ZedBoard开发平台的实时人脸检测系统设计  

Design of Real-time Face Detection System Based on ZedBoard

作　　者：周泽明 王喜斌 徐圆飞[2] 王英喆 王帅帅 Zhou Zeming;Wang Xibin;Xu Yuanfei;Wang Yingzhe;Wang Shuaishuai(School of Electronic and Control Engineering,North China Institute of Aerospace Engineering,Langfang 065000,China;Bejing Hangxing Technology Development Co.,Ltd.)

机构地区：[1]北华航天工业学院电子与控制工程学院,廊坊065000 [2]北京航星机器制造有限公司

出　　处：《单片机与嵌入式系统应用》2019年第8期53-56,共4页Microcontrollers & Embedded Systems

摘　　要：采用Xilinx公司以FPGA+ARM为核心处理器的ZedBoard全可编程SoC开发平台,使用Vivado为嵌入式系统加速配置硬件外设,灵活运用PetaLinux为该处理器定制、构建和调配嵌入式系统所需的组件。利用FPGA并行处理的特性对采集的图像进行灰度化和滤波处理,并通过AXI_HP总线将处理后的数据传回到DDR3中,在ARM中读取DDR3中的数据并采用Viola-Jones人脸检测算法完成实时人脸检测系统设计。In the paper,Xilinx ZedBoard all programmable SoC development platform with FPGA+ARM is used as the core processor,Vivado is used to accelerate the configuration of hardware peripherals for embedded systems,and PetaLinux is used to customize,build and provision components for embedded systems.The acquired image is grayed and filtered by the characteristics of FPGA parallel processing and the processed data is transferred back to DDR3 through AXI_HP bus.The data in DDR3 is read in ARM and Viola-Jones face detection algorithm is used to complete the design of the real-time face detection system.

关 键 词：人脸检测 嵌入式系统 ZedBoard PetaLinux FPGA 

分 类 号：TN402[电子电信—微电子学与固体电子学]