摘要
人工智能视觉芯片是一种以人类视觉系统为仿生学基础的半导体芯片。人工智能芯片集成了图像传感器和智能化处理器,既能够传感视觉图像信息,也能够实施处理信息。回顾了人工智能视觉芯片的发展历史,详细叙述了其架构演进的历程。图像传感器和处理器分离的可编程视觉芯片是目前的重点研究方向。未来,视觉芯片还将向三维集成的方向发展,以获得更高的处理性能。
Artificial intelligent vision chip is based on the bionics of the human vision systems.On the vision chip,image sensor and imaging processors are integrated together.The vision chip can not only capture image data but can also understand the information in the image.The progress of study on vision chip is reviewed,and various vision chip architectures are discussed in detail.Nowadays,image sensor and processor-separated programmable vision chip are the key research direction currently.In the future,3-D integration will help vision chip achieving higher performance.
作者
刘力源
吴南健
LIU Liyuan;WU Nanjian(Institute of Semiconductors,Chinese Academy of Sciences,Beijing 100083,China;University of Chinese Academy of Sciences,Beijing 100049,China)
出处
《微纳电子与智能制造》
2019年第2期12-19,共8页
Micro/nano Electronics and Intelligent Manufacturing
基金
北京市重点研发计划(Z181100008918009)项目资助.
关键词
视觉芯片
人工智能
图像传感器
图像处理器
三维集成
vision chip
artificial intelligence
image sensor
image processor
3D integration