<br>基于完全模拟人类视觉的尖峰人工视觉架构,Advanced Materials

当前位置： X-MOL 学术 › Adv. Mater. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

基于完全模拟人类视觉的尖峰人工视觉架构
Advanced Materials ( IF 27.4 ) Pub Date : 2024-02-06 , DOI: 10.1002/adma.202312094
Yi Wu _{1,

2} , Wenjie Deng ₂ , Kexin Li ₂ , Xiaoting Wang ₂ , Bo Liu ₂ , Jingzhen Li ₂ , Zhijie Chen ₂ , Yongzhe Zhang _{1,

2}

Affiliation

智能视觉需要部署始终开启且低功耗的探测器，反映人类视觉的连续且不间断的响应特性。尽管如此，当代的人工视觉系统通过连续处理大量图像帧并执行复杂的算法来实现这一目标，从而消耗大量的计算能力和能量。相比之下，基于事件触发尖峰的生物数据处理具有更高的效率和更低的能耗。在这里，这项工作提出了一种由尖峰光电探测器和人工突触组成的人工视觉架构，密切反映了人类视觉系统的复杂性。与之前报道的技术不同，该光电探测器是自供电和事件触发的，直接输出光调制尖峰信号，从而满足低功耗始终开启的要求。通过集成突触单元进行尖峰信号处理，实现了图形、手势和人类动作的识别，展示了该架构固有的强大图像处理能力。结果证明，利用基本的人工神经网络，在短短 5 个周期内，人类动作识别的准确率就达到了 90%。这种新颖的架构以尖峰光电探测器为基础，为现有的始终在线的低功耗人工视觉系统模型提供了可行的替代方案。

"点击查看英文标题和摘要"

A Spiking Artificial Vision Architecture Based on Fully Emulating the Human Vision

Intelligent vision necessitates the deployment of detectors that are always-on and low-power, mirroring the continuous and uninterrupted responsiveness characteristic of human vision. Nonetheless, contemporary artificial vision systems attain this goal by the continuous processing of massive image frames and executing intricate algorithms, thereby expending substantial computational power and energy. In contrast, biological data processing, based on event-triggered spiking, has higher efficiency and lower energy consumption. Here, this work proposes an artificial vision architecture consisting of spiking photodetectors and artificial synapses, closely mirroring the intricacies of the human visual system. Distinct from previously reported techniques, the photodetector is self-powered and event-triggered, outputting light-modulated spiking signals directly, thereby fulfilling the imperative for always-on with low-power consumption. With the spiking signals processing through the integrated synapse units, recognition of graphics, gestures, and human action has been implemented, illustrating the potent image processing capabilities inherent within this architecture. The results prove the 90% accuracy rate in human action recognition within a mere five epochs utilizing a rudimentary artificial neural network. This novel architecture, grounded in spiking photodetectors, offers a viable alternative to the extant models of always-on low-power artificial vision system.

更新日期：2024-02-06

点击分享查看原文

点击收藏

阅读更多本刊新发论文本刊介绍/投稿指南