[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-663521-105":59,"doc-detail-663521-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","computer-vision-approaches-for-extracting-fire-safety-information-from-service-drawings","Computer Vision Approaches for Extracting Fire-Safety Information from Service Drawings","","Fire-safety documentation supports routine building inspections during operations and maintenance, but keeping it current across many technical drawings is time-consuming and error-prone. This thesis proposes an end-to-end computer-vision pipeline for service drawings by combining a Keypoint R-CNN for fire-device symbol detection with OCR-based address parsing and region-merging segmentation for fire zones. Symbols are linked to addresses using the Hungarian algorithm with Euclidean distance, achieving high accuracy overall while revealing limitations in detecting true installation positions and producing oversegmentation-driven false positives.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/computer-vision-approaches-for-extracting-fire-safety-information-from-service-drawings/663521/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/computer-vision-approaches-for-extracting-fire-safety-information-from-service-drawings/663521.png","ImageObject",300,407,{"name":92,"@type":93},"Jordan Avery","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-10-28",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What information is extracted from service drawings in this thesis?","Question",{"text":112,"@type":113},"The pipeline extracts fire-device symbols with installation positions, parses addresses via OCR, and segments fire zones using a region-merging procedure.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How are detected symbols matched to their corresponding addresses?",{"text":117,"@type":113},"Symbol-to-address pairing is performed with the Hungarian algorithm, using Euclidean distance as the base cost.",{"name":119,"@type":110,"acceptedAnswer":120},"What are the main performance limitations reported?",{"text":121,"@type":113},"The Keypoint R-CNN can detect symbols accurately despite class imbalance, but it fails to recover true installation positions when those are indicated by auxiliary lines; fire-zone segmentation achieves high recall with low precision due to oversegmentation and false positives.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},663521,1793228915,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":24,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144},1099523882367,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","Computer Vision Approaches for Extracting Fire-Safety Information from Service Drawings  \nJulius Ekstrand  \n...  \nVictor Truong [vi2840tr-s@student. lu. se](vi2840tr-s@student. lu. se)  \nDepartment of Electrical and Information Technology Lund University  \nSupervisor: Kaan Bür  \nExaminer: Christian Nyberg  \nMarch 3, 2026  \n© 2026  \nPrinted in Sweden  \nTryckeriet i E-huset, Lund  \nAbstract  \nFire-safety documentation is an essential part of regular inspections during the building operations and maintenance phase. As help, service drawings exist to detail the positions of various fire-safety devices and their addresses, as well as fire zone coverage throughout the floors and sectors of a building. Automatically extracting this information would be immensely helpful towards, for example, maintaining up-to-date documentation or integration onto digital systems. To that end, this thesis adapts multiple computer vision techniques in order to extract pertinent information: (1) a Keypoint R-CNN model is trained on a custom dataset to detect the symbols of fire devices along with their installation positions,(2) OCR is used to parse addresses and (3) a region merging procedure is implemented to segment fire zones. Additionally, symbols are also assigned to their addresses using the Hungarian algorithm, with Euclidean distance as base cost.  \nFor the symbol detection, we find that crucial model settings had to be changed in order to tailor the model for the domain and achieve satisfactory performance. High accuracy is achieved despite major class-imbalances in the dataset, but the model fails in all cases to detect the true installation positions of devices, whenever these are indicated by an auxiliary line. Assigning symbols and addresses to eachother based on distance works well in most cases, while having a few edge cases that are impossible to amend with our method alone, due to inherent quirks in the service drawings. Using region merging for the fire zone segmentation gives us high recall, but low precision. The low precision is mainly due to the oversegmentation step of region merging, and partly due to the existence of hard-to-ignore false positives in most service drawings. Overall, the results across all tasks are promising while still leaving plenty of room for improvement, or alternative approaches, in further work.  \nii  \nPopular Science Summary  \nFire-safety is a critical aspect of buildings where, in extreme cases, human lives are at stake. As required by law, documentation exists to record the locations of various fire-safety devices (e.g. smoke detectors) in order to support proper maintenance and regulatory compliance. This thesis mainly explores, to great success, the use of artificial intelligence to automatically extracting information from such documents.  \nAutomating this process could reduce time-consuming documentation work and make it easier to keep fire-safety systems up to date—especially for larger facilities such as hospitals, universities, or industrial sites where hundreds of documents may need to be maintained and regularly revised. Although these documents are often easy for humans to interpret at a glance, handling them at a large scale can require extensive manual effort. This would also provide great value for digital platforms seeking to simplify the management of a building’s fire-safety system. Our work therefore seek to bridge the gap between traditional documentation and modern digital systems by extracting structured information from complex technical drawings.  \nWe extract this information through a combination of machine learning and algorithmic methods. One important type of document is the so-called service drawing, which resembles a floor plan marked with devices and fire zones. We train a model to detect different kinds of fire-safety devices and use an algorithmic approach for extracting fire zones. Before training the model, we first had to gather and create our own dataset of service d","cbCaijIEWO2FX0wp","https://ap.wps.com/l/cbCaijIEWO2FX0wp","pdf",6072642,89,"English","# Introduction\n## Motivation\n## Objectives\n## Thesis Outline\n# Background & Related Work\n## Document Image Analysis\n## Deep Learning\n## A Primer on Computer Vision\n## Convolutional Neural Networks\n## Region-based Convolutional Neural Networks\n## Feature Pyramid Network\n## Optical Character Recognition\n## Related Work\n# Methodology\n## Problem decomposition and pipeline\n## Dataset Creation and Analysis\n## Symbol Detection\n## Address Extraction\n## Symbol-to-Address Pairing\n## Fire Zone Segmentation\n# Dataset Analysis\n## Service Drawings\n## Dataset Annotation\n## Dataset Characteristics\n## Potential Difficulties\n# Implementation\n## Symbol Detection\n## Address Extraction\n## Symbol-to-Address Pairing\n## Fire Zone Segmentation","[{\"question\":\"What information is extracted from service drawings in this thesis?\",\"answer\":\"The pipeline extracts fire-device symbols with installation positions, parses addresses via OCR, and segments fire zones using a region-merging procedure.\"},{\"question\":\"How are detected symbols matched to their corresponding addresses?\",\"answer\":\"Symbol-to-address pairing is performed with the Hungarian algorithm, using Euclidean distance as the base cost.\"},{\"question\":\"What are the main performance limitations reported?\",\"answer\":\"The Keypoint R-CNN can detect symbols accurately despite class imbalance, but it fails to recover true installation positions when those are indicated by auxiliary lines; fire-zone segmentation achieves high recall with low precision due to oversegmentation and false positives.\"}]","Computer Vision Approaches for Extracting Fire-Safety Information from Service Drawings | PDF",224]