Show simple item record

contributor authorMarianna Kopsida
contributor authorIoannis Brilakis
date accessioned2022-01-30T19:25:06Z
date available2022-01-30T19:25:06Z
date issued2020
identifier other%28ASCE%29CP.1943-5487.0000896.pdf
identifier urihttp://yetl.yabesh.ir/yetl1/handle/yetl/4265264
description abstractOn-site construction inspection for progress monitoring is important because accurate and timely assessment of progress allows managers to make adjustments to minimize time and cost overrun when deviations from the schedule occur. However, current practice still remains manual, time consuming, and labor intensive, which usually requires exhaustive manual data extraction from drawings and other databases. Inspection of the interior environment can be even more challenging due to the complexity and interconnectivity of tasks. Systems based on mobile devices could potentially enhance the inspection process and reduce the required time by allowing the inspector to acquire progress data by simply walking around the site. This paper presents an automated method that allows a real-time comparison between the registered as-built and as-planned data while the inspector navigates inside a building under construction to perform inspection wearing a Microsoft HoloLens device. The proposed method automatically detects if volumetric objects such as beams, columns, walls, and so on exist in reality according to plan. Different parameters of the method were tested, and 95.2% accuracy, 96.5% precision, and 97.3% recall was achieved by using the optimum set of parameters.
publisherASCE
titleReal-Time Volume-to-Plane Comparison for Mixed Reality–Based Progress Monitoring
typeJournal Paper
journal volume34
journal issue4
journal titleJournal of Computing in Civil Engineering
identifier doi10.1061/(ASCE)CP.1943-5487.0000896
page04020016
treeJournal of Computing in Civil Engineering:;2020:;Volume ( 034 ):;issue: 004
contenttypeFulltext


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record