{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/46892"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/46892","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Vision-based workface assessment using depth images for activity analysis of interior construction operations","abstract":"Workface assessment –the process of determining the overall activity rates of onsite construction workers throughout a day– typically involves manual visual observations which are time-consuming and labor-intensive. To minimize subjectivity and the time required for conducting detailed assessments, and allowing managers to spend their time on the more important task of assessing and implementing improvements, we propose a new inexpensive vision-based method using RGB-D sensors that is applicable to interior construction operations. This is particularly a challenging task as construction activities have a large range of intra-class variability including varying sequences of body posture and time-spent on each individual activity. On the other hand, the state-of-the-art skeleton extraction algorithms from RGB-D sequences are not robust enough especially when workers interact with tools or self-occlude the camera’s field-of-view. Existing vision-based methods are also rather limited as they can primarily classify “atomic” activities from RGB-D sequences involving one worker conducting a single activity. To address these limitations, our proposed original method involves three main components: 1) an algorithm for detecting, tracking, and extracting body skeleton features from depth images; 2) A discriminative bag-of-poses activity classifier trained using multiple Support Vector Machines for classifying single visual activities from a given body skeleton sequence; and 3) a Hidden Markov model with a Kernel Density Estimation function to represent emission probabilities in form of a statistical distribution of single activity classifiers. For training and testing purposes, we also introduce a new dataset of eleven RGB-D sequences for interior drywall construction operations involving three actual construction workers conducting eight different activities in various interior locations. Our experimental results with an average accuracy of 76% on the testing dataset show the promise of vision-based methods using RGB-D sequences for facilitating the activity analysis workface assessment.","abstract_html":"Workface assessment –the process of determining the overall activity rates of onsite construction workers throughout a day– typically involves manual visual observations which are time-consuming and labor-intensive. To minimize subjectivity and the time required for conducting detailed assessments, and allowing managers to spend their time on the more important task of assessing and implementing improvements, we propose a new inexpensive vision-based method using RGB-D sensors that is applicable to interior construction operations. This is particularly a challenging task as construction activities have a large range of intra-class variability including varying sequences of body posture and time-spent on each individual activity. On the other hand, the state-of-the-art skeleton extraction algorithms from RGB-D sequences are not robust enough especially when workers interact with tools or self-occlude the camera’s field-of-view. Existing vision-based methods are also rather limited as they can primarily classify “atomic” activities from RGB-D sequences involving one worker conducting a single activity. To address these limitations, our proposed original method involves three main components: 1) an algorithm for detecting, tracking, and extracting body skeleton features from depth images; 2) A discriminative bag-of-poses activity classifier trained using multiple Support Vector Machines for classifying single visual activities from a given body skeleton sequence; and 3) a Hidden Markov model with a Kernel Density Estimation function to represent emission probabilities in form of a statistical distribution of single activity classifiers. For training and testing purposes, we also introduce a new dataset of eleven RGB-D sequences for interior drywall construction operations involving three actual construction workers conducting eight different activities in various interior locations. Our experimental results with an average accuracy of 76% on the testing dataset show the promise of vision-based methods using RGB-D sequences for facilitating the activity analysis workface assessment.","abstract_has_math":false,"creators":["Khosrowpour, Ardalan"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Civil Engineering","degree_department":null,"school":null,"contributors":["Golparvar-Fard, Mani"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2014,"date_issued":"2014-01-16T18:25:29Z","date_published":"2014-01-16T18:25:29Z","updated_at":"2026-07-22T22:25:38Z","subjects":["Activity Analysis","Workface Assessment","RGB-D (RedGreenBlue-Depth) cameras","Hidden Markov ModelActivity analysis","Hidden Markov Model"],"languages":["en"],"rights":["Copyright © 2013 Ardalan Khosrowpour"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/46892","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Golparvar-Fard, Mani"]},{"key":"dc:creator","label":"Author","values":["Khosrowpour, Ardalan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2014-01-16T18:25:29Z","2016-01-16T11:01:53Z","2013-12"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Civil Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Activity Analysis","Workface Assessment","RGB-D (RedGreenBlue-Depth) cameras","Hidden Markov ModelActivity analysis","Hidden Markov Model"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright © 2013 Ardalan Khosrowpour"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/46892"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Workface assessment –the process of determining the overall activity rates of onsite construction workers throughout a day– typically involves manual visual observations which are time-consuming and labor-intensive. To minimize subjectivity and the time required for conducting detailed assessments, and allowing managers to spend their time on the more important task of assessing and implementing improvements, we propose a new inexpensive vision-based method using RGB-D sensors that is applicable to interior construction operations. This is particularly a challenging task as construction activities have a large range of intra-class variability including varying sequences of body posture and time-spent on each individual activity. On the other hand, the state-of-the-art skeleton extraction algorithms from RGB-D sequences are not robust enough especially when workers interact with tools or self-occlude the camera’s field-of-view. Existing vision-based methods are also rather limited as they can primarily classify “atomic” activities from RGB-D sequences involving one worker conducting a single activity. To address these limitations, our proposed original method involves three main components: 1) an algorithm for detecting, tracking, and extracting body skeleton features from depth images; 2) A discriminative bag-of-poses activity classifier trained using multiple Support Vector Machines for classifying single visual activities from a given body skeleton sequence; and 3) a Hidden Markov model with a Kernel Density Estimation function to represent emission probabilities in form of a statistical distribution of single activity classifiers. For training and testing purposes, we also introduce a new dataset of eleven RGB-D sequences for interior drywall construction operations involving three actual construction workers conducting eight different activities in various interior locations. Our experimental results with an average accuracy of 76% on the testing dataset show the promise of vision-based methods using RGB-D sequences for facilitating the activity analysis workface assessment.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2013-12-12T19:39:08Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 3 Khosrowpour_Ardalan.pdf: 1734451 bytes, checksum: 4ac6df276cc7f4a8750c35c1a508bba1 (MD5) Khosrowpour_Ardalan.docx: 11320392 bytes, checksum: 7f5d424d608c67b277bafac84c9c9c39 (MD5) Khosrowpour_Ardalan.pdf: 1740594 bytes, checksum: 1cffda78fee2c0f12e1c79f05b3ece0c (MD5)","Made available in DSpace on 2014-01-16T18:25:29Z (GMT). No. of bitstreams: 4 Ardalan_Khosrowpour.pdf: 1725370 bytes, checksum: ad236d0b24bd8c2a3255de49c5b12740 (MD5) Khosrowpour_Ardalan.docx: 11320783 bytes, checksum: c352e7859b4f55c48a18cf01f2cad13d (MD5) 1_Khosrowpour_Ardalan.docx: 11320392 bytes, checksum: 7f5d424d608c67b277bafac84c9c9c39 (MD5) license.txt: 4069 bytes, checksum: 9886df77281d564570b1585b432b21f4 (MD5)","Restriction data tranferred 2014-07-01T11:36:44-05:00 Original Data Group with Access Administrator Release Date: 2016-01-16 12:27:27 UTC Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Item marked as restricted to the 'Administrator' Group (id=1) by Seth Robbins (robbins.sd@gmail.com) on 2014-01-16T18:27:31Z Item is restricted until 2016-01-16T18:27:27Z","Limited Restriction Lifted for Item 46911 on 2016-01-16T11:01:53Z."]},{"key":"dc:title","label":"Title","values":["Vision-based workface assessment using depth images for activity analysis of interior construction operations"]}]}],"canonical_facts":{"dc:contributor":["Golparvar-Fard, Mani"],"dc:creator":["Khosrowpour, Ardalan"],"dc:date":["2014-01-16T18:25:29Z","2016-01-16T11:01:53Z","2013-12"],"dc:description":["Workface assessment –the process of determining the overall activity rates of onsite construction workers throughout a day– typically involves manual visual observations which are time-consuming and labor-intensive. To minimize subjectivity and the time required for conducting detailed assessments, and allowing managers to spend their time on the more important task of assessing and implementing improvements, we propose a new inexpensive vision-based method using RGB-D sensors that is applicable to interior construction operations. This is particularly a challenging task as construction activities have a large range of intra-class variability including varying sequences of body posture and time-spent on each individual activity. On the other hand, the state-of-the-art skeleton extraction algorithms from RGB-D sequences are not robust enough especially when workers interact with tools or self-occlude the camera’s field-of-view. Existing vision-based methods are also rather limited as they can primarily classify “atomic” activities from RGB-D sequences involving one worker conducting a single activity. To address these limitations, our proposed original method involves three main components: 1) an algorithm for detecting, tracking, and extracting body skeleton features from depth images; 2) A discriminative bag-of-poses activity classifier trained using multiple Support Vector Machines for classifying single visual activities from a given body skeleton sequence; and 3) a Hidden Markov model with a Kernel Density Estimation function to represent emission probabilities in form of a statistical distribution of single activity classifiers. For training and testing purposes, we also introduce a new dataset of eleven RGB-D sequences for interior drywall construction operations involving three actual construction workers conducting eight different activities in various interior locations. Our experimental results with an average accuracy of 76% on the testing dataset show the promise of vision-based methods using RGB-D sequences for facilitating the activity analysis workface assessment.","Item withdrawn by Mark Zulauf (zulauf@illinois.edu) on 2013-12-12T19:39:08Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 3 Khosrowpour_Ardalan.pdf: 1734451 bytes, checksum: 4ac6df276cc7f4a8750c35c1a508bba1 (MD5) Khosrowpour_Ardalan.docx: 11320392 bytes, checksum: 7f5d424d608c67b277bafac84c9c9c39 (MD5) Khosrowpour_Ardalan.pdf: 1740594 bytes, checksum: 1cffda78fee2c0f12e1c79f05b3ece0c (MD5)","Made available in DSpace on 2014-01-16T18:25:29Z (GMT). No. of bitstreams: 4 Ardalan_Khosrowpour.pdf: 1725370 bytes, checksum: ad236d0b24bd8c2a3255de49c5b12740 (MD5) Khosrowpour_Ardalan.docx: 11320783 bytes, checksum: c352e7859b4f55c48a18cf01f2cad13d (MD5) 1_Khosrowpour_Ardalan.docx: 11320392 bytes, checksum: 7f5d424d608c67b277bafac84c9c9c39 (MD5) license.txt: 4069 bytes, checksum: 9886df77281d564570b1585b432b21f4 (MD5)","Restriction data tranferred 2014-07-01T11:36:44-05:00 Original Data Group with Access Administrator Release Date: 2016-01-16 12:27:27 UTC Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Item marked as restricted to the 'Administrator' Group (id=1) by Seth Robbins (robbins.sd@gmail.com) on 2014-01-16T18:27:31Z Item is restricted until 2016-01-16T18:27:27Z","Limited Restriction Lifted for Item 46911 on 2016-01-16T11:01:53Z."],"dc:identifier":["http://hdl.handle.net/2142/46892"],"dc:language":["en"],"dc:rights":["Copyright © 2013 Ardalan Khosrowpour"],"dc:subject":["Activity Analysis","Workface Assessment","RGB-D (RedGreenBlue-Depth) cameras","Hidden Markov ModelActivity analysis","Hidden Markov Model"],"dc:title":["Vision-based workface assessment using depth images for activity analysis of interior construction operations"],"dc:type":["text"],"thesis:degree_discipline":["Civil Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:25:38Z"}