File Download
There are no files associated with this item.
SFX Link
- Find it @ UNIST can give you direct access to the published full text of this article. (UNISTARs only)
- Lee, Kyuho Jason
- Intelligent Systems Lab.
Views & Downloads
Detailed Information
Cited time in 
Cited time in 
Cited time in
Metadata Downloads
A multi-granularity parallelism object recognition processor with content-aware fine-grained task scheduling
- Author(s)
- Park, Junyoung, Hong, Injoon, Kim, Gyeonghoon, Kim, Youchang, Lee, Kyuho, Park, Seongwook, Bong, Kyeongryeol, Yoo, Hoi-Jun
- Issued Date
- 2013-04-17
- Citation
- IEEE Symposium on Low-Power and High-Speed Chips
- Abstract
- Multiple granularity parallel core architecture is proposed to accelerate object recognition with low area and energy consumption. By adopting task-level optimized cores with different parallelism and complexity, the proposed processor achieves real-time object recognition with 271.4 GOPS peak performance. In addition, content-aware fine-grained task scheduling is proposed to enable low power real-time object recognition on 30fps 720p HD video streams. As a result, the object recognition processor achieves 9.4nJ/pixel energy efficiency and 25.8 GOPS/W·mm 2 power-area efficiency in O.13um CMOS technology.
- Publisher
- 16th IEEE Symposium on Low-Power and High-Speed Chips, COOL Chips 2013
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.