含巡檢規劃、劣化辨識、損傷量化之進階建物劣化檢測架構

Framework of Advanced Building Inspection with Route Planning, Defect Detection, and Damage Rating

許舜翔(Shun-Hsiang Hsu) ； 許筠曼(Yun-Man Hsu) ； 洪昊天(Ho-Tin Hung) ； 林禹齊 ； 張家銘(Chia-Ming Chang) ； 陳宗珷(Tzung-Wu Chen) ； 陳俊仲(Chun-Chung Chen)

《結構工程》 37卷4期 (2022/12) Pp. 6-26

https://doi.org/10.6849/SE.202212_37(4).0001

摘要

目視檢測常用於結構檢測中，以快速評估建物中構件或材料之耐用性，及尋找可能的損傷。然而，傳統目視檢測相當耗費人力及時間，鑒於以上問題，本研究開發一個進階的建物劣化檢測架構，其中功能包括巡檢規劃、即時劣化識別、損傷程度判別及記錄詳細的損傷狀況。於該架構中，首先規劃巡檢草圖，提供檢測時最有效率檢測路徑；接著本研究使用Scaled-YOLOv4，進行損傷物件偵測，該方法於大規模場域中，也能快速檢測損傷，並使用SOLOv2模型，對混凝土裂縫位置進行像素等級之實例分割，以利更精確的裂縫量化；最後，根據檢測到的劣化嚴重性及面積大小，對構件的損傷程度進行評級。本研究以一所小學之走廊進行實際場域驗證，目的為檢測和量化混凝土構件之表面劣化。由驗證結果可見，藉由本研究之進階建物劣化檢測架構，於劣化辨識、損傷量化和檢測效率上，相較傳統建物目視檢測都獲得顯著改善。

並列摘要

Visual inspection is commonly adopted for building operation, maintenance, and safety. The durability and defects of components or materials in buildings can be quickly assessed through visual inspection. However, implementations of visual inspection are substantially time-consuming, labor-intensive, and error-prone because useful auxiliary tools that can instantly highlight defects or damage locations from images are not available. Therefore, an advanced building inspection framework is developed and implemented with route planning, real-time and detailed damage recognition, and damage rating in this study. The inspection route sketching is first exploited to provide an efficient plan with significantly reduced disruption. Then, Scaled-YOLOv4 and SOLOv2 models are considered in this study to detect defects even in a large-scale field quickly and acquire pixel-level damage recognition for more precise quantification, respectively. Finally, damage levels of components are rated following the importance and numbers per unit area of the detected defects. This entire framework is also implemented and verified by the hallway of an elementary school to detect and quantify surface damage of concrete components. As seen in the results, the conventional building inspection is significantly improved by the aid of the proposed framework in terms of damage localization, damage quantification, and inspection efficiency.

參考文獻

Abdel-Qader, I., Abudayyeh, O., and M. E. Kelly. 2003. "Analysis of edge-detection techniques for crack identification in bridges," J. Comput. Civ. Eng. 17 (4): 255-63. https://doi.org/10.1061/(ASCE)0887-3801(2003)17:4(255).

Anand, T., Sinha, S., Mandal, M., Chamola, V., and F. R. Yu. 2021. "AgriSegNet: Deep aerial semantic segmentation framework for IoT-assisted precision agriculture." IEEE Sens. J., 21 (16), 17581–17590. https://doi.org/10.1109/JSEN.2021.3071290.

Carrasco, M., Araya-Letelier, G., Velázquez, R., and P. Visconti. 2021. "Image-based automated width measurement of surface cracking." Sensors, 21 (22), 7534. https://doi.org/10.3390/s21227534.

Gupta, S., Girshick, R., Arbeláez, P., and J. Malik. 2014. "Learning rich features from RGB-D images for object detection and segmentation." In Proc., European Conf. on Computer Vision, 45-360. Springer, Cham. https://doi.org/10.1007/978-3-319-10584-0_23.

Hamledari, H., Sajedi, S. O., McCabe, B., and M. A. Fischer. 2021. "Automation of inspection mission planning using 4D BIMs and in support of unmanned aerial vehicle–based data collection." J. Constr. Eng. Manag. 147(3): 04020179. https://doi.org/10.1061/(ASCE)CO.1943-7862.0001995.