Abstract
While mobile applications have greatly benefited from 2D computer vision algorithms such as object detection and classification, there is limited research on exploring 3D vision that is enabled by the increasing availability of depth cameras and LiDAR scanners on mobile devices. In this paper, we propose a hybrid mobile vision system that intelligently combines 2D and 3D vision for improving the performance of emerging applications such as augmented and mixed reality and volumetric content analytics. Our research is motivated by and explores the key observation of the crucial latency-accuracy tradeoff between 2D and 3D vision. We present a research agenda with two principles for enhancing mobile vision stack, complementing 3D vision with its 2D counterpart by leveraging their diverse resource/accuracy profiles and processing 3D data (e.g., point clouds) with 2D vision cues for mitigating the high computation and storage costs.
Original language | English (US) |
---|---|
Title of host publication | HotMobile 2022 - Proceedings of the 23rd Annual International Workshop on Mobile Computing Systems and Applications |
Publisher | Association for Computing Machinery, Inc |
Pages | 61-67 |
Number of pages | 7 |
ISBN (Electronic) | 9781450392181 |
DOIs | |
State | Published - Mar 9 2022 |
Event | 23rd Annual International Workshop on Mobile Computing Systems and Applications, HotMobile 2022 - Virtual, Online, United States Duration: Mar 9 2022 → Mar 10 2022 |
Publication series
Name | HotMobile 2022 - Proceedings of the 23rd Annual International Workshop on Mobile Computing Systems and Applications |
---|
Conference
Conference | 23rd Annual International Workshop on Mobile Computing Systems and Applications, HotMobile 2022 |
---|---|
Country/Territory | United States |
City | Virtual, Online |
Period | 3/9/22 → 3/10/22 |
Bibliographical note
Funding Information:We thank the anonymous reviewers and our shepherd Urs Hen-gartner for their insightful comments. The research of Bo Han and Nan Wu was funded in part by 4-VA, a collaborative partnership for advancing the Commonwealth of Virginia. Felix Xiaozhu Lin was supported in part by NSF awards #1846102, #1919197, #2106893, and the Virginia’s Commonwealth Cyber Initiative.
Publisher Copyright:
© 2022 Owner/Author.
Keywords
- hybrid mobile vision
- mobile vision
- object detection
- point cloud
- volumetric content process