Vela Receives ASCE Best Paper Award

Atlanta, GA
Patricio Vela

Patricio Vela

Download Image

Patricio A. Vela received the American Society of Civil Engineers (ASCE) 2018 John O. Bickel Award for a paper co-authored with colleagues from the University of Cambridge. The award was presented at the Construction Research Congress, held April 2-4 in New Orleans, Louisiana, and recognizes the best original article or paper published in an ASCE journal during a specified year. 

The title of the award-winning paper is “Optimized Parameters for Over-Height Vehicle Detection under Variable Weather Conditions,” published in the September 2017 issue of the Journal of Computing in Civil Engineering. Vela’s coauthors are Ioannis Brilakis, the Laing O Rourke Reader in Construction Engineering at the University of Cambridge, and his Ph.D. student Bella Nguyen, who conducted the research for this project at Georgia Tech through the Marie Curie International Research Staff Exchange Scheme.

Over-height vehicle drivers continuously ignore warning signs and strike onto bridges despite the number of preventative methods installed at low clearance bridges. In this paper, the authors present a new method for over-height vehicle strike prevention with a single calibrated camera mounted on the side of the roadway. The camera is installed at the height of the over-height plane formed by the average of the maximum allowable heights across all lanes in a given traffic direction; the error caused by the road gradient is assumed to be negligible and absorbed through the calibration process. 

At that height, the over-height plane can be safely approximated as a line in the camera view. Any vehicle exceeding this line is consequently over-height. The camera position and orientation are determined through a calibration process proposed. Instances of over-height vehicles are detected through optical flow monitoring. Evaluation of the system resulted in a height accuracy of ±2.875mm; outperforming the target accuracy of ±5cm, OH detection accuracy of 68.9%, and classification performance of 83.3%. Although its accuracy is comparable to existing laser beam systems, it outperforms them on cost which is an order of magnitude less because of eliminating the need for new permanent infrastructure.

Last revised August 6, 2018