利用持久光电导技术实现多帧集成传感器内计算

IF 4.8 4区 物理与天体物理 Q2 PHYSICS, CONDENSED MATTER Journal of Semiconductors Pub Date : 2024-09-01 DOI:10.1088/1674-4926/24040002
Xiaoyong Jiang, Minrui Ye, Yunhai Li, Xiao Fu, Tangxin Li, Qixiao Zhao, Jinjin Wang, Tao Zhang, Jinshui Miao, Zengguang Cheng
{"title":"利用持久光电导技术实现多帧集成传感器内计算","authors":"Xiaoyong Jiang, Minrui Ye, Yunhai Li, Xiao Fu, Tangxin Li, Qixiao Zhao, Jinjin Wang, Tao Zhang, Jinshui Miao, Zengguang Cheng","doi":"10.1088/1674-4926/24040002","DOIUrl":null,"url":null,"abstract":"The utilization of processing capabilities within the detector holds significant promise in addressing energy consumption and latency challenges. Especially in the context of dynamic motion recognition tasks, where substantial data transfers are necessitated by the generation of extensive information and the need for frame-by-frame analysis. Herein, we present a novel approach for dynamic motion recognition, leveraging a spatial-temporal in-sensor computing system rooted in multiframe integration by employing photodetector. Our approach introduced a retinomorphic MoS<sub>2</sub> photodetector device for motion detection and analysis. The device enables the generation of informative final states, nonlinearly embedding both past and present frames. Subsequent multiply-accumulate (MAC) calculations are efficiently performed as the classifier. When evaluating our devices for target detection and direction classification, we achieved an impressive recognition accuracy of 93.5%. By eliminating the need for frame-by-frame analysis, our system not only achieves high precision but also facilitates energy-efficient in-sensor computing.","PeriodicalId":17038,"journal":{"name":"Journal of Semiconductors","volume":"11 1","pages":""},"PeriodicalIF":4.8000,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multiframe-integrated, in-sensor computing using persistent photoconductivity\",\"authors\":\"Xiaoyong Jiang, Minrui Ye, Yunhai Li, Xiao Fu, Tangxin Li, Qixiao Zhao, Jinjin Wang, Tao Zhang, Jinshui Miao, Zengguang Cheng\",\"doi\":\"10.1088/1674-4926/24040002\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The utilization of processing capabilities within the detector holds significant promise in addressing energy consumption and latency challenges. Especially in the context of dynamic motion recognition tasks, where substantial data transfers are necessitated by the generation of extensive information and the need for frame-by-frame analysis. Herein, we present a novel approach for dynamic motion recognition, leveraging a spatial-temporal in-sensor computing system rooted in multiframe integration by employing photodetector. Our approach introduced a retinomorphic MoS<sub>2</sub> photodetector device for motion detection and analysis. The device enables the generation of informative final states, nonlinearly embedding both past and present frames. Subsequent multiply-accumulate (MAC) calculations are efficiently performed as the classifier. When evaluating our devices for target detection and direction classification, we achieved an impressive recognition accuracy of 93.5%. By eliminating the need for frame-by-frame analysis, our system not only achieves high precision but also facilitates energy-efficient in-sensor computing.\",\"PeriodicalId\":17038,\"journal\":{\"name\":\"Journal of Semiconductors\",\"volume\":\"11 1\",\"pages\":\"\"},\"PeriodicalIF\":4.8000,\"publicationDate\":\"2024-09-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Semiconductors\",\"FirstCategoryId\":\"101\",\"ListUrlMain\":\"https://doi.org/10.1088/1674-4926/24040002\",\"RegionNum\":4,\"RegionCategory\":\"物理与天体物理\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"PHYSICS, CONDENSED MATTER\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Semiconductors","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1088/1674-4926/24040002","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PHYSICS, CONDENSED MATTER","Score":null,"Total":0}
引用次数: 0

摘要

利用检测器内部的处理能力在解决能耗和延迟问题方面大有可为。特别是在动态运动识别任务中,由于需要生成大量信息并进行逐帧分析,因此必须传输大量数据。在此,我们提出了一种新颖的动态运动识别方法,该方法通过采用光电探测器,利用植根于多帧集成的时空传感器内计算系统。我们的方法引入了一种视网膜形态的 MoS2 光电探测器设备,用于运动检测和分析。该装置可生成信息丰富的最终状态,非线性地嵌入过去和现在的帧。随后的乘法累加(MAC)计算可作为分类器有效执行。在对我们的设备进行目标检测和方向分类评估时,我们取得了令人印象深刻的 93.5% 的识别准确率。通过消除逐帧分析的需要,我们的系统不仅实现了高精度,还促进了高能效的传感器内计算。
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
Multiframe-integrated, in-sensor computing using persistent photoconductivity
The utilization of processing capabilities within the detector holds significant promise in addressing energy consumption and latency challenges. Especially in the context of dynamic motion recognition tasks, where substantial data transfers are necessitated by the generation of extensive information and the need for frame-by-frame analysis. Herein, we present a novel approach for dynamic motion recognition, leveraging a spatial-temporal in-sensor computing system rooted in multiframe integration by employing photodetector. Our approach introduced a retinomorphic MoS2 photodetector device for motion detection and analysis. The device enables the generation of informative final states, nonlinearly embedding both past and present frames. Subsequent multiply-accumulate (MAC) calculations are efficiently performed as the classifier. When evaluating our devices for target detection and direction classification, we achieved an impressive recognition accuracy of 93.5%. By eliminating the need for frame-by-frame analysis, our system not only achieves high precision but also facilitates energy-efficient in-sensor computing.
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
Journal of Semiconductors
Journal of Semiconductors PHYSICS, CONDENSED MATTER-
CiteScore
6.70
自引率
9.80%
发文量
119
期刊介绍: Journal of Semiconductors publishes articles that emphasize semiconductor physics, materials, devices, circuits, and related technology.
期刊最新文献
Effects of gallium surfactant on AlN thin films by microwave plasma chemical vapor deposition Effects of 1 MeV electron radiation on the AlGaN/GaN high electron mobility transistors 10 × 10 Ga2O3-based solar-blind UV detector array and imaging characteristic Multiframe-integrated, in-sensor computing using persistent photoconductivity Localized-states quantum confinement induced by roughness in CdMnTe/CdTe heterostructures grown on Si(111) substrates
×
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