Model-based detection of progress using D4AR models generated by daily site photologs and building information models

M. Golparvar-Fard, F. Peña-Mora, S. Savarese

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper a new approach that automatically recognizes progress from daily construction photologs and Building Information Models (BIMs) is presented. Currently daily site photologs are being collected at almost no cost on all construction sites; meanwhile BIM models are increasingly turning into binding components of AEC contracts. Using these emerging sources of information, we present a 4 Dimensional Augmented Reality - D4AR - modeling approach for integrated visualization of as-built and as-planned models as well as a novel framework for automated recognition of progress. Our approach is based on structure-from-motion, multi-view stereo plus voxel coloring and labeling algorithms to calibrate cameras, reconstruct the building scene, traverse and label the integrated as-built and as-planned scene for occupancy and visibility. Next, a machine learning scheme built upon a Bayesian model is proposed that automatically detects physical components in presence of occlusions and demonstrates that component-based tracking could be fully automated. Finally, the system enables the as-planned and as-built models to be jointly explored with an interactive, image-based 3D viewer where deviations are automatically color-coded over the BIM model. To that extent, we present our underlying hypotheses and algorithms for generation of integrated as-built and as-planned models plus automated progress monitoring which is the first of its kind that takes advantage of unordered daily site photologs. Experimental results are presented for challenging datasets collected under different lighting conditions and sever occlusions from two ongoing construction projects.

Original languageEnglish (US)
Title of host publicationEG-ICE 2010 - 17th International Workshop on Intelligent Computing in Engineering
EditorsWalid Tizani
PublisherNottingham
ISBN (Electronic)9781907284601
StatePublished - 2019
Event17th International Workshop on Intelligent Computing in Engineering, EG-ICE 2010 - Nottingham, United Kingdom
Duration: Jun 30 2010Jul 2 2010

Publication series

NameEG-ICE 2010 - 17th International Workshop on Intelligent Computing in Engineering

Conference

Conference17th International Workshop on Intelligent Computing in Engineering, EG-ICE 2010
Country/TerritoryUnited Kingdom
CityNottingham
Period6/30/107/2/10

Keywords

  • 4D
  • Augmented reality
  • BIM
  • IFC
  • Image processing
  • Product modelling
  • Virtual reality

ASJC Scopus subject areas

  • Computer Science Applications
  • General Engineering

Fingerprint

Dive into the research topics of 'Model-based detection of progress using D4AR models generated by daily site photologs and building information models'. Together they form a unique fingerprint.

Cite this