视频监控行人流量统计系统的设计

doi:10.16180/j.cnki.issn1007-7820.2019.12.010

电子科技 ›› 2019, Vol. 32 ›› Issue (12): 48-52.doi: 10.16180/j.cnki.issn1007-7820.2019.12.010

视频监控行人流量统计系统的设计

殷涛,崔佳冬

杭州电子科技大学新型电子器件与用研究所,浙江杭州 310018

收稿日期:2018-12-16 出版日期:2019-12-15 发布日期:2019-12-24
作者简介:殷涛(1994-),男,硕士研究生。研究方向:数字图像处理。|崔佳冬(1974-),男,副教授。研究方向:嵌入式系统及物联网应用。
基金资助:
国家自然科学基金国际（地区）合作与交流资助项目(61411136003)

Designof Pedestrian Flow Statistics System on Video Monitoring

YIN Tao,CUI Jiadong

Institute of Electron Devices & Application,Hangzhou Dianzi University,Hangzhou 310000,China

Received:2018-12-16 Online:2019-12-15 Published:2019-12-24
Supported by:
National Natural Science Foundation International (Regional) Cooperation and Exchange Funding Project(61411136003)

摘要/Abstract

摘要：

针对当前行人统计方式落后、非实时性、统计数据滞后等问题,文中提出采用智能视频监控、图像识别的方式实时统计行人流量。系统根据积分通道思想统计行人目标特征,通过Adaboost算法训练分类器对图像帧中的行人目标进行定位、识别。文中在已识别目标的基础上采用CPU多任务模型改进核相关滤波算法对目标进行实时跟踪、统计得到行人流量。测试结果表明,系统能实时识别、跟踪、统计行人目标,整体功能稳定,平均识别率为93%,改进多任务模型使得跟踪速率提高约20%。

关键词: 人流量统计, 实时监控, 积分通道特征, 核相关滤波, 多任务跟踪, Adaboost算法

Abstract:

Aiming at the problems of backward pedestrian statistics, non-real-time and backward statistical data, intelligent video surveillance and image recognition were proposed for real-time pedestrian traffic statistics. The system calculated the pedestrian target characteristics according to the integral channel idea, and used the Adaboost algorithm to train the classifier to locate and identify the pedestrian target in the image frame. Based on the identified targets, the CPU multi-task model was used to improve the kernel correlation filtering algorithm to track the target in real time and obtain the pedestrian traffic. The test results showed that the system can recognize, track and count pedestrian targets in real time. The average recognition rate was 93%, and the improved multi-task model increased the tracking rate by about 20%.

Key words: pedestrian flow statistics, real-time monitoring, integral channel features, kernel correlation filtering, multi-task tracking, Adaboost algorithm

中图分类号:

TP311

殷涛,崔佳冬. 视频监控行人流量统计系统的设计[J]. 电子科技, 2019, 32(12): 48-52.

YIN Tao,CUI Jiadong. Designof Pedestrian Flow Statistics System on Video Monitoring[J]. Electronic Science and Technology, 2019, 32(12): 48-52.

图/表 11

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

表1

参考文献 16

[1]	王瑞 . 基于机器视觉的人流量双向统计技术研究[D]. 西安:西北大学, 2013.
	Wang Rui . Research on two-way statistical technology of human flow based on machine vision[D]. Xi’an:Northwest University, 2013.
[2]	屈鉴铭 . 智能视频监控中的运动目标检测与跟踪技术研究[D]. 西安:西安电子科技大学, 2015.
	Qu Jianming . Research on moving object detection and tracking technology in intelligent video surveillance[D]. Xi’an:Xidian University, 2015.
[3]	白平平 . 智能视频监控中行人的检测与跟踪方法研究[D]. 北京:北京交通大学, 2017.
	Bai Pingping . Pedestrian detection and tracking in intelligent video surveillance[D]. Beijing:Beijing Jiaotong University, 2017.
[4]	闫婷 . 基于图像处理的公交乘客流量统计系统的研究[D]. 呼和浩特:内蒙古大学, 2016.
	Yan Ting . Research on bus passenger flow statistics system based on image processing[D]. Hohhot:Inner Mongolia University, 2016.
[5]	毛星云 . Open CV3编程入门[M]. 北京: 电子工业出版社, 2015.
	Mao Xingyun. Introduction to Open CV3 programming[M]. Beijing: Electronic Industry Press, 2015.
[6]	马纯 . 动态背景下的行人检测与跟踪研究[D]. 南京:南京邮电大学, 2016.
	Ma Chun . Pedestrian detection and tracking under dynamic background[D]. Nanjing:Nanjing University of Posts and Telecommunications, 2016.
[7]	Zini L, Noceti N, Odone F . Precise people counting in real time [C].Melbourne:IEEE International Conference on Image Processing,IEEE, 2014.
[8]	程栗 . 基于视频监控的人流量统计系统研究[D]. 绵阳:西南科技大学, 2015.
	Cheng Li . Research on video-based traffic statistics system[D]. Mianyang:Southwest University of Science and Technology, 2015.
[9]	査宇锋 . 基于HOG和SVM的公交客流量统计技术研究[D]. 合肥:安徽大学, 2015.
	Zha Yufeng . Research on statistical technology of bus passenger flow based on HOG and SVM[D]. Hehui: Anhui University, 2015.
[10]	Dollár P, Wojek C, Schiele B , et al. Pedestrian detection: an evaluation of the state of the art[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2012,34(4):743-761. doi: 10.1186/1756-0500-5-610 pmid: 23116330
[11]	王盼盼, 李玉惠 . 基于特征融合和L-M算法的车辆重识别方法[J]. 电子科技, 2018,31(4):12-15.
	Wang Panpan, Li Yuhui . Vehicle recognition method based on feature fusion and L-M algorithm[J]. Electronic Science and Technology, 2018,31(4):12-15.
[12]	彭志勇 . 智能视频监控系统中的行人重识别方法研究[D]. 济南:山东大学, 2016.
	Peng Zhiyong . Pedestrian recognition in intelligent video surveillance system[D]. Jinan:Shandong University, 2016.
[13]	Henriques J F, Caseiro R, Martins P , et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015,37(3):583-596. doi: 10.1109/TPAMI.2014.2345390 pmid: 26353263
[14]	张英 . 基于视频的实时人数统计关键技术的研究[D]. 杭州:杭州电子科技大学, 2014.
	Zhang Ying . Research on key technologies of video-based real-time number statistics[D]. Hangzhou:Hangzhou Dianzi University, 2014.
[15]	程伟 . 智能视频监控系统中运动目标检测与跟踪的研究与实现[D]. 镇江:江苏科技大学, 2016.
	Cheng Wei . Research and implementation of moving object detection and tracking in intelligent video surveillance system[D]. Zhengjiang:Jiangsu University of Science and Technology, 2016.
[16]	聂义 . 智能视频监控中单目标运动的检测与跟踪算法研究[D]. 长沙:湖南师范大学, 2016.
	Nie Yi . Research on single target motion detection and tracking algorithm in intelligent video surveillance[D]. Changsha:Hunan Normal University, 2016.

处理器CPU	GPU	帧耗时/ms	测试人数	检测人数	正确率
Inteli5-7500(台)	GT730	24	76	69	90.7%
Inteli5-3500(笔记本)	GT630	36	45	43	95.6%

视频监控行人流量统计系统的设计

Designof Pedestrian Flow Statistics System on Video Monitoring

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 16

相关文章 10

Metrics

本文评价

推荐阅读 7

[1]	杨思燕,苗凯彬,王锋,苗启广. 视频图像中人脸自动检测与统计算法[J]. 电子科技, 2020, 33(8): 1-9.
[2]	汪欣,吴薇,曾照. 基于视频的人脸检测算法研究[J]. 电子科技, 2020, 33(2): 25-31.
[3]	于世强，应捷. 基于Android平台的实时人脸检测与跟踪[J]. , 2016, 29(7): 78-.
[4]	王毅,王创新,卢进,盛文正. 基于HSV模型和改进AdaBoost算法的车牌检测[J]. , 2015, 28(2): 107-.
[5]	赵喆,侯俊. 基于肤色模型和改进Adaboost算法的人脸检测[J]. , 2015, 28(12): 80-.
[6]	张超,仲梁维,陈彩凤. 基于Web的车间实时监控管理系统设计与实现[J]. , 2015, 28(11): 120-.
[7]	巨志勇,黄凯. 基于共生概率特征量的行人检测[J]. , 2015, 28(11): 139-.
[8]	王寅. 基于LARK特征提取的AdaBoost人脸检测系统[J]. , 2014, 27(7): 137-.
[9]	王锋涛. 基于NiosⅡ的人脸检测系统设计[J]. , 2013, 26(3): 102-.
[10]	位闯, 黄林. 水产养殖环境因子监控系统[J]. , 2010, 23(5): 29-.