A graphics and vision unified processor with 0.89μw/fps pose estimation engine for augmented reality

Jae Sung Yoon, Jeong Hyun Kim, Hyo Eun Kim, Won Young Lee, Seok Hoon Kim, Kyusik Chung, Jun Seok Park, Lee Sup Kim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

12 Scopus citations

Abstract

In many ways, 3D graphics and vision processing are inverse operations. Graphics processing generates pixels from descriptors, while vision generates descriptors from pixels [1]. Since augmented reality (AR) requires both graphics and vision abilities (Fig. 18.6.1), we report a unified processor for graphics, vision, and pose estimation for marker tracking. To process both graphics and vision simultaneously, we use 4 key features: (1) 6-way VLIW datapath design of processing elements, (2) reconfigurable processing elements for graphics and vision modes, (3) a pixel arranger for vision processing that has the inverse characteristic of a graphics rasterizer, and (4) a dedicated pose-estimation engine to generate graphics control data from vision processing. Using these methods, we achieve 371.9GOPS/W for full operation in a VGA image and 0.89μW/fps for pose estimation.

Original languageEnglish
Title of host publication2010 IEEE International Solid-State Circuits Conference, ISSCC 2010 - Digest of Technical Papers
Pages336-337
Number of pages2
DOIs
StatePublished - 2010
Event2010 IEEE International Solid-State Circuits Conference, ISSCC 2010 - San Francisco, CA, United States
Duration: 7 Feb 201011 Feb 2010

Publication series

NameDigest of Technical Papers - IEEE International Solid-State Circuits Conference
Volume53
ISSN (Print)0193-6530

Conference

Conference2010 IEEE International Solid-State Circuits Conference, ISSCC 2010
Country/TerritoryUnited States
CitySan Francisco, CA
Period7/02/1011/02/10

Fingerprint

Dive into the research topics of 'A graphics and vision unified processor with 0.89μw/fps pose estimation engine for augmented reality'. Together they form a unique fingerprint.

Cite this