Detecting the Hazards of Lifting and Carrying in Construction through a Coupled 3D Sensing and IMUs Sensing System
Publication: Computing in Civil and Building Engineering (2014)
Abstract
Construction companies in Hong Kong suffer huge losses due to labor fatalities and injuries. More than 25% of all of the injuries and fatalities in all industries in Hong Kong are caused by the construction industry. This is different from the U.S., whose top injury cause for fatal injuries is a fall to a lower level (34%) and nonfatal injuries (23%). The most frequent type of injuries in Hong Kong is due to lifting and carrying (19.2%). Recently, automated 3D sensing systems (Kinect) have been employed to identify motion-related hazards to improve construction safety conditions. However, limitations (such as extreme light conditions, occlusions and misrepresentations) of 3D sensing systems hinder its application in engineering practices. To resolve those limitations, this research proposed a coupled system which integrates and synchronizes the Kinect with Inertial Measurement Unit (IMUs). With the help of the coupled system, IMUs could uninterruptedly collect motion data (accelerations and angular rates), even under extreme light conditions or under occlusions, while Kinect could provide a reference system for IMUs to construct postures. The whole sensor network will be able to capture complete and reliable data even if Kinect fails to work properly. Moreover, the proposed coupled system will also promote other human related research, such as productivity and labor tracking.
Get full access to this article
View all available purchase options and get full access to this chapter.
Information & Authors
Information
Published In
Copyright
© 2014 American Society of Civil Engineers.
History
Published online: Jun 17, 2014
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.