基于传感器内计算的动态视觉预测分析
Analysis of Dynamic Visual Prediction Based on In-sensor Computing Network
李耘海 1付晓1
作者信息
- 1. 江苏大学 物理与电子工程学院,江苏 212000
- 折叠
摘要
阐述一种创新的基于多维信息的传感器内计算方法,实现图像的高效识别与预测.该方法融合储层计算(RC)网络的理论框架,并以此为基础,开发出一种基于二硫化钼(MoS2)的探测器阵列.充分利用探测器本身固有的光电导率(PPC)效应.通过这种方式,成功地将当前与过去的多帧信息整合至单一帧内,从而改变传统的逐帧计算模式.此外,在器件层面进行深入的预处理,细致比较不同衰减曲线对任务性能的影响.最终实现多帧字母变换预测任务,为机器视觉领域带来新的突破.
Abstract
This paper describes a method of in-sensor computing with multidimensional information to achieve image recognition and prediction.In the work,incorporating the computational theory of reservoir computing(RC)networks,it developed a MoS2-based detector array that functions as a dynamic photoelectronic reservoir,and by leveraging the inherent persistence of photoconductivity(PPC)effect of the detector itself,integrated present and past multi-frame information into a single frame,breaking traditional frame-by-frame computing paradigm.Furthermore,it performed preprocessing on the device to compare the impact of different decay curves on task performance,ultimately accomplishing multi-frame letter transformation classification and word prediction tasks.
关键词
智能技术/动态视觉/感内计算/二硫化钼Key words
intelligent technology/dynamic vision/in-sensor computing network/MoS2引用本文复制引用
出版年
2024
NETL
NSTL
万方数据