An 81.6 GOPS Object Recognition Processor Based on NoC and Visual Image Processing Memory

Donghyun Kim, Kwanho Kim, Joo-Young Kim, Seungjin Lee, H. Yoo
{"title":"An 81.6 GOPS Object Recognition Processor Based on NoC and Visual Image Processing Memory","authors":"Donghyun Kim, Kwanho Kim, Joo-Young Kim, Seungjin Lee, H. Yoo","doi":"10.1109/CICC.2007.4405769","DOIUrl":null,"url":null,"abstract":"An 81.6 GOPS object recognition processor is developed by using NoC and visual image processing (VIP) memory. SIFT (scale invariant feature transform) object recognition requires huge computing power and data transactions among tasks. The chip integrates 10 SIMD PEs for data/task level parallelism while the NoC facilitates inter-PE communications. The VIP memory searches local maximum pixel inside a 3times3 window in a single cycle providing 65.6 GOPS. The proposed processor achieves 15.9 fps SIFT feature extraction at 200 MHz.","PeriodicalId":130106,"journal":{"name":"2007 IEEE Custom Integrated Circuits Conference","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"43","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 IEEE Custom Integrated Circuits Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CICC.2007.4405769","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 43

Abstract

An 81.6 GOPS object recognition processor is developed by using NoC and visual image processing (VIP) memory. SIFT (scale invariant feature transform) object recognition requires huge computing power and data transactions among tasks. The chip integrates 10 SIMD PEs for data/task level parallelism while the NoC facilitates inter-PE communications. The VIP memory searches local maximum pixel inside a 3times3 window in a single cycle providing 65.6 GOPS. The proposed processor achieves 15.9 fps SIFT feature extraction at 200 MHz.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于NoC和视觉图像处理存储器的81.6 GOPS目标识别处理器
采用NoC和视觉图像处理(VIP)存储器,开发了81.6 GOPS目标识别处理器。SIFT (scale invariant feature transform)目标识别需要巨大的计算能力和任务间的数据交易。该芯片集成了10个SIMD pe,用于数据/任务级并行,而NoC则促进pe间通信。VIP内存在单个周期内在3times3窗口内搜索局部最大像素,提供65.6 GOPS。该处理器在200 MHz下可实现15.9 fps的SIFT特征提取。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
A Real-Time Feedback Controlled Hearing Aid Chip with Reference Ear Model An 81.6 GOPS Object Recognition Processor Based on NoC and Visual Image Processing Memory A Time-Interleaved Track & hold in 0.13 μm CMOS sub-sampling a 4 GHz signal with 43 dB SNDR Low-Power CMOS Energy Detection Transceiver for UWB Impulse Radio System An Embedded 8-bit RISC Controller for Yield Enhancement of the 90-nm PRAM
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1