TO TOP

Phillip Schönfelder

M. Sc.
Research Assistant
Room: IC 6/71
Phone: +49 234 32 - 21573
ORC-ID: 0000-0002-8685-436X
E-Mail

Foto Phillip Schönfelder
Automatic Deep Learning-based Information Extraction from Architectural Drawings

Governmental institutions and economic players have huge archives of old building drawings at their disposal. Digitizing these paper drawings would strongly benefit the maintenance and operation of the respective buildings. However, there is no end-to-end method to automatically digitize these drawings in their entirety. Therefore, my research addresses the gaps in automatic drawing digitization. This includes extracting text information, determining the geometry of objects, and recognizing symbols in scanned drawings. Since these tasks are complex and require a profound understanding of the drawing's structure, I use deep learning based-algorithms to tackle the digitization task.

Bachelor

  • Paschkowski, Adrian (2022): Assembling a Floor Plan Dataset from Scraped Web Images Using Machine Learning
  • Kleinert, Angelo (2022): Converting Pixel-based Floor Plan Geometries to Regularized Vector Drawings
  • Rosenthal, Felix (2022): Deep Learning-based Symbol Detection on Construction Drawings Using the Single Stage Detector YOLOv5
  • Andreou, Nikos (2023): Applying the YOLOv7 Model Architecture for Text Localization on Floorplans
  • Stebel, Fynn (2023): Improving Deep Learning-based Text Detection Performance in Engineering Drawings with Synthetic Training Data
  • Boehnke, Lara (2023): Semantic Analysis of Room Information Text in Floor Plans Using Machine Learning-based Natural Language Processing
  • Gugenheimer, Marcel (2023): Converting Vector-based Floorplans to IFC Building Models
  • Höner, Laurenz (2023): Localizing Fire Safety Equipment in Escape Plans Using Keypoint RCNN
  • Liu, Shipan (2024): Conceptualization and Implementation of a Web Application Backend for Processing Technical Drawings
  • Ritz, Julia (2024): Conceptualization and Implementation of a Web Application Frontend for Processing Technical Drawings
  • Danylyshyn, Heorhii (2024): Deploying a Web-Application for Technical Drawing Processing
  • Konnerth, Patrick (2024): Conceptual design and prototyping of an application for the semantic analysis of drawing headers in analog plan documents
  • Müller, Daniel (2025): UI concepts for human-in-the-loop applications for AI-based drawing analysis

Master

  • Staka, Inri (2022): Digitization of 2D Drawings Using Artificial Intelligence
  • Brosch, Pascal (2022): Deep Learning-basierte Extraktion und Verarbeitung von Kosteninformationen aus tabellarisch-strukturierten Dokumenten
  • Hakert, Alexander (2022): Automatic Segmentation of Floor Plan Images Using Informed Machine Learning
  • Shayanfar, Kia (2022): Feasibility analysis of roll-bonded cooling plates based on machine learning
  • Kundu, Pitambar (2022): Object Recognition of Temporary Construction Items Using Synthetic Data Sets and Deep Learning
  • Bongardt, Robin (2022): Automatic Linkage of  CAD Elements with Corresponding List of Quantity Items
  • Nematkah, Ali (2023): Supervised learning-based detection of technical building equipment symbols
  • Duski, Husan (2023): Digitizing Zoning Plans with Deep Learning-based Image Processing
  • Brauksiepe, Marc (2023): Fine-grained Synthetic Data Generation for Deep Learning-based Floor Plan Analysis with Focus on Wall Layer Segmentation
  • Santehanser, Timo (2024): Automatic extraction of pipe routes and manhole details in site plans
  • Ashrafi, Ahmadreza (2024): Automatic Recognition of the Cross-Sectional Geometry of Tunnels in Drawings

Publications