SGER: Development of Human Poses for the Determination of on-site Construction Productivity in Real Time

University Of Kansas Center For Research Inc, Lawrence KS

Investigators

Abstract

After the September 11, 2001 terrorist attacks, hurricane Katrina, and the tsunami in South Asia, rapid replacement of damaged infrastructure after extreme events has been paid close attention to by government agencies, engineering and construction communities, and the general public. To enhance the capability of rapid replacement of damaged infrastructure after extreme events, there is an urgent need to develop innovative technologies that could be used to produce an accurate and reliable construction schedule to support rapid replacement operations. Results of previous research indicated that the inaccurate schedule is due to the inaccurate productivity data that is used to produce the schedule. Thus, the developed innovative technologies must address the fundamental issues (1) how to improve the accuracy of on-site construction productivity data and (2) how to determine the construction productivity automatically and continuously in order to support rapid construction operations that make dramatic progress every day. Intellectual Merit: The principal investigator (PI) proposes to automatically and continuously measure the on-site construction productivity in real time based on live images acquired from the construction site using a wireless real-time productivity measurement system. To accomplish this, the research team, including the PI and a Ph.D. student, will develop human poses that are associated with construction activities, graphical models that represent human poses and algorithms that can be used to calculate the productivity. If successful, this project will make several major contributions to the advancement of knowledge in the construction industry. First, it will advance the applications of computer vision technologies in construction operations. Second, it will improve the accuracy of on-site construction productivity data. Finally, it will develop new technology that is capable of automatically and continuously measuring productivity data in real-time. With these advancements, it will be possible to develop an accurate and reliable construction schedule for rapid construction operations. Thus, the results of this research project will enhance the capability of rapid replacement of damaged infrastructure after extreme events. Broader Impacts: The PI proposes the following activities to broaden the impact of this project. Results will be widely disseminated to enhance scientific and technological understanding through participation in conferences and professional meetings, publishing results in technical journals and proceedings, as well as establishing a website. The PI will broaden participation of underrepresented groups by making campus visits and presentations at institutions that serve underrepresented groups. In addition, presentations and seminars will be made at the student chapters of Society of Women Engineers, National Society of Black Engineers, and the Society of Hispanic Professional Engineers at the University of Kansas and/or other universities. Finally, the PI will enhance the infrastructure for research and education by developing, maintaining, and operating the construction laboratory in the Department of Civil, Environmental, and Architectural Engineering at the University of Kansas.