Its performance reaches 156 FPS, suitable for real-time inspection in smart construction scenarios. Our model significantly improves defect detection accuracy and robustness in complex scenarios. The study offers a reliable solution for accurate multi-type defect detection on building surfaces. |
| format | Article |
| id | doaj-art-2e8a46fe307f47558d9e55bf3832bee9 |
| institution | OA Journals |
| issn | 2075-5309 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Buildings |
| spelling | doaj-art-2e8a46fe307f47558d9e55bf3832bee92025-08-20T02:23:44ZengMDPI AGBuildings2075-53092025-05-011511186510.3390/buildings15111865Building Surface Defect Detection Based on Improved YOLOv8Xiaoxia Lin0Yingzhou Meng1Lin Sun2Xiaodong Yang3Chunwei Leng4Yan Li5Zhenyu Niu6Weihao Gong7Xinyue Xiao8College of Intelligent Equipment, Shandong University of Science and Technology, Taian 271001, ChinaCollege of Intelligent Equipment, Shandong University of Science and Technology, Taian 271001, ChinaCollege of Intelligent Equipment, Shandong University of Science and Technology, Taian 271001, ChinaCollege of Intelligent Equipment, Shandong University of Science and Technology, Taian 271001, ChinaHanqing Data Consulting Co., Ltd., Zibo 255000, ChinaHanqing Data Consulting Co., Ltd., Zibo 255000, ChinaHanqing Data Consulting Co., Ltd., Zibo 255000, ChinaCollege of Intelligent Equipment, Shandong University of Science and Technology, Taian 271001, ChinaCollege of Intelligent Equipment, Shandong University of Science and Technology, Taian 271001, ChinaIn intelligent building, efficient surface defect detection is crucial for structural safety and maintenance quality. Traditional methods face three challenges in complex scenarios: locating defect features accurately due to multi-scale texture and background interference, missing fine cracks because of their tiny size and low contrast, and the insufficient generalization of irregular defects due to complex geometric deformation. To address these issues, an improved version of the You Only Look Once (YOLOv8) algorithm is proposed for building surface defect detection. The dataset used in this study contains six common building surface defects, and the images are captured in diverse scenarios with different lighting conditions, building structures, and ages of material. Methodologically, the first step involves a normalization-based attention module (NAM). This module minimizes irrelevant features and redundant information and enhances the salient feature expression of cracks, delamination, and other defects, improving feature utilization. Second, for bottlenecks in fine crack detection, an explicit vision center (EVC) feature fusion module is introduced. It focuses on integrating specific details and overall context, improving the model’s effectiveness. Finally, the backbone network integrates deformable convolution net v2 (DCNV2) to capture the contour deformation features of targets like mesh cracks and spalling. Our experimental results indicate that the improved model outperforms YOLOv8, achieving a 3.9% higher mAP50 and a 4.2% better mAP50-95. Its performance reaches 156 FPS, suitable for real-time inspection in smart construction scenarios. Our model significantly improves defect detection accuracy and robustness in complex scenarios. The study offers a reliable solution for accurate multi-type defect detection on building surfaces.https://www.mdpi.com/2075-5309/15/11/1865building surface defect detectionYOLOv8feature fusionnormalization-based attentiondeformable convolution |
| spellingShingle | Xiaoxia Lin Yingzhou Meng Lin Sun Xiaodong Yang Chunwei Leng Yan Li Zhenyu Niu Weihao Gong Xinyue Xiao Building Surface Defect Detection Based on Improved YOLOv8 Buildings building surface defect detection YOLOv8 feature fusion normalization-based attention deformable convolution |
| title | Building Surface Defect Detection Based on Improved YOLOv8 |
| title_full | Building Surface Defect Detection Based on Improved YOLOv8 |
| title_fullStr | Building Surface Defect Detection Based on Improved YOLOv8 |
| title_full_unstemmed | Building Surface Defect Detection Based on Improved YOLOv8 |
| title_short | Building Surface Defect Detection Based on Improved YOLOv8 |
| title_sort | building surface defect detection based on improved yolov8 |
| topic | building surface defect detection YOLOv8 feature fusion normalization-based attention deformable convolution |
| url | https://www.mdpi.com/2075-5309/15/11/1865 |
| work_keys_str_mv | AT xiaoxialin buildingsurfacedefectdetectionbasedonimprovedyolov8 AT yingzhoumeng buildingsurfacedefectdetectionbasedonimprovedyolov8 AT linsun buildingsurfacedefectdetectionbasedonimprovedyolov8 AT xiaodongyang buildingsurfacedefectdetectionbasedonimprovedyolov8 AT chunweileng buildingsurfacedefectdetectionbasedonimprovedyolov8 AT yanli buildingsurfacedefectdetectionbasedonimprovedyolov8 AT zhenyuniu buildingsurfacedefectdetectionbasedonimprovedyolov8 AT weihaogong buildingsurfacedefectdetectionbasedonimprovedyolov8 AT xinyuexiao buildingsurfacedefectdetectionbasedonimprovedyolov8 |