skip to content

Construction Information Technology Laboratory

 

Past Projects

DAMAGE DETECTION for BRIDGE CONDITION ASSESSMENT

October 2014 – September 2018

Trimble Europe BV Grant, PI: Ioannis Brilakis, £99,858

The aim of this project was to investigate new methods for detecting bridge damage and deterioration, and mapping the detections to the bridge’s information model. The goal was to detect all patterns of damage through a common multi-classifier, and automatically measure its structurally important spatial properties and map them on the corresponding element in the information model.

Leading student researcher:  Philipp Huethwohl

 

COLLABORATIVE RESEARCH: MACHINE VISION ENHANCED POST EARTHQUAKE INSPECTION AND RAPID LOSS ESTIMATION

August 2010 – August 2013
NSF Grant #1000700, PI: Reginald DesRoches, £235,315

This project combined infrastructure objects and damage recognition from video with structural engineering to enable quantitative assessments of buildings damaged by earthquakes. The purpose was to create the missing link between measured damage data and the condition of the building as a whole, so as to assist structural specialists in making an assessment decision grounded on measurements. The proposed automated procedure classified component damage per the ATC-20 guidelines using empirically based models. Component damage was compiled to determine the damage state of the building, recommend red, yellow, or green tagging of the building, and estimate repair time and cost. Building damage state, configuration and type were used to query a set of fragility curves defining the likelihood of building collapse during an aftershock and, thereby, provided an improved understanding of risk. The validation of this work was based on structural tests from NEESR and other sources.

Leading student researcher: Stephanie German and Jong Su Jeon.

 

RAPID: URGENT COLLECTION OF PERISHABLE CONDITION DATA FROM STRUCTURES AFFECTED BY THE HAITI EARTHQUAKE

April 2010 – July 2010
NSF Grant #1034845, PI: Laura Lowes, £26,144

This Rapid Response Research (RAPID) grant provided the opportunity to a team of researchers to travel to Haiti and collect damage data and design information for concrete buildings damaged during the 2010 earthquake. These data were used to validate a rapid, image-based, semi-automated method for assessing damage and collapse risk for reinforced concrete structures to both reduce the time needed for, and to improve the reliability of, post-event inspection. The aftermath of recent earthquakes in the United States suggests that for even a moderate intensity earthquake affecting a metropolitan area, it could take weeks or months to inspect, and thereby grant access to, damaged buildings. The research team sought to both reduce the time needed for and improve the reliability of post-event inspection by using the collected data to validate rapid methods for assessing damage and collapse risk for reinforced concrete structures.

Leading student researchers: Zhenhua Zhu and Stephanie German.

 

 

Latest news

PhD studentships advertised as part of the Cloud-based Building Information Modelling (CBIM) training network

13 November 2019

The following PhD studentships are available at the University of Cambridge on the European Commission-funded, Marie Sklodowska-Curie "CBIM" European...

Infrastructure Computer Vision – Book available for pre-order

28 October 2019

Pre-order the soon-to-be-released Infrastructure Computer Vision to explore advanced information and sensing technologies, and how to apply them to individual projects.