Multi-Dimensional Structural Assessment with a Mobile Scanning Device - a


  • Rishabh Bajaj University of Waterloo
  • Zaid Abbas Al-Sabbag University of Waterloo
  • Chul Min Yeum University of Waterloo
  • Sriram Narasimhan University of California, Los Angeles



visual inspection, remote inspection, damage quantification, computer vision


The objective of the proposed research is to build a mobile data acquisition system that can perform multi-dimension structural assessment. The system is fully portable (either handheld or backpack-based) and self-contained hardware consisting of a solid-state lidar sensor, a camera, an onboard computer, and all the auxiliary hardware. The system incorporates a multi-dimension damage assessment algorithm that can detect, segment, and quantify various types of damages needed to be inspected. For example, inspectors measure the length and width of crack (1D) and the areas and depth for spalling (2D and 3D). Our system streamlines such quantitative damage assessment by utilizing 2D images localized to the structure and detailed 3D point cloud data reconstructed from lidar and images. We implemented computer vision algorithms to extract useful damage parameters from those data following a structure inspection guideline.  For the demonstration of our system, we gather data from the in-service bridge using a mobile data acquisition system and conduct damage assessment as per the Ontario Structural Inspection Manual.