广西师范大学学报(自然科学版) ›› 2019, Vol. 37 ›› Issue (4): 61-67.doi: 10.16088/j.issn.1001-6600.2019.04.007

• • 上一篇    下一篇

基于多特征的快速行人检测方法及实现

肖逸群, 宋树祥*, 夏海英   

  1. 广西师范大学电子工程学院,广西桂林541004
  • 收稿日期:2018-09-06 出版日期:2019-10-25 发布日期:2019-11-28
  • 通讯作者: 宋树祥(1970—),男,湖南双峰人,广西师范大学教授,博士。E-mail: songshuxiang@mailbox.gxnu.edu.cn
  • 基金资助:
    国家自然科学基金(61762014)

Fast Pedestrian Detection Method Based on Multi-Features    and Implementation

XIAO Yiqun, SONG Shuxiang*, XIA Haiying   

  1. College of Electronic Engineering, Guangxi Normal University, Guilin Guangxi 541004, China
  • Received:2018-09-06 Online:2019-10-25 Published:2019-11-28

摘要: 针对行人检测速度与实际应用问题,本文提出一种多特征的快速行人检测方法并应用于视频监控系统中。首先通过混合高斯建模,提取图像有效的运动区域,使得检测面积缩小;接着,将提取出的图像进行边缘处理,对HOG特征与LBP特征进行融合,使用支持向量机(SVM)训练分类器;最后在Hi3516A开发板上实现行人检测算法,实现实时监控检测。本文分别在PC端和开发板上进行实验,结果表明本文方法有效地提高了速度,达到了实时行人检测要求,且系统运行稳定,可用于实际监控中。

关键词: 行人检测, 混合高斯建模, HOG, LBP, 视频监控

Abstract: Aimed at the pedestrian detection speed and related practical application problems, a fast multi-feature pedestrian detection method is proposed and applied to video monitoring system in this paper. Firstly, the Gaussian modeling is used to extract the effective motion region of the image, so that the detection area is reduced. Then, the extracted image is edge-processed, the HOG feature is merged with the LBP feature, and the classifier is trained using the support vector machine (SVM). Finally the pedestrian detection algorithm on the Hi3516A development board is conducted to monitor and detect in real time. Experiments are carried out on the PC side and the development board respectively. It is show that the method effectively improves the speed and achieves the real-time pedestrian detection requirements. The system runs stably and can be used in actual monitoring.

Key words: pedestrian detection, mixed Gaussian modeling, HOG, LBP, video surveillance

中图分类号: 

  • TP391.41
[1] HONG Xiaopeng,ZHAO Guoying,PIETIKÄINEN M,et al.Combining LBP difference and feature correlation for texture description[J]. IEEE Transactions on Image Processing,2014,23(6):2557-2568.DOI:10.1109/TIP.2014.2316640.
[2] ZENG Chengbin,MA Huadong.Robust head-shoulder detection by PCA-based multilevel HOG-LBP detector for people counting[C]//Proceedings of the 2010 20th International Conference on Pattern Recognition. Los Alamitos,CA:IEEE Computer Society,2010:2069-2072.DOI:10.1109/ICPR.2010.509.
[3] FAN Guojuan,LI Bo,MU Wanquan,et al.HOGG: Gabor and HOG-based human detection[C]//Proceedings of 2016 8th International Conference on Information Technology in Medicine and Education.Los Alamitos,CA:IEEE Computer Society,2016:562-566.DOI:10.1109/ITME.2016.0133.
[4] JI Luping,REN Yan,LIU Guisong,et al.Training-based gradient LBP feature models for multiresolution texture classification[J].IEEE Transactions on Cybernetics,2018,48(9):2683-2696.DOI:10.1109/TCYB. 2017.2748500.
[5] ZHAO Lihong,LIU Fei,WANG Yongjun.Face recognition based on LBP and genetic algorithm [C]//Proceedings of the 28th Chinese Control and Decision Conference.Singapore:IEEE Industrial Electronics Chapter, 2016:1582-1587.DOI:10.1109/CCDC.2016.7531236.
[6] 程德强,唐世轩,冯晨晨,等.改进的HOG-CLBC的行人检测方法[J].光电工程,2018,45(8):180111.DOI:10.12086/ oee.2018.180111
[7] GIRSHICK R.Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision.Los Alamitos,CA:IEEE Computer Society,2015:1440-1448.DOI:10.1109/ICCV.2015.169.
[8] SUN Deqing,ROTH S,BLACK M J.Secrets of optical flow estimation and their principles[C]//Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Los Alamitos,CA: IEEE Computer Society,2010:2432-2439.DOI:10.1109/CVPR.2010.5539939.
[9] 杨恒,王超,姜文涛,等.基于随机背景建模的目标检测算法[J].应用光学,2015,36(6):880-887.DOI:10.5768/ JAO201536.0602001.
[10]黄大卫,胡文翔,吴小培,等.改进单高斯模型的视频前景提取与破碎目标合并算法[J].信号处理,2015,31(3): 299-307.DOI:10.3969/j.issn.1003-0530.2015.03.007.
[11]DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Los Alamitos,CA:IEEE Computer Society,2005:886-893.DOI:10.1109/CVPR.2005.177.
[12]GAO Wenshuo,ZHANG Xiaoguang,YANG Lei,et al.An improved sobel edge detection operator[C]//Proceedings of 2010 3rd International Conference on Computer Science and Information Technology.Piscateway, NJ:IEEE Press,2010:67-71.DOI:10.1109/ICCSIT.2010.5563693.
[13]袁宝华,王欢,任明武.基于完整LBP特征的人脸识别[J].计算机应用研究,2012,29(4):1557-1559.DOI: 10.3969/j.issn.1001-3695.2012.04.099.
[14]WU Jianxin,REHG J M.CENTRIST:a visual descriptor for scene categorization[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2011,33(8):1489-1501.DOI:10.1109/TPAMI.2010.224.
[15]陈义,马云林.基于视觉的手势识别技术在车载主机上的应用[J].电子设计工程,2016,24(8):141-144.DOI: 10.14022/j.cnki.dzsjgc.2016.08.040.
[16]何群山.基于ARM的嵌入式视频监控系统设计[D].淮南:安徽理工大学,2016.
[17]郑阳.基于Hi3516A处理器的KVM终端软件设计[D].杭州:浙江工业大学,2016.
[18]深圳市海思半导体有限公司.HiMPP V3.0媒体处理软件开发参考[M].深圳:深圳市海思半导体有限公司,2013.
[1] 夏海英, 喻潇琪. 基于对比度金字塔图像融合的自发笑脸识别[J]. 广西师范大学学报(自然科学版), 2017, 35(3): 45-52.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 孟春梅, 陆世银, 梁永红, 莫肖敏, 李卫东, 黄远洁, 成晓静, 苏志恒, 郑华. 岩黄连总碱诱导肝星状细胞凋亡和自噬的电镜实验研究[J]. 广西师范大学学报(自然科学版), 2018, 36(3): 76 -79 .
[2] 林永生, 裴建国, 邹胜章, 杜毓超, 卢丽. 清江下游红层岩溶及其水化学特征[J]. 广西师范大学学报(自然科学版), 2018, 36(3): 113 -120 .
[3] 李贤江, 石淑芹, 蔡为民, 曹玉青. 基于CA-Markov模型的天津滨海新区土地利用变化模拟[J]. 广西师范大学学报(自然科学版), 2018, 36(3): 133 -143 .
[4] 刘国伦, 宋树祥, 岑明灿, 李桂琴, 谢丽娜. 带宽可调带阻滤波器的设计[J]. 广西师范大学学报(自然科学版), 2018, 36(3): 1 -8 .
[5] 滕志军, 吕金玲, 郭力文, 许媛媛. 基于改进粒子群算法的无线传感器网络覆盖策略[J]. 广西师范大学学报(自然科学版), 2018, 36(3): 9 -16 .
[6] 刘铭, 张双全, 何禹德. 基于改进SOM神经网络的异网电信用户细分研究[J]. 广西师范大学学报(自然科学版), 2018, 36(3): 17 -24 .
[7] 苗新艳, 张龙, 罗颜涛, 潘丽君. 一类交替变化的竞争—合作混杂种群模型研究[J]. 广西师范大学学报(自然科学版), 2018, 36(3): 25 -31 .
[8] 黄荣里, 李长友, 汪敏庆. 一类常微分方程的伯恩斯坦定理Ⅱ[J]. 广西师范大学学报(自然科学版), 2018, 36(3): 50 -55 .
[9] 温玉卓, 唐胜达, 邓国和. 随机环境下具有阈值分红策略的风险过程的破产时间分析[J]. 广西师范大学学报(自然科学版), 2018, 36(3): 56 -62 .
[10] 冯修, 马楠楠, 职红涛, 韩双乔, 张翔. 重金属捕集剂UDTC对低浓度镉废水的处理研究[J]. 广西师范大学学报(自然科学版), 2018, 36(3): 63 -67 .
版权所有 © 广西师范大学学报(自然科学版)编辑部
地址:广西桂林市三里店育才路15号 邮编:541004
电话:0773-5857325 E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发