Construction progress management and interior work analysis using kinect 3D image sensors

Kosei Ishida*

*Corresponding author for this work

Research output: Contribution to conferencePaperpeer-review

5 Citations (Scopus)

Abstract

Construction progress management and work analysis are often difficult in building interiors. In order to make progress management easier, the authors developed methods for recording the interior work environment. These methods record data using Microsoft Kinect sensors. In this paper, the authors describe methods for recording work data utilizing several Kinect sensors. The authors recorded the following types of data: 1. The work environment at the construction site 2. The shape of the building at the construction site 3. The work efficiency at the site derived from the motion capture data To record the three types of data, the authors developed a method for performing motion capture using several Kinects. In addition, a shape recognition method for identifying building materials was developed. The shape recognition method utilizes point cloud data and camera image data. The authors also studied methods for analyzing the work efficiency data on the basis of skeletal tracking information.

Original languageEnglish
Pages314-322
Number of pages9
DOIs
Publication statusPublished - 2016
Externally publishedYes
Event33rd International Symposium on Automation and Robotics in Construction, ISARC 2016 - Auburn, United States
Duration: 2016 Jul 182016 Jul 21

Other

Other33rd International Symposium on Automation and Robotics in Construction, ISARC 2016
Country/TerritoryUnited States
CityAuburn
Period16/7/1816/7/21

Keywords

  • Construction management
  • Interior work
  • Kinect
  • Point cloud
  • Skeletal tracking
  • Work efficiency

ASJC Scopus subject areas

  • Artificial Intelligence
  • Civil and Structural Engineering
  • Human-Computer Interaction
  • Geotechnical Engineering and Engineering Geology

Fingerprint

Dive into the research topics of 'Construction progress management and interior work analysis using kinect 3D image sensors'. Together they form a unique fingerprint.

Cite this