skip to primary navigationskip to content

Dr Ioannis Brilakis selected for ASCE 2013 Collingwood Prize

last modified Aug 05, 2015 02:28 PM

Dr Ioannis Brilakis, Laing O'Rourke Lecturer of Construction Engineering and his former students, Zhenhua Zhu - Assistant Professor (Concordia University, Canada) and Stephanie German - Post-Doctural Fellow (EPFL, Switzerland), are the recipients of the 2013 Collingwood Prize of the American Society of Civil Engineers for their paper titled "Visual Pattern Recognition Models for Remote Sensing of Civil Infrastructure", Journal of Computing in Civil Engineering, October 2011.  In selecting this paper for this prize, the committee particularly noted its contribution to engineering knowledge.  The award will be presented during the ASCE's Annual Conference Leadership Breakfast, October 11, 2013 in Charlotte, NC.


This paper stemmed from Dr Brilakis' CAREER Award from the US National Science Foundation.  It outlines his fundamental theory on how to create recognition models for civil infrastructure elements, such as columns, beams, walls, slabs, decks, etc. followed by example applications that have proven successful.  The paper essentially formalises the process of creating new Visual Pattern Recognition (VPR) models to simplify the steps needed to create each mathematical description and provide a set of common tools necessary for this purpose.  This will automate the transformation of infrastructures' 3D surfaces into information rich, 3D element models with the help of machine vision.  Brilakis said that this way, instead of manually recognising each element every time it is encountered, we need only recognise its characteristics once and automatically detect it each subsequent time.  This is an analogous to defining an alphabet (letters = characteristics) so that this project will build the words (element models) and find them in text (3D surface), instead of having to manually find the words in every text that we encounter.  The benefit comes from the ability to reuse the known letters (characteristics) and the words (element models) every time we have a new text (3D surface).


The immediate advantage that will result from this work is the ability to automate the element recognition step of the "as-built" model generation process.  The National Academy of Engineering recently listed listed "Restoring and Improving Urban Infrastructure" as one of the Grand Challenges of Engineering in the 21st century,  Two of the greater issues that cause this grand challenge are the need for more automation in construction, through advances in computer science and robotics, and the lack of viable methods to map and label existing infrastructure is spent on manually converting surface data to a 3D model.  This result id that as-build models are not produced for the vast majority of new construction and retrofit projects, which leads to rework and design challenges that cost up to 10% of the installed costs.  Any efforts towards automating the modelling process will increase the percentage of infrastructure projects being modelled and, considering that construction is a multi-trillion industry worldwide, each 1% of increase can lead up to billions in savings.