Construction Information Technology Laboratory

Test image

Welcome to the Construction Information Technology (CIT) Laboratory at the University of Cambridge. The laboratory is a state-of-the-art facility that is set up for sensing, information retrieval, and knowledge discovery from infrastructure data. The research projects at the laboratory focus on the extraction and analysis of unstructured and semi-structured data, such as images, video, and the geometry of construction projects. The laboratory also engages in education, outreach and engagement activities that relate to its mission. This includes demonstrations for graduate and undergraduate students, hands-on activities for secondary education, student experiments for class projects, and others.

Experiments performed at the laboratory commonly involve the real-time collection of data using intensity, infrared, and positioning sensors placed on the CIT lab's testbeds and the subsequent pre-processing and analysis needed to extract information using pattern recognition tools for object detection, segmentation, abnormal pattern extraction and other purposes that serve the objectives of each research project.


CIT News & Spotlights


  • 1
  • 2
  • 3
  • 4
  • Current Research    
  • Sponsored by the National Science Foundation, CEE researchers are using machine vision techniques to automate the procedures of evaluating post-earthquake building safety. Learn more


    1
  • Sponsored by the National Science Foundation, CITL researchers are working on a novel framework for reciprocally using 3D reconstruction and 2D object recognition techniques for 3D modeling of constructed facilities. Learn more

    2
  • A new videogrammetric approach for 3D as-built reconstruction is being created under the sponsorship of the National Science Foundation. It can lead to faster and more flexible 3D scans of infrastructure scenes. Learn more


    3
  • Sponsored by the National Science Foundation, CEE researchers are using a tag-less approach to automatically track construction site resources, using stationary cameras and machine vision algorithms. Learn more


    4