网络视频监控中运动目标跟踪方法改进

doi:10.3969/j.issn.1000-436x.2014.z1.031

通信学报 ›› 2014, Vol. 35 ›› Issue (Z1): 160-164.doi: 10.3969/j.issn.1000-436x.2014.z1.031

网络视频监控中运动目标跟踪方法改进

韩光星,李崇荣

清华大学网络科学与网络空间研究院，北京 100084

出版日期:2014-10-25 发布日期:2017-06-19

Improvement on moving object tracking method for network video surveillance

Guang-xing HAN,Chong-rong LI

Institute for Network Sciences and Cyberspace,Tsinghua University,Beijing 100084,China

Online:2014-10-25 Published:2017-06-19

摘要/Abstract

摘要：

摘要：针对传统的基于Kalman滤波的MeanShift跟踪算法目标运动速度突然改变时跟踪丢失的问题，在Kalman滤波器中引入加速度项使跟踪保持稳定；为了提高Camshift跟踪算法的实时性，使用简化的Camshift算法自适应调整跟踪窗口尺寸。实验结果表明2种改进分别提高了速度突变时跟踪准确性和目标跟踪的实时性，适合网络视频监控场景。

关键词: 网络视频监控, MeanShift算法, Kalman滤波, Camshift算法

Abstract:

To improve the performance of the traditional MeanShift algorithm based on Kalman filter,acceleration to solve the problem that the moving target changes the direction abruptly is proposed.Another algorithm using simplified Camshift algorithm to keep track of the blob size has low time complexity which meets the real time requirement of network video surveillance.

Key words: network video monitoring, MeanShift algorithm, Kalman filter, Camshift algorithm

韩光星,李崇荣. 网络视频监控中运动目标跟踪方法改进[J]. 通信学报, 2014, 35(Z1): 160-164.

Guang-xing HAN,Chong-rong LI. Improvement on moving object tracking method for network video surveillance[J]. Journal on Communications, 2014, 35(Z1): 160-164.

图/表 7

图1

图2

图3

图4

图5

图6

图7

参考文献 12

[1]	赵春晖, 潘泉, 梁彦等 . 视频运动目标分析[M]. 北京: 国防工业出版社, 2011. 1-109. ZHAO C H , PAN Q , LIANG Y . Video Imagery Moving Targets Analysis[M]. Beijing: National Defence Industry PressPress, 2011. 1-109.
[2]	COMANICIU D , RAMESH V , MEER P . Real-time tracking of non-rigid objects using mean shift[A]. IEEE Conference on Computer Vision and Pattern Recognition[C]. 2000. 142-149.
[3]	COMANICIU D , RAMESH V , MEER P . Kernel-based object tracking[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003,25(5): 564-577.
[4]	KALMAN R E . A new approach to linear filtering and prediction problems[J]. Journal of Basic Engineering, 1960,82(1): 35-45.
[5]	PENG N , YANG J , LIU Z . Mean shift blob tracking with kernel histogram filtering and hypothesis testing[J]. Pattern Recognition Letters, 2005,26, 605-614.
[6]	ZHAO J , QIAO W , MEN G Z . An approach based on mean shift and kalman filter for target tracking under occlusion[A]. 2009 International Conference on Machine Learning and Cybernetics[C]. 2009,4: 2058-2062.
[7]	ABHARI S Q , ERSHADI T Z . Target tracking based on mean shift and Kalman filter with kernel histogram filtering[J]. Computer and Information Science, 2011,4(2): 152.
[8]	COLLINS R T . Mean-shift blob tracking through scale space[A]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition[C]. IEEE, 2003.II-234-40.
[9]	ALLEN J G , XU R Y D , JIN J S . Object tracking using camshift algorithm and multiple quantized feature spaces[A]. Proceedings of the Pan-Sydney Area Workshop on Visual Information Processing[C]. Australian Computer Society,Inc, 2004. 3-7.
[10]	BRADSKI G , KAEHLER A . Learning OpenCV:Computer Vision with the OpenCV Library[M]. O'Reilly Media,Inc, 2008.
[11]	韦迅 . 基于均值漂移的动态目标跟踪算法研究[D]. 哈尔滨:哈尔滨工程大学, 2012. WEI X . The Study of Dynamic Target Tracking Algorithm Based on Mean Shift[D]. Harbin:Harbin Engineering University, 2012.
[12]	夏瑜 . 视觉跟踪新方法及其应用研究[D]. 江苏:江南大学, 2013. XIA Y . Research on Novel Method of Visual Tracking and Its Applications[D]. Jiangsu:Jiangnan University, 2013.

网络视频监控中运动目标跟踪方法改进

Improvement on moving object tracking method for network video surveillance

在线阅读

PDF下载

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 12

相关文章 3

Metrics

推荐阅读 0

[1]	韩光星，李崇荣. 网络视频监控中运动目标跟踪方法改进[J]. 通信学报, 2014, 35(Z1): 31-164.
[2]	陈灿辉,张晓林,霍航宇. 卫星导航系统中基于序贯处理的Kalman滤波[J]. 通信学报, 2012, 33(1): 174-181.
[3]	田增山,周冬生. 基于分形理论的移动单基站定位参数估计算法[J]. 通信学报, 2007, 28(6): 131-136.