计算机工程

• 软件技术与数据库 • 上一篇    下一篇

结合SVM分类器与HOG特征提取的行人检测

徐渊  1,许晓亮  1,李才年  1,姜梅  1,张建国  2   

  1. (1.深圳大学信息工程学院,广东 深圳 518060; 2.深圳市振华微电子有限公司,广东 深圳 518060)
  • 收稿日期:2015-01-08 出版日期:2016-01-15 发布日期:2016-01-15
  • 作者简介:徐渊(1978-),男,讲师、博士,主研方向为集成电路设计、数字系统设计;许晓亮、李才年,硕士研究生;姜梅,讲师、博士;张建国,工程师。
  • 基金项目:
    深圳市战略新兴产业发展专项基金资助项目“神经形态学视觉芯片模型研究及仿真”(JCYJ20140418095735603)。

Pedestrian Detection Combining with SVM Classifier and HOG Feature Extraction

XU Yuan  1,XU Xiaoliang  1,LI Cainian  1,JIANG Mei  1,ZHANG Jianguo  2   

  1. (1.College of Information Engineering,Shenzhen University,Shenzhen,Guangdong 518060,China; 2.Shenzhen Zhenhua Microelectronics Co.,Ltd.,Shenzhen,Guangdong 518060,China)
  • Received:2015-01-08 Online:2016-01-15 Published:2016-01-15

摘要: 针对基于方向梯度直方图(HOG)的行人检测方案存在运算量大、实时性差的问题,设计一个内嵌支持向量机(SVM)分类器的HOG特征提取归一化模块,并将其应用于行人检测。提出两级流水线架构,第1级采用16×16像素块扫描,并结合查找表的方式生成HOG,以减少乘法器资源 消耗量,第2级将15路并行SVM内嵌到HOG归一化模块中,通过提前启动SVM降低15路SVM乘累加器的位宽。利用面向硬件实现的自动消除检测重复性算法,进一步提高检测准确性。实验结果表明,该方案能够以100 MHz时钟频率运行在Spartan6 FPGA芯片上,每秒可处理47帧SVGA (800×600)分辨率的图像,具有较高的行人检测实时性和准确率。

关键词: 现场可编程门阵列, 流水线, 查找表, 方向梯度直方图, 支持向量机

Abstract: Aiming at the problem that pedestrian detection scheme based on Histogram of Oriented Gradient(HOG) has large computation and poor real-time,this paper designs a HOG feature extraction normalized module embedded Support Vector Machine (SVM) classifier,and applies it to pedestrian detection.It proposes a two-stage pipeline architecture.On the first level,it uses 16×16 pixel scanning,simplifies the histogram generation with Look-up Table(LUT),and it can reduce resources consumption of multiplier.On the second level,the 15-way parallel SVM is embedded itself in the HOG normalization module,and it can reduce bit of 15-way parallel SVM multiply-accumulator through pre-start SVM.Also,an algorithm is proposed to automatically reduce duplicated detection to improve detection accuracy.The scheme is verified for SVGA resolution video(800×600) at 47 frames on Spartan6 Field Programmable Gate Array(FPGA) with 100 MHz and it improves the real-time and accuracy of pedestrian detection.

Key words: Field Programmable Gate Array(FPGA), pipeline, Look-up Table(LUT), Histogram of Oriented Gradient(HOG), Support Vector Machine(SVM)

中图分类号: