Automated safety analysis of construction site activities using spatio-temporal data

During the past 10 years, construction was the leading industry of occupational fatalities when compared to other goods producing industries in the US. This is partially attributed to ineffective safety management strategies, specifically lack of automated construction equipment and worker monitoring. Currently, worker safety performance is measured and recorded manually, assessed subjectively, and the resulting performance information is infrequently shared among selected or all project stakeholders. Accurate and emerging remote sensing technology provides critical spatio-temporal data that has the potential to automate and advance the safety monitoring of construction processes.
This doctoral research focuses on pro-active safety utilizing radio-frequency location tracking (Ultra Wideband) and real-time three-dimensional (3D) immersive data visualization technologies. The objective of the research is to create a model that can automatically analyze the spatio-temporal data of the main construction resources (personnel, materials, and equipment), and automatically measure, assess, and visualize worker's safety performance. The research scope is limited to human-equipment interaction in a complex construction site layout where proximities among construction resources are omnipresent. In order to advance the understanding of human-equipment proximity issues, extensive data has been collected in various field trials and from projects with multiple scales. Computational algorithms developed in this research process the data to provide spatio-temporal information that is crucial for construction activity monitoring and analysis. Results indicate that worker's safety performance of selected activities can be automatically and objectively measured using the developed model.
The major contribution of this research is the creation of a proximity hazards assessment model to automatically analyze spatio-temporal data of construction resources, and measure, evaluate, and visualize their safety performance. This research will significantly contribute to transform safety measures in construction industry, as it can determine and communicate automatically safe and unsafe conditions to various project participants located on the field or remotely.

Identiferoai:union.ndltd.org:GATECH/oai:smartech.gatech.edu:1853/47564
Date26 March 2013
CreatorsCheng, Tao
PublisherGeorgia Institute of Technology
Source SetsGeorgia Tech Electronic Thesis and Dissertation Archive
Detected LanguageEnglish
TypeDissertation

Page generated in 0.0024 seconds