Augmented Reality (AR) allows workers to construct buildings accurately and intuitively without the need for traditional tools like 2-D drawings and rulers. However, accurately tracking worker’s pose remains a significant challenge in existing experiments due to their continuous and irregular movement. This research discusses a series of methods using cameras and algorithms to achieve the 6-DoF pose tracking function and reveal the relationship between each method and corresponding tracking accuracy in order to figure out a robust approach of AR-assisted assembly. This paper begins with a consideration of the possible limitations of existing methods including the image drift associated with visual SLAM and the time-consuming nature of fiducial markers. Next, the entire hardware and software framework was introduced, which elaborates on how the motion capture system is integrated into the AR-assisted assembly system. Then, some experiments have been carried out to demonstrate the connection between the system set up and pose tracking accuracy. This research shows the possibility to easily finish assembly task based on AR technology by integrating motion capture system.