BFD-YOLO: A YOLOv7-Based Detection Method for Building Façade Defects
Façade defects not only detract from the building’s aesthetics but also compromise its performance. Furthermore, they potentially endanger pedestrians, occupants, and property. Existing deep-learning-based methodologies are facing some challenges in terms of recognition speed and model complexity. A...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/17/3612 |
| _version_ | 1797582707143737344 |
|---|---|
| author | Guofeng Wei Fang Wan Wen Zhou Chengzhi Xu Zhiwei Ye Wei Liu Guangbo Lei Li Xu |
| author_facet | Guofeng Wei Fang Wan Wen Zhou Chengzhi Xu Zhiwei Ye Wei Liu Guangbo Lei Li Xu |
| author_sort | Guofeng Wei |
| collection | DOAJ |
| description | Façade defects not only detract from the building’s aesthetics but also compromise its performance. Furthermore, they potentially endanger pedestrians, occupants, and property. Existing deep-learning-based methodologies are facing some challenges in terms of recognition speed and model complexity. An improved YOLOv7 method, named BFD-YOLO, is proposed to ensure the accuracy and speed of building façade defects detection in this paper. Firstly, the original ELAN module in YOLOv7 was substituted with a lightweight MobileOne module to diminish the quantity of parameters and enhance the speed of inference. Secondly, the coordinate attention module was added to the model to enhance feature extraction capability. Next, the SCYLLA-IoU was used to expedite the rate of convergence and increase the recall of the model. Finally, we have extended the open datasets to construct a building façade damage dataset that includes three typical defects. BFD-YOLO demonstrates excellent accuracy and efficiency based on this dataset. Compared to YOLOv7, BFD-YOLO’s precision and mAP@.5 are improved by 2.2% and 2.9%, respectively, while maintaining comparable efficiency. The experimental results indicate that the proposed method obtained higher detection accuracy with guaranteed real-time performance. |
| first_indexed | 2024-03-10T23:25:14Z |
| format | Article |
| id | doaj.art-fb9d54b4ab48421e9729eac4a89348fd |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T23:25:14Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-fb9d54b4ab48421e9729eac4a89348fd2023-11-19T08:01:37ZengMDPI AGElectronics2079-92922023-08-011217361210.3390/electronics12173612BFD-YOLO: A YOLOv7-Based Detection Method for Building Façade DefectsGuofeng Wei0Fang Wan1Wen Zhou2Chengzhi Xu3Zhiwei Ye4Wei Liu5Guangbo Lei6Li Xu7School of Computer Science, Hubei University of Technology, Wuhan 430068, ChinaSchool of Computer Science, Hubei University of Technology, Wuhan 430068, ChinaSchool of Computer Science, Hubei University of Technology, Wuhan 430068, ChinaSchool of Computer Science, Hubei University of Technology, Wuhan 430068, ChinaSchool of Computer Science, Hubei University of Technology, Wuhan 430068, ChinaSchool of Computer Science, Hubei University of Technology, Wuhan 430068, ChinaSchool of Computer Science, Hubei University of Technology, Wuhan 430068, ChinaSchool of Computer Science, Hubei University of Technology, Wuhan 430068, ChinaFaçade defects not only detract from the building’s aesthetics but also compromise its performance. Furthermore, they potentially endanger pedestrians, occupants, and property. Existing deep-learning-based methodologies are facing some challenges in terms of recognition speed and model complexity. An improved YOLOv7 method, named BFD-YOLO, is proposed to ensure the accuracy and speed of building façade defects detection in this paper. Firstly, the original ELAN module in YOLOv7 was substituted with a lightweight MobileOne module to diminish the quantity of parameters and enhance the speed of inference. Secondly, the coordinate attention module was added to the model to enhance feature extraction capability. Next, the SCYLLA-IoU was used to expedite the rate of convergence and increase the recall of the model. Finally, we have extended the open datasets to construct a building façade damage dataset that includes three typical defects. BFD-YOLO demonstrates excellent accuracy and efficiency based on this dataset. Compared to YOLOv7, BFD-YOLO’s precision and mAP@.5 are improved by 2.2% and 2.9%, respectively, while maintaining comparable efficiency. The experimental results indicate that the proposed method obtained higher detection accuracy with guaranteed real-time performance.https://www.mdpi.com/2079-9292/12/17/3612building façade defectsobject detectionYOLOv7MobileOne |
| spellingShingle | Guofeng Wei Fang Wan Wen Zhou Chengzhi Xu Zhiwei Ye Wei Liu Guangbo Lei Li Xu BFD-YOLO: A YOLOv7-Based Detection Method for Building Façade Defects Electronics building façade defects object detection YOLOv7 MobileOne |
| title | BFD-YOLO: A YOLOv7-Based Detection Method for Building Façade Defects |
| title_full | BFD-YOLO: A YOLOv7-Based Detection Method for Building Façade Defects |
| title_fullStr | BFD-YOLO: A YOLOv7-Based Detection Method for Building Façade Defects |
| title_full_unstemmed | BFD-YOLO: A YOLOv7-Based Detection Method for Building Façade Defects |
| title_short | BFD-YOLO: A YOLOv7-Based Detection Method for Building Façade Defects |
| title_sort | bfd yolo a yolov7 based detection method for building facade defects |
| topic | building façade defects object detection YOLOv7 MobileOne |
| url | https://www.mdpi.com/2079-9292/12/17/3612 |
| work_keys_str_mv | AT guofengwei bfdyoloayolov7baseddetectionmethodforbuildingfacadedefects AT fangwan bfdyoloayolov7baseddetectionmethodforbuildingfacadedefects AT wenzhou bfdyoloayolov7baseddetectionmethodforbuildingfacadedefects AT chengzhixu bfdyoloayolov7baseddetectionmethodforbuildingfacadedefects AT zhiweiye bfdyoloayolov7baseddetectionmethodforbuildingfacadedefects AT weiliu bfdyoloayolov7baseddetectionmethodforbuildingfacadedefects AT guangbolei bfdyoloayolov7baseddetectionmethodforbuildingfacadedefects AT lixu bfdyoloayolov7baseddetectionmethodforbuildingfacadedefects |