This paper introduces a novel approach to assist augmented reality (AR) research by creating a versatile data-capturing rig and an integrated software pipeline. In this project we focus on monocular depth estimation. The project's primary objectives encompass designing and implementing a user-friendly software pipeline and a scalable hardware rig. The scalability of the hardware rig is enabled through the support for multiple sensors with varying computational capabilities and position on the rig. The pipeline serves as an interface to enable the simultaneous activation of a suite of sensors, session recording, post-processing of collected data, and efficient storage for future utilization. The physical rig, featuring wireless connectivity and mobility, allows mounting a computational device and an array of diverse sensors on an easily constructed frame. The seamless integration of various sensors enhances the rig's utility, allowing researchers to gather diverse datasets essential for various AR tasks, such as depth estimation, object recognition, and light estimation.

• This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator

• Haly, Reese
• Galbiati, Federico

Publisher

• Worcester Polytechnic Institute

Identifier

• 115450
• E-project-122023-163008

Advisor

• Guo, Tian

Year

• 2023

Date created

• 2023-12-20

Resource type

• Major Qualifying Project

Major

• Computer Science

Source

• E-project-122023-163008

Rights statement

• In Copyright

Last modified

• 2024-02-07