{"id":{"repo_id":"rowan","oai_identifier":"oai:rdw.rowan.edu:etd-4576"},"canonical_url":"https://search.ndltd.org/etd/rowan/oai:rdw.rowan.edu:etd-4576","repository":{"repo_id":"rowan","name":"Rowan University","base_url":"https://rdw.rowan.edu/do/oai/"},"display":{"title":"AUTOMATED CLASSIFICATION, MEASUREMENT, AND SEMANTIC SEGMENTATION OF OPEN-WEB JOISTS FROM POINT CLOUD DATA","abstract":"This thesis presents a BIM-oriented methodology for the automated classification, measurement, and segmentation of structural trusses from point cloud data. A real truss point cloud and a complementary synthetic dataset derived from CADBIM Revit families were used to develop and evaluate the workflow. Classification was performed using a rule-based Python algorithm based on principal component analysis, side-view feature extraction, and family-specific geometric decision logic, while a separate family-aware script was used to extract key truss dimensions. Semantic segmentation was evaluated using a PointTransformerV3 model to separate truss and non-truss points in mixed point cloud scenes. The results demonstrated strong performance across all major tasks, indicating that structural trusses can be effectively identified, measured, and segmented from point cloud data. Overall, the study provides a strong foundation for future BIM- oriented automation workflows involving structural point cloud analysis.","abstract_html":"This thesis presents a BIM-oriented methodology for the automated classification, measurement, and segmentation of structural trusses from point cloud data. A real truss point cloud and a complementary synthetic dataset derived from CADBIM Revit families were used to develop and evaluate the workflow. Classification was performed using a rule-based Python algorithm based on principal component analysis, side-view feature extraction, and family-specific geometric decision logic, while a separate family-aware script was used to extract key truss dimensions. Semantic segmentation was evaluated using a PointTransformerV3 model to separate truss and non-truss points in mixed point cloud scenes. The results demonstrated strong performance across all major tasks, indicating that structural trusses can be effectively identified, measured, and segmented from point cloud data. Overall, the study provides a strong foundation for future BIM- oriented automation workflows involving structural point cloud analysis.","abstract_has_math":false,"creators":["Dworacek, Justin Raymond"],"institution":null,"degree_name":"M.S. Civil Engineering","degree_level":"Thesis","degree_discipline":"Civil and Environmental Engineering","degree_department":null,"school":null,"contributors":["Adriana Trias Blanco, Ph.D.","William T. Riddell, Ph.D.","Huaxia Wang, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T09:00:08Z","subjects":["Building Information Modeling;Computer Vision;LiDAR;Machine Learning;Remote Sensing;Semantic Segmentation","Geography","Remote Sensing","Social and Behavioral Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://rdw.rowan.edu/etd/3570","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://rdw.rowan.edu/etd/3570","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://rdw.rowan.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Ardw.rowan.edu%3Aetd-4576","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Adriana Trias Blanco, Ph.D.","William T. Riddell, Ph.D.","Huaxia Wang, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Dworacek, Justin Raymond"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2026-08-10T07:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2026-08-10T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Civil and Environmental Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S. Civil Engineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Building Information Modeling;Computer Vision;LiDAR;Machine Learning;Remote Sensing;Semantic Segmentation","Geography","Remote Sensing","Social and Behavioral Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://rdw.rowan.edu/etd/3570"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This thesis presents a BIM-oriented methodology for the automated classification, measurement, and segmentation of structural trusses from point cloud data. A real truss point cloud and a complementary synthetic dataset derived from CADBIM Revit families were used to develop and evaluate the workflow. Classification was performed using a rule-based Python algorithm based on principal component analysis, side-view feature extraction, and family-specific geometric decision logic, while a separate family-aware script was used to extract key truss dimensions. Semantic segmentation was evaluated using a PointTransformerV3 model to separate truss and non-truss points in mixed point cloud scenes. The results demonstrated strong performance across all major tasks, indicating that structural trusses can be effectively identified, measured, and segmented from point cloud data. Overall, the study provides a strong foundation for future BIM- oriented automation workflows involving structural point cloud analysis."]},{"key":"dc:title","label":"Title","values":["AUTOMATED CLASSIFICATION, MEASUREMENT, AND SEMANTIC SEGMENTATION OF OPEN-WEB JOISTS FROM POINT CLOUD DATA"]}]}],"canonical_facts":{"dc:contributor":["Adriana Trias Blanco, Ph.D.","William T. Riddell, Ph.D.","Huaxia Wang, Ph.D."],"dc:creator":["Dworacek, Justin Raymond"],"dc:date.available":["2026-08-10T07:00:00Z"],"dc:date.created":["2026-08-10T07:00:00Z"],"dc:description.abstract":["This thesis presents a BIM-oriented methodology for the automated classification, measurement, and segmentation of structural trusses from point cloud data. A real truss point cloud and a complementary synthetic dataset derived from CADBIM Revit families were used to develop and evaluate the workflow. Classification was performed using a rule-based Python algorithm based on principal component analysis, side-view feature extraction, and family-specific geometric decision logic, while a separate family-aware script was used to extract key truss dimensions. Semantic segmentation was evaluated using a PointTransformerV3 model to separate truss and non-truss points in mixed point cloud scenes. The results demonstrated strong performance across all major tasks, indicating that structural trusses can be effectively identified, measured, and segmented from point cloud data. Overall, the study provides a strong foundation for future BIM- oriented automation workflows involving structural point cloud analysis."],"dc:identifier":["https://rdw.rowan.edu/etd/3570"],"dc:subject":["Building Information Modeling;Computer Vision;LiDAR;Machine Learning;Remote Sensing;Semantic Segmentation","Geography","Remote Sensing","Social and Behavioral Sciences"],"dc:title":["AUTOMATED CLASSIFICATION, MEASUREMENT, AND SEMANTIC SEGMENTATION OF OPEN-WEB JOISTS FROM POINT CLOUD DATA"],"thesis:degree_discipline":["Civil and Environmental Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S. Civil Engineering"]},"updated_at":"2026-11-19T09:00:08Z"}