{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/113302"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/113302","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Monitoring and designing built environments with computer vision","abstract":"The digitalization of the construction industry has led to workflows of modern construction projects relying on visual data. In particular, cameras are used for monitoring progress and construction resource activities, and Building Information Modelling (BIM) models are used to digitally represent building assets and document construction progress. The vast amounts of resulting images and videos, as well as the size, intricacy and complexity of BIM models, incentivize the use of computer vision to facilitate and automate said workflows. In addition, the uniqueness of construction site imagery and BIM structure present one-of-a-kind opportunities for computer vision research. In this thesis, we firstly explore the effectiveness of using established vision methods for action recognition for temporally categorizing and segmenting construction worker and excavator activities, and introduce benchmark datasets to incentivize further research in this direction. Secondly, motivated by the need for semantic understanding of scenes for progress monitoring, we explore means of encouraging the geometric regularity we expect to see in scenes of built environments in outputs of 2D semantic segmentation methods. Finally, we address practical concerns of existing generative models for hierarchically structured 3D shapes.","abstract_html":"The digitalization of the construction industry has led to workflows of modern construction projects relying on visual data. In particular, cameras are used for monitoring progress and construction resource activities, and Building Information Modelling (BIM) models are used to digitally represent building assets and document construction progress. The vast amounts of resulting images and videos, as well as the size, intricacy and complexity of BIM models, incentivize the use of computer vision to facilitate and automate said workflows. In addition, the uniqueness of construction site imagery and BIM structure present one-of-a-kind opportunities for computer vision research. In this thesis, we firstly explore the effectiveness of using established vision methods for action recognition for temporally categorizing and segmenting construction worker and excavator activities, and introduce benchmark datasets to incentivize further research in this direction. Secondly, motivated by the need for semantic understanding of scenes for progress monitoring, we explore means of encouraging the geometric regularity we expect to see in scenes of built environments in outputs of 2D semantic segmentation methods. Finally, we address practical concerns of existing generative models for hierarchically structured 3D shapes.","abstract_has_math":false,"creators":["Roberts, Dominic"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Golparvar-Fard, Mani","Forsyth, David","Hoiem, Derek","Savarese, Silvio"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2022,"date_issued":"2022-01-12T22:55:04Z","date_published":"2022-01-12T22:55:04Z","updated_at":"2026-07-22T22:24:53Z","subjects":["Computer Vision","Construction Management","Deep Learning"],"languages":["en"],"rights":["Copyright 2021 Dominic Roberts"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/113302","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Golparvar-Fard, Mani","Forsyth, David","Hoiem, Derek","Savarese, Silvio"]},{"key":"dc:creator","label":"Author","values":["Roberts, Dominic"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2022-01-12T22:55:04Z","2024-01-12T22:56:20Z","2021-07-12","2021-08"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"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":["Computer Vision","Construction Management","Deep Learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2021 Dominic Roberts"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/113302"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The digitalization of the construction industry has led to workflows of modern construction projects relying on visual data. In particular, cameras are used for monitoring progress and construction resource activities, and Building Information Modelling (BIM) models are used to digitally represent building assets and document construction progress. The vast amounts of resulting images and videos, as well as the size, intricacy and complexity of BIM models, incentivize the use of computer vision to facilitate and automate said workflows. In addition, the uniqueness of construction site imagery and BIM structure present one-of-a-kind opportunities for computer vision research. In this thesis, we firstly explore the effectiveness of using established vision methods for action recognition for temporally categorizing and segmenting construction worker and excavator activities, and introduce benchmark datasets to incentivize further research in this direction. Secondly, motivated by the need for semantic understanding of scenes for progress monitoring, we explore means of encouraging the geometric regularity we expect to see in scenes of built environments in outputs of 2D semantic segmentation methods. Finally, we address practical concerns of existing generative models for hierarchically structured 3D shapes.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2023-08-01","The student, Dominic Roberts, accepted the attached license on 2021-07-12 at 11:23.","The student, Dominic Roberts, submitted this Dissertation for approval on 2021-07-12 at 11:33.","This Dissertation was approved for publication on 2021-07-12 at 13:53.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16864 on 2022-01-12 at 13:04:32","Made available in DSpace on 2022-01-12T22:55:04Z (GMT). No. of bitstreams: 2 ROBERTS-DISSERTATION-2021.pdf: 5627616 bytes, checksum: 7993624e9ddf2fd0766e733c9edfd205 (MD5) LICENSE.txt: 4212 bytes, checksum: cfa8d13f521e6f4f310673a83d972ae9 (MD5) Previous issue date: 2021-07-12","Embargo set by: Seth Robbins for item 121230 Lift date: 2024-01-12T22:55:09Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 121230 Lift date: 2024-01-12T22:56:20Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Monitoring and designing built environments with computer vision"]}]}],"canonical_facts":{"dc:contributor":["Golparvar-Fard, Mani","Forsyth, David","Hoiem, Derek","Savarese, Silvio"],"dc:creator":["Roberts, Dominic"],"dc:date":["2022-01-12T22:55:04Z","2024-01-12T22:56:20Z","2021-07-12","2021-08"],"dc:description":["The digitalization of the construction industry has led to workflows of modern construction projects relying on visual data. In particular, cameras are used for monitoring progress and construction resource activities, and Building Information Modelling (BIM) models are used to digitally represent building assets and document construction progress. The vast amounts of resulting images and videos, as well as the size, intricacy and complexity of BIM models, incentivize the use of computer vision to facilitate and automate said workflows. In addition, the uniqueness of construction site imagery and BIM structure present one-of-a-kind opportunities for computer vision research. In this thesis, we firstly explore the effectiveness of using established vision methods for action recognition for temporally categorizing and segmenting construction worker and excavator activities, and introduce benchmark datasets to incentivize further research in this direction. Secondly, motivated by the need for semantic understanding of scenes for progress monitoring, we explore means of encouraging the geometric regularity we expect to see in scenes of built environments in outputs of 2D semantic segmentation methods. Finally, we address practical concerns of existing generative models for hierarchically structured 3D shapes.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2023-08-01","The student, Dominic Roberts, accepted the attached license on 2021-07-12 at 11:23.","The student, Dominic Roberts, submitted this Dissertation for approval on 2021-07-12 at 11:33.","This Dissertation was approved for publication on 2021-07-12 at 13:53.","DSpace SAF Submission Ingestion Package generated from Vireo submission #16864 on 2022-01-12 at 13:04:32","Made available in DSpace on 2022-01-12T22:55:04Z (GMT). No. of bitstreams: 2 ROBERTS-DISSERTATION-2021.pdf: 5627616 bytes, checksum: 7993624e9ddf2fd0766e733c9edfd205 (MD5) LICENSE.txt: 4212 bytes, checksum: cfa8d13f521e6f4f310673a83d972ae9 (MD5) Previous issue date: 2021-07-12","Embargo set by: Seth Robbins for item 121230 Lift date: 2024-01-12T22:55:09Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 121230 Lift date: 2024-01-12T22:56:20Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/113302"],"dc:language":["en"],"dc:rights":["Copyright 2021 Dominic Roberts"],"dc:subject":["Computer Vision","Construction Management","Deep Learning"],"dc:title":["Monitoring and designing built environments with computer vision"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:53Z"}