Bridges, Tunnels and other Transportation Structures

Full Session with Abstracts

501463 - Crowd-sourced urban image recognition for monitoring in a smart city

Friday, April 26
3:30 PM - 5:00 PM
Location: Bayhill 23-24

The concept of citizen engineering has been previously introduced as a new paradigm in urban infrastructure monitoring that seeks to fill the gaps that exist within the assessment of urban infrastructure by proposing a cyber-human evaluation system. In this framework, non-expert citizens are engaged, trained and motivated to contribute data describing the urban infrastructure and its condition. A technical challenge facing this system is how to develop an efficient automated means of converting this crowd-sourced data into information, insights and decisions.
This work aims to leverage the recent advances in the field of computer vision and image recognition to develop a framework for image-based crowd-sourced monitoring of urban infrastructure and built environment. To this end, visual recognition models based on deep convolutional neural networks were built that can process urban infrastructure images and automatically detect and describe features of interest in them. Specifically, a dataset of the most common condition descriptors in urban environment was collected and annotated. These include infrastructure defects and degradation such as cracks, potholes, patches, and faded markings. To enhance the performance of the image recognition models, an auxiliary class of features including visual distractors from urban scene elements was added to the training set. Finally, the trained models were tested on user-generated samples and their performance was reported. Results demonstrate that the models are capable of classifying the images into the pertinent categories with excellent accuracy and therefore they can be integrated into the citizen engineering framework to automate the urban monitoring task.

Devin Harris

Associate Professor
University of Virginia

Dr. Harris is currently an Associate Professor Civil and Environmental Engineering Department at the University of Virginia. He is also the Director of the Center for Transportation Studies (CTS) and a member of the Link Lab. He joined the program as an Assistant Professor in July 2012. He had a prior appointment at Michigan Technological University as the Donald F. and Rose Ann Tomasini Assistant Professor in structural engineering. His research and teaching interests include bridge behavior, image-based measurement techniques, crowd-sourcing, data analytics, condition assessment and structural health monitoring, reinforced and prestressed concrete behavior, the application of innovative materials in civil infrastructure, and railroad engineering. Dr. Harris’ research approach often utilizes a combination of laboratory and field investigations and finite element modeling. Dr. Harris is active in the American Concrete Institute (ACI), the Transportation Research Board (TRB), the International Digital Image Correlation Society (IDICS). He has also been involved in other professional organizations including the American Railway Engineering and Maintenance-of-Way Association (AREMA), Precast/Prestressed Concrete Institute, and the National Society of Black Engineers.


Send Email for Devin Harris


501463 - Crowd-sourced urban image recognition for monitoring in a smart city

Attendees who have favorited this

Please enter your access key

The asset you are trying to access is locked. Please enter your access key to unlock.

Send Email for Crowd-sourced urban image recognition for monitoring in a smart city