一种动态可重构视觉芯片架构的背景光效果

R. Moriwaki, Minora Watanabe
{"title":"一种动态可重构视觉芯片架构的背景光效果","authors":"R. Moriwaki, Minora Watanabe","doi":"10.1109/SII.2010.5708363","DOIUrl":null,"url":null,"abstract":"Recently, demands for implementation of a highspeed image recognition function onto autonomous vehicles and robots, that is superior to that of the human eye, have been increasing. To date, analog-type vision chips and digital vision chips have been developed. Nevertheless, even now, realizing such high-speed real-time image recognition operation is extremely difficult because the template information transfer rate and template matching operation cycle reach the order of Petapixel/s. Therefore, to accommodate template matching operations that can be executed at rates greater than Petapixel/s, a dynamically reconfigurable vision-chip architecture has been developed in which a holographic memory technique is introduced to current VLSI technology. However, the dynamically reconfigurable vision-chip architecture must receive image information in addition to configuration context information. At such a time, a salient concern is that image information light might reduce the retention time of photodiode memories on a dynamically reconfigurable vision-chip. This paper therefore clarifies that the background light does not affect the photodiode memories on a dynamically reconfigurable vision-chip architecture.","PeriodicalId":334652,"journal":{"name":"2010 IEEE/SICE International Symposium on System Integration","volume":"16 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Background light effect of a dynamically reconfigurable vision-chip architecture\",\"authors\":\"R. Moriwaki, Minora Watanabe\",\"doi\":\"10.1109/SII.2010.5708363\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recently, demands for implementation of a highspeed image recognition function onto autonomous vehicles and robots, that is superior to that of the human eye, have been increasing. To date, analog-type vision chips and digital vision chips have been developed. Nevertheless, even now, realizing such high-speed real-time image recognition operation is extremely difficult because the template information transfer rate and template matching operation cycle reach the order of Petapixel/s. Therefore, to accommodate template matching operations that can be executed at rates greater than Petapixel/s, a dynamically reconfigurable vision-chip architecture has been developed in which a holographic memory technique is introduced to current VLSI technology. However, the dynamically reconfigurable vision-chip architecture must receive image information in addition to configuration context information. At such a time, a salient concern is that image information light might reduce the retention time of photodiode memories on a dynamically reconfigurable vision-chip. This paper therefore clarifies that the background light does not affect the photodiode memories on a dynamically reconfigurable vision-chip architecture.\",\"PeriodicalId\":334652,\"journal\":{\"name\":\"2010 IEEE/SICE International Symposium on System Integration\",\"volume\":\"16 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2010-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2010 IEEE/SICE International Symposium on System Integration\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/SII.2010.5708363\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 IEEE/SICE International Symposium on System Integration","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SII.2010.5708363","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

最近,在自动驾驶汽车和机器人上实现优于人眼的高速图像识别功能的需求越来越大。到目前为止,模拟型视觉芯片和数字视觉芯片已经被开发出来。然而,即使是现在,实现这种高速的实时图像识别操作也是极其困难的,因为模板信息传输速率和模板匹配操作周期达到了Petapixel/s的量级。因此,为了适应可以以大于Petapixel/s的速率执行的模板匹配操作,开发了一种动态可重构的视觉芯片架构,其中将全息存储技术引入到当前的VLSI技术中。然而,动态可重构的视觉芯片架构除了接收配置上下文信息外,还必须接收图像信息。此时,一个突出的问题是图像信息光可能会减少光电二极管存储器在动态可重构视觉芯片上的保留时间。因此,本文阐明了背景光不会影响动态可重构视觉芯片架构上的光电二极管存储器。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Background light effect of a dynamically reconfigurable vision-chip architecture
Recently, demands for implementation of a highspeed image recognition function onto autonomous vehicles and robots, that is superior to that of the human eye, have been increasing. To date, analog-type vision chips and digital vision chips have been developed. Nevertheless, even now, realizing such high-speed real-time image recognition operation is extremely difficult because the template information transfer rate and template matching operation cycle reach the order of Petapixel/s. Therefore, to accommodate template matching operations that can be executed at rates greater than Petapixel/s, a dynamically reconfigurable vision-chip architecture has been developed in which a holographic memory technique is introduced to current VLSI technology. However, the dynamically reconfigurable vision-chip architecture must receive image information in addition to configuration context information. At such a time, a salient concern is that image information light might reduce the retention time of photodiode memories on a dynamically reconfigurable vision-chip. This paper therefore clarifies that the background light does not affect the photodiode memories on a dynamically reconfigurable vision-chip architecture.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Depth computation using optical flow and least squares Development of a laser scan method to decrease hidden areas caused by objects like pole at whole 3-D shape measurement Rhythmic components of spatio-temporally decorrelated EEG signals based Common Spatial Pattern Fluorescent microscope system to track a particular region of C. elegans Clamp grasping and insertion task automation for automobile industry
×
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