Many legacy buildings lack Building Information Models (BIMs), even though they have detailed engineering drawings that contain essential mechanical, electrical, plumbing (MEP) components and structural components. Converting these drawings into BIM models remains a largely manual process, which is time-consuming, difficult to scale, and costly. This thesis presents a computer vision–based pipeline designed to automate two fundamental steps necessary for downstream BIM reconstruction from engineering drawings: legend extraction and engineering drawing preprocessing and noise removal. The legend extraction module combines histogram segmentation with Paddle OCR, enabling accurate extraction across heterogeneous MEP legend images. The engineering drawing preprocessing and noise removal module removes background structural components and employs a multi-stage approach for detecting and removing annotation arrows along with annotations, which commonly obscure MEP components. A sequence of morphological filtering and geometric analysis enables robust annotation arrows detection and removal, producing cleaner drawings for future analysis. Experimental results on engineering drawings of multiple real-world construction projects show strong legend segmentation accuracy, reliable annotation arrows detection, and consistent preprocessing performance across diverse engineering drawing layouts. The proposed pipeline establishes essential preprocessing and extraction capabilities that significantly reduce manual effort and provide a foundation for developing automated BIM models.
","abstract_html":"<p>Many legacy buildings lack Building Information Models (BIMs), even though they have detailed engineering drawings that contain essential mechanical, electrical, plumbing (MEP) components and structural components. Converting these drawings into BIM models remains a largely manual process, which is time-consuming, difficult to scale, and costly. This thesis presents a computer vision–based pipeline designed to automate two fundamental steps necessary for downstream BIM reconstruction from engineering drawings: legend extraction and engineering drawing preprocessing and noise removal. The legend extraction module combines histogram segmentation with Paddle OCR, enabling accurate extraction across heterogeneous MEP legend images. The engineering drawing preprocessing and noise removal module removes background structural components and employs a multi-stage approach for detecting and removing annotation arrows along with annotations, which commonly obscure MEP components. A sequence of morphological filtering and geometric analysis enables robust annotation arrows detection and removal, producing cleaner drawings for future analysis. Experimental results on engineering drawings of multiple real-world construction projects show strong legend segmentation accuracy, reliable annotation arrows detection, and consistent preprocessing performance across diverse engineering drawing layouts. The proposed pipeline establishes essential preprocessing and extraction capabilities that significantly reduce manual effort and provide a foundation for developing automated BIM models.</p>","abstract_has_math":false,"creators":["Chen, Suyang"],"institution":null,"degree_name":"Master of Science (M.S.)","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Jin Chen","Zhigang Zhu"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-01-01T08:00:00Z","date_published":"2025-01-01T08:00:00Z","updated_at":"2026-07-24T01:58:07Z","subjects":["BIM Reconstruction","Engineering Drawing","Image Processing","Computer Vision.","Computer Sciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://academicworks.cuny.edu/cc_etds_theses/1240","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Jin Chen","Zhigang Zhu"]},{"key":"dc:creator","label":"Author","values":["Chen, Suyang"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2027-12-24T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (M.S.)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["BIM Reconstruction","Engineering Drawing","Image Processing","Computer Vision.","Computer Sciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://academicworks.cuny.edu/cc_etds_theses/1240"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Many legacy buildings lack Building Information Models (BIMs), even though they have detailed engineering drawings that contain essential mechanical, electrical, plumbing (MEP) components and structural components. Converting these drawings into BIM models remains a largely manual process, which is time-consuming, difficult to scale, and costly. This thesis presents a computer vision–based pipeline designed to automate two fundamental steps necessary for downstream BIM reconstruction from engineering drawings: legend extraction and engineering drawing preprocessing and noise removal. The legend extraction module combines histogram segmentation with Paddle OCR, enabling accurate extraction across heterogeneous MEP legend images. The engineering drawing preprocessing and noise removal module removes background structural components and employs a multi-stage approach for detecting and removing annotation arrows along with annotations, which commonly obscure MEP components. A sequence of morphological filtering and geometric analysis enables robust annotation arrows detection and removal, producing cleaner drawings for future analysis. Experimental results on engineering drawings of multiple real-world construction projects show strong legend segmentation accuracy, reliable annotation arrows detection, and consistent preprocessing performance across diverse engineering drawing layouts. The proposed pipeline establishes essential preprocessing and extraction capabilities that significantly reduce manual effort and provide a foundation for developing automated BIM models.
"]},{"key":"dc:title","label":"Title","values":["Engineering Drawing Segmentation and Understanding For Building Construction Digital Twins"]}]}],"canonical_facts":{"dc:contributor":["Jin Chen","Zhigang Zhu"],"dc:creator":["Chen, Suyang"],"dc:date.available":["2027-12-24T08:00:00Z"],"dc:description.abstract":["Many legacy buildings lack Building Information Models (BIMs), even though they have detailed engineering drawings that contain essential mechanical, electrical, plumbing (MEP) components and structural components. Converting these drawings into BIM models remains a largely manual process, which is time-consuming, difficult to scale, and costly. This thesis presents a computer vision–based pipeline designed to automate two fundamental steps necessary for downstream BIM reconstruction from engineering drawings: legend extraction and engineering drawing preprocessing and noise removal. The legend extraction module combines histogram segmentation with Paddle OCR, enabling accurate extraction across heterogeneous MEP legend images. The engineering drawing preprocessing and noise removal module removes background structural components and employs a multi-stage approach for detecting and removing annotation arrows along with annotations, which commonly obscure MEP components. A sequence of morphological filtering and geometric analysis enables robust annotation arrows detection and removal, producing cleaner drawings for future analysis. Experimental results on engineering drawings of multiple real-world construction projects show strong legend segmentation accuracy, reliable annotation arrows detection, and consistent preprocessing performance across diverse engineering drawing layouts. The proposed pipeline establishes essential preprocessing and extraction capabilities that significantly reduce manual effort and provide a foundation for developing automated BIM models.
"],"dc:identifier":["https://academicworks.cuny.edu/cc_etds_theses/1240"],"dc:subject":["BIM Reconstruction","Engineering Drawing","Image Processing","Computer Vision.","Computer Sciences"],"dc:title":["Engineering Drawing Segmentation and Understanding For Building Construction Digital Twins"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (M.S.)"]},"updated_at":"2026-07-24T01:58:07Z"}