Skip to main content
UCL Logo Navigate back to homepage

Main navigation

  • Home
  • Study

    Study

    • Study at UCL
    • Prospective students
    • Current students
    • Accommodation
    • Careers
    • Doctoral School
    • Immigration and visas
    • Student finances
    • Support and wellbeing
  • Research

    Research

    • Research at UCL
    • Engage with us
    • Explore our Research
    • Initiatives and networks
    • Research news
  • Engage

    Engage

    • Engage with UCL
    • Alumni
    • Business partnerships and collaboration
    • Global engagement
    • News and Media relations
    • Public Policy
    • Schools and priority groups
    • Give to UCL
  • About

    About

    • About UCL
    • Who we are
    • Faculties
    • Governance
    • President and Provost
    • Strategy
    • UCL's Bicentenary
  • UCL Logo Active parent page: UCL Engineering
    • Study
    • Active parent page: Research
    • Collaborate
    • Departments
    • News and Events
    • People
    • About

Building segmentation using Convolutional Neural Networks for fused airborne lidar and image data

We develop a novel pipeline which uses Active Contour models and fused image-lidar data to achieve state-of-the-art accuracy in aerial building segmentation using CNNs.

Colourized and rasterized airborne LIDAR scene

Breadcrumb trail

  • Faculty of Engineering

Faculty menu

  • Case studies
  • Centres, Institutes and Labs
  • Disruptive Thinkers: Video Series
  • Intelligent Mobility @UCL: The Podcast
  • Current page: Research projects
  • Research strategy

Breadcrumb trail

  • Faculty of Engineering
  • Research
  • Building segmentation using Convolutional Neural Networks for fused airborne lidar and image data

Manually labelling buildings for segmentation is a time-consuming task. We show that readily available GIS mapping data such as that from the Ordnance Survey (UK) can be used as training data. Further, we develop a novel pipeline which uses Active Contour models and fused image-lidar data to achieve state-of-the-art accuracy in aerial building segmentation.

People

  • David Griffiths
  • Prof. Jan Boehm

Publication

Publisher link 

More from UCL Engineering...

Engineering Foundation Year
UCL East Marshgate building at dusk

Programme Spotlight

Engineering Foundation Year

We'll help you to gain new knowledge, learn academic and study skills, and develop your confidence levels so you'll have what it takes to transform your life.

Inaugural Lectures
Farhaneen Mazlan delivering a talk at UCL

Event series

Inaugural Lectures

An opportunity to explore ground-breaking research that is shaping the future and transforming the world.

Disruptive Thinkers Video Series
Dr Claire Walsh looking at a human organ in an imaging facility

Watch Now

Disruptive Thinkers Video Series

From making cities more inclusive to using fibre optics in innovative medical procedures, explore the disruptive thinking taking place across UCL Engineering.

UCL footer

Visit

  • Bloomsbury Theatre and Studio
  • Library, Museums and Collections
  • UCL Maps
  • UCL Shop
  • Contact UCL

Students

  • Accommodation
  • Current Students
  • Moodle
  • Students' Union

Staff

  • Inside UCL
  • Staff Intranet
  • Work at UCL
  • Human Resources
UCL Logo

University College London, Gower Street, London, WC1E 6BT

Tel: +44 (0) 20 7679 2000

UCL social media menu

  • Link to Instagram
  • Link to LinkedIn
  • Link to Youtube
  • Link to TikTok
  • Link to Facebook
  • Link to Bluesky
  • Link to Threads
  • Link to Soundcloud
Here, it can happen.
Back to top

Essential

  • Disclaimer
  • Freedom of Information
  • Accessibility
  • Cookies
  • Privacy
  • Slavery statement
  • Log in

© 2026 UCL