面向SPAD图像传感器的超高速目标定位处理器  

An Ultra High-speed Object Location Processor for SPAD Spike Image Sensors

作　　者：姚春赫 杨旭 赵明心 刘剑[1,2] 吴南健 刘力源[1,2] YAO Chunhe;YANG Xu;ZHAO Mingxin;LIU Jian;WU Nanjian;LIU Liyuan(State Key Laboratory of Superlattices and Microstructures,Institute of Semiconductors,Chinese Academy of Sciences,Beijing,100083 China;Center of Materials Science and Optoelectronics Engineering,University of Chinese Academy of Sciences,Beijing,100049 China;Center for Excellence in Brain Science and Intelligence Technology,Chinese Academy of Sciences,Beijing,100083 China)

机构地区：[1]中国科学院半导体研究所半导体超晶格国家重点实验室,北京100083 [2]中国科学院大学材料与光电研究中心,北京100049 [3]中国科学院脑科学与智能技术卓越创新中心,北京100083

出　　处：《光子学报》2022年第11期285-295,共11页Acta Photonica Sinica

基　　金：国家重点研究发展计划(No.2019YFB2204303);国家自然科学基金(Nos.U20A20205,U21A20504);中国科学院先导专项(No.XDB32050200);中国科学院先导专项培育项目课题(No.XDPB22);中国科学院青年创新促进会(No.2021109)。

摘　　要：提出了一种用于单光子雪崩二极管图像传感器的超高速目标定位处理器。它由一个处理阵列,一个Y特征向量生成器和一个位置计算器组成,能够进行噪声减除和目标定位处理。设计了一种省略了乘法和减法运算的高斯滤波和背景减除法,降低了计算复杂度和硬件资源消耗,并显著地提高了处理速度。整个处理器在FPGA开发板上实现,实验结果表明,该处理器能够以100 000帧/s的速度实时处理128×128分辨率的脉冲图像,并定位其中的运动物体。本文提出的处理器架构同样可用于其他脉冲图像传感器。Ultra high-speed object location has potential prospects in civilian and scientific applications.However,the conventional image sensor has a bottleneck that can not achieve continuous ultra high-speed imaging.The Single-Photon Avalanche Diode(SPAD) image sensor,as a new type of spike image sensor,can realize continuous ultra high-speed imaging to support high-speed moving object location.The background subtraction method is a simple and effective high-speed location method,but the image noise caused by the SPAD image sensor will seriously interfere with the processing effect of the background subtraction method.Therefore,denoise processing is required before locating.This paper proposes an ultra high-speed object location processor for SPAD image sensors.It consists of a Processing Element(PE)array,a Y-feature generator,and a position calculator,and is capable of denoising and object location processing.The SPAD image sensor adopts row rolling exposure to produce N pixel output of one row at once exposure.The output format of the SPAD image sensor is a single-bit spike image containing only “1” and “0”.The processing array contains N processing units,each PE unit contains 9 ALUs,which equals the size of filtering window 3×3,for processing Gaussian filtering and background subtraction methods with the current and earliest frames of spiking image data accessed from its two adjacent PEs.The current frame data,the earliest frame data,and the convolution kernel are calculated by complement logic and XOR gate in each ALU of the PE,and then the ALU results and the data in the memory are accumulated to obtain the filtering result.The object location module outputs a row of X feature vector and a column of Y feature vector at the end of each frame.The position calculator compares the feature vector with their thresholds and outputs the coordinate position of the object.We propose the Gaussian filtering and background subtraction method to remove the multiplication and subtraction operations,which reduces the comp

关 键 词：目标定位 现场可编程 单光子雪崩二极管 背景减除 高斯滤波 

分 类 号：TN492[电子电信—微电子学与固体电子学]