Xiaoyong Jiang, Minrui Ye, Yunhai Li, Xiao Fu, Tangxin Li, Qixiao Zhao, Jinjin Wang, Tao Zhang, Jinshui Miao, Zengguang Cheng
{"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":null,"pages":null},"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}
引用次数: 0
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 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.