首页 | 本学科首页   官方微博 | 高级检索  
     

基于AdaBoost算法的人脸检测在嵌入式系统中的实现
引用本文:李先锋,花小朋,赵峰,孔令东. 基于AdaBoost算法的人脸检测在嵌入式系统中的实现[J]. 计算机与现代化, 2010, 0(8): 143-146. DOI: 10.3969/j.issn.1006-2475.2010.08.040
作者姓名:李先锋  花小朋  赵峰  孔令东
作者单位:1. 盐城工学院信息工程学院,江苏,盐城,224051
2. 上海交通大学微电子学院,上海,200240
摘    要:为解决人脸检测实时性问题,针对AdaBoost算法纯软件实现的瓶颈,提出基于FPGA平台的硬件加速策略,采用流水线处理技术实现积分图像的快速计算。实验使用PowerPC405处理器VirtexTM-Ⅱ Pro平台FPGA,在输入图像大小为352×288像素的条件下,检测速度达到每秒50帧,检测率为98%,误检率约1%,实现了实时人脸检测的要求。

关 键 词:人脸检测  AdaBoost算法  硬件加速  现场可编程门阵列

Implementation of Face Detection Based on AdaBoost Algorithm in Embedded System
LI Xian-feng,HUA Xiao-peng,ZHAO Feng,KONG Ling-dong. Implementation of Face Detection Based on AdaBoost Algorithm in Embedded System[J]. Computer and Modernization, 2010, 0(8): 143-146. DOI: 10.3969/j.issn.1006-2475.2010.08.040
Authors:LI Xian-feng  HUA Xiao-peng  ZHAO Feng  KONG Ling-dong
Affiliation:1.School of Information Engineering,Yancheng Institute of Technolog,Yancheng 224051,China;2.School of Microelectronics,Shanghai Jiaotong University,Shanghai 200240,China)
Abstract:To solve the technical problem of real-time face detection and break through the bottleneck of AdaBoost algorithm,a hardware acceleration strategy based on FPGA is used to calculate the integral squared image by pipeline architecture.The system can detect a face in 352×288 image at a speed of 50 fps on PowerPC405 VirtexTM-Ⅱ Pro FPGA platform,and achieve a detection rate of 98% with a false alarm rate of 1%,so it can meet the requirements of real-time face detection.
Keywords:face detection  AdaBoost algorithm  hardware acceleration  Field-Programmable Gate Array(FPGA)
本文献已被 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号