基于车载视频监控的乘客检测及跟踪算法

计算机应用 ›› 2014, Vol. 34 ›› Issue (12): 3521-3525.

基于车载视频监控的乘客检测及跟踪算法

谢璐¹,金志刚¹,王颖¹,²

1. 天津大学电子信息工程学院,天津 300072
2. 61660部队，北京 100089

收稿日期:2014-06-30 修回日期:2014-08-12 发布日期:2014-12-31 出版日期:2014-12-01
通讯作者: 谢璐
作者简介:谢璐(1989-）,女,河北石家庄人,硕士研究生,主要研究方向:车载视频监控、图像处理；金志刚(1972-）,男,上海人,教授,博士生导师,博士,主要研究方向:无线与水下网络协议、无线网络安全、网络视频技术；王颖(1977-）,女,河北张家口人,博士,主要研究方向:网络安全、信息保密。
基金资助:
国家自然科学基金资助项目;天津市软件产业发展专项基金资助项目

Passenger detection and tracking algorithm based on vehicle video surveillance

XIE Lu¹,JIN Zhigang¹,WANG Ying¹,²

1. School of Electronic and Information Engineering, Tianjin University, Tianjin 300072, China;
2. Unit 61660, Beijing 100089, China

Received:2014-06-30 Revised:2014-08-12 Online:2014-12-31 Published:2014-12-01
Contact: XIE Lu

摘要/Abstract

摘要：

针对公交车上乘客相互遮挡及光照变化明显的问题,提出一种基于头肩部边缘特征和局部不变特征的人体检测及跟踪算法。首先对待检测图像进行自适应阈值背景差分,实现乘客目标分割；然后用样本的梯度方向直方图(HOG)特征训练支持向量机(SVM)基础分类器,结合自适应增强(AdaBoost)算法提炼出最终的强分类器,对前景图像进行扫描实现乘客目标检测；最后提取目标区域和当前搜索区域的快速鲁棒性特征(SURF),通过特征点匹配实现乘客目标跟踪。实验表明,在乘客相互遮挡及光照变化明显的情况下,该算法仍具有高于80%的检测率和跟踪率,且满足系统实时性的要求,可用于客流计数。

Abstract:

Concerning the problem of barrier among passengers and unstable illumination on the bus, a detection and tracking algorithm was proposed based on edge feature and local invariant feature of head-shoulder. Firstly, the algorithm used adaptive threshold background subtraction method to achieve passenger segmentation. Secondly, it used Histogram of Oriented Gradient (HOG) feature of different sample sets to train Support Vector Machine (SVM) classifiers, and combined Adaptive Boosting (AdaBoost) algorithm to extract a strong classifier. And then it scanned the foreground using strong classifier to achieve passenger detection. Lastly, it extracted Speeded-Up Robust Feature (SURF) of target region and current search region, and then matched feature points to achieve passenger tracking. The experimental results show that this algorithm has detection rate and tracking rate of more than 80% in the case of barrier among passengers and unstable illumination, and it can meet the requirement of real-time. It can be used for passenger flow counting.

中图分类号:

TP391.4

谢璐金志刚王颖. 基于车载视频监控的乘客检测及跟踪算法[J]. 计算机应用, 2014, 34(12): 3521-3525.

XIE Lu JIN Zhigang WANG Ying. Passenger detection and tracking algorithm based on vehicle video surveillance[J]. Journal of Computer Applications, 2014, 34(12): 3521-3525.

参考文献

［1］HUA Y, LIU W. Moving object detection algorithm of improved Gaussian mixture model ［J］. Journal of Computer Applications, 2014, 34(2): 580-584. (华媛蕾, 刘万军. 改进混合高斯模型的运动目标检测算法［J］. 计算机应用, 2014, 34(2): 580-584.)
［2］ZHENG G, CHEN Y. A review on vision-based pedestrian detection ［C］// Proceedings of the 2012 IEEE Global High Tech Congress on Electronics. Piscataway: IEEE, 2012:49-54.
［3］YANG H, SHAO L, ZHENG F, et al. Recent advances and trends in visual tracking: a review ［J］. Neurocomputing, 2011, 74(18): 3823-3831.
［4］AGRAWAL D, MEENA N. Performance comparison of moving object detection techniques in video surveillance system［J］. The International Journal of Engineering and Science, 2013, 2(1): 240-242.
［5］WANG C, WATADA J. Robust color image segmentation by Karhunen-Loeve transform based Otsu multi-thresholding and K-means clustering ［C］// Proceedings of the 5th International Conference on Genetic and Evolutionary Computing. Piscataway: IEEE, 2011: 377-380.
［6］SAHOO A K, PATNAIK S, BISWAL P K, et al. An efficient algorithm for human tracking in visual surveillance system［C］// Proceedings of the 2013 IEEE Second International Conference on Image Information Processing. Piscataway: IEEE, 2013: 125-130.
［7］ZHU R, WANG Y. Application of improved median filter on image processing［J］. Journal of Computers, 2012, 7(4): 838-841.
［8］LI H, XUE Y, HUANG X. Improved object detection method of adaptive Gaussian mixture model ［J］. Journal of Computer Applications, 2013, 33(9): 2610-2613. (李鸿生, 薛月菊, 黄晓琳, 等. 改进的自适应混合高斯前景检测方法［J］. 计算机应用, 2013, 33(9): 2610-2613.)
［9］LI Z, LI Q. Object classification based on discriminable features and continuous tracking ［J］. Journal of Computer Applications, 2014, 34(5): 1275-1278. (李志华, 李秋峦. 连续跟踪状态下基于可分性特征的目标优化分类［J］. 计算机应用,2014, 34(5): 1275-1278.)
［10］RUAN J, YIN J. Multi-pose detection based on facial features and AdaBoost algorithm ［J］. Journal of Computer Applications, 2010, 30(4): 967-970. (阮锦新, 尹俊勋. 基于人脸特征和AdaBoost算法的多姿态人脸检测［J］. 计算机应用, 2010, 30(4): 967-970.)
［11］TU J, ZHANG C, HAO P. Robust real-time attention-based head-shoulder detection for video surveillance［C］// Proceedings of the 20th IEEE International Conference on Image Processing. Piscataway: IEEE, 2013: 3340-3344.
［12］YANG J, LI R, HUANG C, et al. Fast image registration algorithm based on locally significant edge feature［J］. Journal of Computer Applications, 2014, 34(1): 149-153. (杨健, 李若楠, 黄晨阳, 等. 基于局部显著边缘特征的快速图像配准算法［J］. 计算机应用, 2014, 34(1): 149-153.)
［13］ZHOU D, HU D. A robust object tracking algorithm based on SURF［C］// Proceedings of the 2013 International Conference on Wireless Communications and Signal Processing. Piscataway: IEEE, 2013: 1-5.
［14］ZHAO M. Study on multi-pedestrian detection and tracking technology with monocular vision ［D］. Chongqing: Chongqing University, 2010. (赵敏. 单目视觉多行人目标检测与跟踪技术研究［D］. 重庆: 重庆大学, 2010.)

[1]	张佳慧李晓明张嘉祥. 强化形态感知的路面缺陷检测算法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[2]	杨建锋陈斌李雨轩. 基于点云重构的自监督点云异常检测方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[3]	蒋畅江向杰何旭颖. 面向机械臂抓取的双目视觉目标定位算法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[4]	边小勇胡其仁袁培洋. 多注意力对比学习的红外小目标检测[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[5]	李钟华钟庚辛范萍朱恒亮. 通过边界挖掘和背景引导的伪装目标检测[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[6]	吴松霖张广朝姚远彭博. 基于判别区域引导的多视图困难气道识别[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[7]	李强白少雄熊源袁薇. 基于视觉大模型隐私保护的监控图像定位[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[8]	况世雄姚俊波陆佳炜王琪冰肖刚. 基于动态图卷积网络的电梯乘客异常行为数据增强方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[9]	康斌陈斌王俊杰李昱林赵军智咸伟志. 基于多粒度共享语义中心关联的文本到人物检索方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[10]	王磊胡节彭博. 用于半监督火灾检测的分布自适应和动态课程伪标签框架[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[11]	王子怡李卫军刘雪洋丁建平刘世侠苏易礌. 基于Swin Transformer与多尺度特征融合的图像描述方法#br# [J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[12]	熊炜, 陈奕博, 张丽真, 杨茜, 邹勤. 利用多帧序列影像的自监督单目深度估计[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3907-3914.
[13]	付可意, 王高才, 邬满. 基于改进区域提议网络和特征聚合小样本目标检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3790-3797.
[14]	杨成昊, 胡节, 王红军, 彭博. 基于注意力机制的不完备多视图聚类算法[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3784-3789.
[15]	方鹏, 赵凡, 王保全, 王轶, 蒋同海. 区块链3.0的发展、技术与应用[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3647-3657.