Ioannis Brilakis, assistant professor in Civil and Environmental Engineering and Building Construction, has received a CAREER Award from the National Science Foundation (NSF) for his project, "CAREER: Visual Pattern Recognition Models for Remote Sensing of Civil Infrastructure"
The five-year award at $402,279.00 will continue Brilakis' work in model based infrastructure elements recognition, an area in which he's been involved since 2005. He has applied machine vision algorithms to study ways to detect patterns in infrastructure data, such as structural elements, damage, defects, construction equipment and workers, so as to allow the use of low cost cameras for construction automation and infrastructure mapping.
The project that won him the CAREER Award will involve formalizing 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 recognizing each element every time it is encountered, we need only recognize its characteristics once and automatically detect it each subsequent time. This is analogous to defining an alphabet (letters = characteristics) so that this project will build the words (element models) and find them in a text (3D surface), instead of having to manually find the words in every text we encounter. The benefit comes from the ability to reuse the known letters (characteristics) and words (element models) every time we have a new text (3D surface).
As an educational component, he said the project’s validation prototype will be created and used also for educational purposes at all education levels (K-12, undergraduate, graduate). "I have partnered with the SEIMC GIFT Program, the ACE Atlanta Mentor Program and others to bring the VPR model prototype in K-12 education, and excite the high school students’ interest in science and math through cool machine vision innovations," Brilakis said. "Undergraduate students will get hands-on experience in courses through a concrete and steel inspector spin-off, and graduate students will actually help create new VPR models and validate them as part of course semester projects."
“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,” Brilakis said. “The National Academy of Engineering recently listed “Restoring and Improving Urban Infrastructure” as one of the Grand Challenges of Engineering in the 21st century. Two of the greatest 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. Over two thirds of the effort needed to model even simple infrastructure is spent on manually converting surface data to a 3D model. The result is that as-built models are not produced for the vast majority of new construction and retrofit projects, which leads to rework and design changes that cost up to 10% of the installed costs. Any efforts towards automating the modeling process will increase the percentage of infrastructure projects being modeled and, considering that construction is a $900 billion industry, each 1% of increase can lead up to $900 million in savings.”
For more information about Brilakis’ work, visit his group's homepage at: www.citl.gatech.edu.