Vision-based Tracking of Worker Trajectories in Built Workplaces for Safety and Health Study

Abstract

Construction sites are the place where personnel and equipment work closely. In such workplaces, human movement dynamically adapts to the surrounding circumstances which are congested and continually changing. Acquisition of worker trajectories and measurement of physical value of workplaces, however, typically requires on-site investigation, and thus is a time-consuming and error-prone process. Insufficient understanding of manual tasks and working environments in terms of operational planning and analysis can lead to unreasonable work plans, irrational layout design of the workplace, and unsafe equipment operation. As a result, workers are facing risks caused by adverse jobsite conditions. Accordingly, the purpose of this research is to improve worker health and safety on construction sites through designing a safer workplace, eliminating potential injuries caused by unhealthy motion, and reducing risks of equipment operation. Specifically, stereo videos are collected by a stereo vision camera to record the dimension of construction workplaces and also to record worker movements. Then the depth information contained in the stereo videos are analyzed and processed (e.g., computing disparity from stereo videos and reconstructing 3D scenes from a disparity map) to quickly extract worker trajectories and to accurately rebuild 3D models of workplaces. The acquired geometry information of worker movements and workplace models can assist personnel in designing better project plans to facilitate the following three aspects: (1) providing necessary inputs for motion study to design a healthier motion plan; (2) providing a visible 3D model of workplaces to recognize unsafe workplace layouts; and (3) enabling operators to identify potential risks and hazards during equipment operation and then achieve safer equipment operations.