Natural Visual Perception for (Augmented Reality Workstations
Final Report Abstract
The outcome of this research can be summarized as follows: • A novel method for view-dependent rendering for monocular AR workstation was introduced. The fidelity of the view adaptation has been verified by comparing the received adaptation with a ground truth. • Novel computational techniques for the simulation of perspective, motion parallax, and shadows were developed and their feasibility was proven. • Study results show that users gain advantages from simulated depth cues when estimating the distance between (significant) and the size of (not significant) objects. • The results also indicate that a user only gains advantages from AR instructions when the assembly task can be considered as difficult. The results are scientific relevant and usable: first, the results support other findings that depth cues are an important factor of perception and support the users in several tasks. The study results indicate benefits when assessing complex spatial structures. Second, the research also demonstrates that the simulation of believable depth cues in an AR application is possible with rapid image processing methods. Thus, this research introduce ways to enhance the fidelity of monitor-based AR and the efficiency of AR assembly support. One limitation of this research is due to the subject that was chosen for the user study; the axial piston motor. It was used because it is a real product and the results should be applicable to an industry use case. However, not all steps are considered as difficult and the research results - after finishing the study - indicate that a user only gains benefits when performing difficult tasks. The next step in this research is to design an artificial object that requires several difficult alignment tasks. This would facilitate to better assess the benefits of simulated depth cues.
Publications
- 2013, "A Hybrid Tracking Solution to Enhance Natural Interaction in Marker-based Augmented Reality Applications," The Sixth International Conference on Advances in Computer-Human Interactions (ACHI 2013), February 24 - March 1, Nice, France
R. Radkowski, J. Oliver
- 2013, "Simulation of Motion Parallax for Monitor-based Augmented Reality Applications," Proceedings of the ASME 2013 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference, IDETC/CIE 2013, August 30-September 2, Portland, OR
R. Radkowski, J. Oliver
- 2014, "Enhanced Natural Visual Perception for Augmented Reality-Workstations by Simulation of Perspective," IEEE Journal of Display Technology, 10(5), May 2014, pp. 333-344
R. Radkowski, J. Oliver
- 2014, "Monocular Depth Cues for Augmented Reality Applications to Enhance Spatial Perception Tasks," I. Horváth and Z. Rusák (Eds.), Proceedings of Tools and Methods of Competitive Engineering (TMCE 2014), May 19–23, Budapest, Hungary
R. Radkowski, J. Oliver
- "Augmented reality-based manual assembly support with visual features for different degrees of difficulty," International Journal on Human-Computer Interaction, Volume 31, 2015 - Issue 5, pages 337-349
R. Radkowski, J. Herrema, and J. Oliver
(See online at https://doi.org/10.1080/10447318.2014.994194)
