A Bayesian Approach to Convergence Detection in Underground Excavations using LiDAR
MetadataShow full item record
This thesis deals with the subject of convergence detection in underground excavations --- typically mining operations. Traditional methods for convergence monitoring involve operose surveying procedures that produce measurements in low density along a drift. The aim of this thesis is to introduce a novel convergence monitoring solution which extracts typical convergence features from point cloud scans in a drift. These features are extracted by convergence indicators. These indicators are amalgamated using a Bayesian statistical approach to build an inference about whether or not convergence is occurring. This algorithm was tested on simulated as well as actual mining convergence drift scans.