Automated 2D Detection and Localization of Construction Resources in Support of Automated Performance Assessment of Construction Operations

Simple item page
dc.contributor.authorMemarzadeh, Miladen
dc.contributor.committeechairGolparvar-Fard, Manien
dc.contributor.committeememberde la Garza, Jesus M.en
dc.contributor.committeememberNiebles, Juan Carlosen
dc.contributor.committeememberMarr, Linsey C.en
dc.contributor.departmentCivil Engineeringen
dc.date.accessioned2017-04-04T19:50:14Zen
dc.date.adate2013-01-11en
dc.date.available2017-04-04T19:50:14Zen
dc.date.issued2012-12-10en
dc.date.rdate2016-10-07en
dc.date.sdate2012-12-11en
dc.description.abstractThis study presents two computer vision based algorithms for automated 2D detection of construction workers and equipment from site video streams. The state-of-the-art research proposes semi-automated detection methods for tracking of construction workers and equipment. Considering the number of active equipment and workers on jobsites and their frequency of appearance in a camera's field of view, application of semi-automated techniques can be time-consuming. To address this limitation, two new algorithms based on Histograms of Oriented Gradients and Colors (HOG+C), 1) HOG+C sliding detection window technique, and 2) HOG+C deformable part-based model are proposed and their performance are compared to the state-of-the-art algorithm in computer vision community. Furthermore, a new comprehensive benchmark dataset containing over 8,000 annotated video frames including equipment and workers from different construction projects is introduced. This dataset contains a large range of pose, scale, background, illumination, and occlusion variation. The preliminary results with average performance accuracies of 100%, 92.02%, and 89.69% for workers, excavators, and dump trucks respectively, indicate the applicability of the proposed methods for automated activity analysis of workers and equipment from single video cameras. Unlike other state-of-the-art algorithms in automated resource tracking, these methods particularly detects idle resources and does not need manual or semi-automated initialization of the resource locations in 2D video frames.en
dc.description.degreeMaster of Scienceen
dc.identifier.otheretd-12112012-103535en
dc.identifier.sourceurlhttp://scholar.lib.vt.edu/theses/available/etd-12112012-103535/en
dc.identifier.urihttp://hdl.handle.net/10919/76908en
dc.language.isoen_USen
dc.publisherVirginia Techen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectSupport Vector Machineen
dc.subjectHistogram of Oriented Gradientsen
dc.subjectDeformable Part-based Modelsen
dc.subjectHSV Colorsen
dc.subjectResource Detection and Localizationen
dc.subjectPerformance Monitoringen
dc.titleAutomated 2D Detection and Localization of Construction Resources in Support of Automated Performance Assessment of Construction Operationsen
dc.typeThesisen
dc.type.dcmitypeTexten
thesis.degree.disciplineCivil Engineeringen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.levelmastersen
thesis.degree.nameMaster of Scienceen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
etd-12112012-103535_Memarzadeh_M_T_2012.pdf
Size:
8.02 MB
Format:
Adobe Portable Document Format
Download

Collections

Masters Theses