Construction Progress Tracking Using Scan-vs-BIM from Visual and Sensed Data

This project is a direct continuation of previous research at the Centre for Systems Engineering and Innovation and aims to develop a prototype to process visual and sensed data for construction progress monitoring in a fully automated fashion. Our research employs BIM and computer vision methods, in addition to exploring the potential of deep learning and semantic SLAM in this context.

Automating manual progress and quality reporting processes in the construction industry would allow to identify problems early on and respond quickly, avoiding reworks and overruns of cost- and time-schedules. In contrast, it can currently take up to several weeks for critical information to reach stakeholders.


Objectives

  1. A review of 3D reconstruction methods such as SLAM from visual data, i.e. RGB, RGB-D and 360° images, and an exploration of applications for progress monitoring.
  2. A review of Scan-to-BIM for progress monitoring and a comparison to Scan-vs-BIM approaches.
  3. Development of a prototype for large-scale reconstruction and semantic understanding from image data.


Research Team

Centre for Systems Engineering and Innovation:
Marcus Wallbaum, Prof. Jennifer Whyte

Smart Robotics Lab:
Dimos Tzoumanikas, Dr. Stefan Leutenegger


Funding

This project is a collaboration with Contilio and funded by Innovate UK. Research is conducted jointly at the Smart Robotics Lab and the Centre for Systems Engineering and Innovation at Imperial College London.

Cont