Slope Protection and Cutting Identification of Foundation Pit Construction Based on Deep Learning and Binocular Vision

Bo Wang, Donghai Liu () and Han Liu
Additional contact information
Bo Wang: Tianjin University
Donghai Liu: Tianjin University
Han Liu: Tianjin University

Chapter Chapter 120 in Proceedings of the 28th International Symposium on Advancement of Construction Management and Real Estate, 2024, pp 1733-1750 from Springer

Abstract: Abstract 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.

Keywords: Foundation construction; Slope protection; Slope cutting identification; Deep learning; Binocular stereo vision; Adjacent constraint detection (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnopch:978-981-97-1949-5_121

Ordering information: This item can be ordered from
http://www.springer.com/9789819719495

DOI: 10.1007/978-981-97-1949-5_121

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().