Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Slope Protection and Cutting Identification of Foundation Pit Construction Based on Deep Learning and Binocular Vision
https://orcid.org/http://orcid.org/0009-0007-5139-9655
https://orcid.org/http://orcid.org/0009-0003-4676-0611
https://orcid.org/http://orcid.org/0009-0006-1973-716X
Excavation slope protection and reasonable slope cutting are crucial for construction safety in foundation pits. Currently, manual on-site inspections are frequently used to check whether slope protection and slope cutting (SPSC) meet safety requirements. However, due to the dynamic changes in the excavation face of the foundation pit, human negligence, or delayed detection, it is challenging to ensure that SPSC are executed according to requirements, which poses a safety accident to construction. To address this issue, a method for identifying SPSC in foundation pit construction based on deep learning and binocular vision is proposed. Firstly, the YOLOv7 target detection model is used to recognize slope protection facilities and determine the slope area range based on the video monitoring images at the job construction site. Then, using the binocular stereo vision method, the 3D spatial coordinates of each pixel in the slope area range in the images are obtained. Finally, the adjacent constraint detection method is used to optimize the point cloud data of the foundation pit slope, fit the slope surface and calculate the slope angle, which is used to determine whether the slope protection facilities are in compliance and whether the slope cutting meets specification requirements. A case analysis result shows that the recognition accuracy of the foundation pit slope and protection facilities calculated by this method is 0.93, the measurement error of the slope angle is 0.64°, and the relative error is 1.51%. It meets the practical accuracy requirements and provides an automated intelligent means for safety management and control of foundation pit construction.
Slope Protection and Cutting Identification of Foundation Pit Construction Based on Deep Learning and Binocular Vision
https://orcid.org/http://orcid.org/0009-0007-5139-9655
https://orcid.org/http://orcid.org/0009-0003-4676-0611
https://orcid.org/http://orcid.org/0009-0006-1973-716X
Excavation slope protection and reasonable slope cutting are crucial for construction safety in foundation pits. Currently, manual on-site inspections are frequently used to check whether slope protection and slope cutting (SPSC) meet safety requirements. However, due to the dynamic changes in the excavation face of the foundation pit, human negligence, or delayed detection, it is challenging to ensure that SPSC are executed according to requirements, which poses a safety accident to construction. To address this issue, a method for identifying SPSC in foundation pit construction based on deep learning and binocular vision is proposed. Firstly, the YOLOv7 target detection model is used to recognize slope protection facilities and determine the slope area range based on the video monitoring images at the job construction site. Then, using the binocular stereo vision method, the 3D spatial coordinates of each pixel in the slope area range in the images are obtained. Finally, the adjacent constraint detection method is used to optimize the point cloud data of the foundation pit slope, fit the slope surface and calculate the slope angle, which is used to determine whether the slope protection facilities are in compliance and whether the slope cutting meets specification requirements. A case analysis result shows that the recognition accuracy of the foundation pit slope and protection facilities calculated by this method is 0.93, the measurement error of the slope angle is 0.64°, and the relative error is 1.51%. It meets the practical accuracy requirements and provides an automated intelligent means for safety management and control of foundation pit construction.
Slope Protection and Cutting Identification of Foundation Pit Construction Based on Deep Learning and Binocular Vision
https://orcid.org/http://orcid.org/0009-0007-5139-9655
https://orcid.org/http://orcid.org/0009-0003-4676-0611
https://orcid.org/http://orcid.org/0009-0006-1973-716X
Excavation slope protection and reasonable slope cutting are crucial for construction safety in foundation pits. Currently, manual on-site inspections are frequently used to check whether slope protection and slope cutting (SPSC) meet safety requirements. However, due to the dynamic changes in the excavation face of the foundation pit, human negligence, or delayed detection, it is challenging to ensure that SPSC are executed according to requirements, which poses a safety accident to construction. To address this issue, a method for identifying SPSC in foundation pit construction based on deep learning and binocular vision is proposed. Firstly, the YOLOv7 target detection model is used to recognize slope protection facilities and determine the slope area range based on the video monitoring images at the job construction site. Then, using the binocular stereo vision method, the 3D spatial coordinates of each pixel in the slope area range in the images are obtained. Finally, the adjacent constraint detection method is used to optimize the point cloud data of the foundation pit slope, fit the slope surface and calculate the slope angle, which is used to determine whether the slope protection facilities are in compliance and whether the slope cutting meets specification requirements. A case analysis result shows that the recognition accuracy of the foundation pit slope and protection facilities calculated by this method is 0.93, the measurement error of the slope angle is 0.64°, and the relative error is 1.51%. It meets the practical accuracy requirements and provides an automated intelligent means for safety management and control of foundation pit construction.
Slope Protection and Cutting Identification of Foundation Pit Construction Based on Deep Learning and Binocular Vision
Lecture Notes in Operations res.
Li, Dezhi (Herausgeber:in) / Zou, Patrick X. W. (Herausgeber:in) / Yuan, Jingfeng (Herausgeber:in) / Wang, Qian (Herausgeber:in) / Peng, Yi (Herausgeber:in) / Wang, Bo (Autor:in) / Liu, Donghai (Autor:in) / Liu, Han (Autor:in)
International Symposium on Advancement of Construction Management and Real Estate ; 2023 ; Jiulonghu Hotel, Nanjing, China
Proceedings of the 28th International Symposium on Advancement of Construction Management and Real Estate ; Kapitel: 121 ; 1733-1750
28.11.2024
18 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
| Europäisches Patentamt | 2023
Deep cutting high slope active protection system and construction method
| Europäisches Patentamt | 2024
System for foundation pit slope protection construction
Europäisches Patentamt | 2020