RESEARCH ARTICLE
Detection of Rockfalls on Tunnel Faces Using Extracted Moving Objects, Excavation Point Estimation, and Generation of Trajectory Images
Rei Kobayashi1, *, Yoshihiro Sato1, Yoshiki Takahashi1, Masahito Maemura2, Masaya Miura2, Yue Bao1
Article Information
Identifiers and Pagination:
Year: 2022Volume: 16
E-location ID: e187414952207130
Publisher ID: e187414952207130
DOI: 10.2174/18741495-v16-e2207130
Article History:
Received Date: 30/3/2022Revision Received Date: 15/4/2022
Acceptance Date: 19/5/2022
Electronic publication date: 04/10/2022
Collection year: 2022
open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Abstract
Background:
Tunnels are constructed at various locations for infrastructural purposes. During tunnel construction, industrial accidents have occurred due to rockfalls at tunnel faces. In addition, it has been confirmed that large rockfalls are precursors to tunnel collapses. Visual monitoring is currently used to detect such rockfalls. However, there are limitations to visual monitoring, and monitoring equipment is needed.
Objective:
In existing research, the inter-frame difference method of image processing and laser measurement methods have been proposed. However, there are difficulties in monitoring the entirety of the tunnel face using these methods. Thus, we propose methods that can overcome these difficulties and accurately detect rockfalls and identify where they occur.
Methods:
In this study, we propose a method for detecting rockfalls by combining the extraction of moving objects on a tunnel face and the estimation of excavation points. To identify the location of the rockfalls, rockfall trajectory images were generated.
Results:
Through experiments conducted during excavation, it was confirmed that the proposed method could correctly identify and detect only rockfalls in real time and identify the locations where they occurred.
Conclusion:
In this study, only rockfalls of 52 mm x 71 mm in size are detected in real time. It can enable workers to evacuate and prevent industrial accidents. In addition, by identifying the location of rockfalls, it is possible to know the danger level of the tunnel face.
