 

This paper proposes a method that can apply augmented reality under the conditions of industrial workshops in large scene. This method is based on the theory of robot kinematics and adopts the unlabeled augmented reality visual tracking, which can realize the remote location of imaging position and attitude tracking in a large field.

This paper also makes a comparative analysis of the marked augmented reality system and the unmarked augmented reality system under the conditions of application in industrial workshops in large scenes and summarizes the advantages of unmarked augmented reality.

This paper also describes the hardware of the large scene augmented reality system, including its mechanical structure and control system. The design process of the software is also explained, especially the software platform unity3D and software design language used in the system are emphatically introduced.

This article through to the screen imaging principle, such as the center, the analysis of the factors such as the actual focal length, lens distortion, and the world coordinate system, workpiece coordinate system, video camera, screen, camera turntable coordinate system, the introduction of the five space coordinate system and convert computing applications, enhanced by a big scene shows the calculation method, under this kind of calculation method, The orbital robot with a camera moves in large space and long-distance orbit. Combining with the ground system of sensor array objects, it achieves good 3D augmented reality image registration, and solves the problem of poor matching of identifying augmented reality images under the condition of insufficient light or interference in large industrial manufacturing workshops.

In this paper, an application of an on-track node switch is introduced to solve the initialization problem of orbital robot in large space, and the industrial application of large space unlabeled augmented reality is effectively realized, which improves the observation efficiency.

In this paper, the error of the large scene augmented reality observation system designed by the experimental team is analyzed, and the relationship between the system error and the accuracy of the orbit and the output error of the camera turntable Angle is summarized, as well as the influence of other factors on the observation accuracy of the system is also summarized. Taking this experiment as an example, the standard deviation of observation is calculated.

Finally, two repetitive experiments are carried out to verify the capability of the proposed method in observing static large size objects and dynamic objects in a large scene.


A Kinematic-Based Unmarked Augmented Reality Method for Large Scene Industrial Workshops

Division / Sponsors: 
Aerospace, Bioengineering, Applied Mechanics, Design Engineering Division, Advanced Energy Systems, Manufacturing Engineering Division, Noise Control and Acoustics, Nondestructive Evaluation, Diagnosis, and Prognosis (NDPD), Nuclear Engineering Division, Process Industries Division, Fluids Engineering, Heat Transfer, Materials, Microelectromechanical Systems, Safety Engineering and Risk Analysis, Computers & Information in Engineering


Paper Proceedings: https://asmedigitalcollection.asme.org/IMECE/IMECE2020/volume/84478

IMECE2020 - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.