[1]杜 鹃,吴芬芬.高斯混合模型的运动目标检测与跟踪算法[J].南京理工大学学报(自然科学版),2017,41(01):41.[doi:10.14177/j.cnki.32-1397n.2017.41.01.006]
 Du Juan,Wu Fenfen.Movement target tracking algorithm by using Gaussian mixture model[J].Journal of Nanjing University of Science and Technology,2017,41(01):41.[doi:10.14177/j.cnki.32-1397n.2017.41.01.006]
点击复制

高斯混合模型的运动目标检测与跟踪算法()
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
41卷
期数:
2017年01期
页码:
41
栏目:
出版日期:
2017-02-28

文章信息/Info

Title:
Movement target tracking algorithm by using Gaussian mixture model
文章编号:
1005-9830(2017)01-0041-06
作者:
杜 鹃1吴芬芬2
1.黄河水利职业技术学院 信息工程系,河南 开封 475004; 2.河南交通职业技术学院 交通信息工程系,河南 郑州 451400
Author(s):
Du Juan1Wu Fenfen2
1.Information Engineering Department,Yellow River Conservancy Technical Institute,Kaifeng 475004,China; 2.Department of Traffic Information Engineering,Henan Vocational andTechnical College of Communication,Zhengzhou 451400,China
关键词:
混合高斯算法 目标跟踪 无线传感器 节点协作 均值漂移算法 仿真实验
Keywords:
Gaussian mixture model target tracking wireless sensor node nodes collaboration mean shift algorithm simulation experiment
分类号:
TP391.4
DOI:
10.14177/j.cnki.32-1397n.2017.41.01.006
摘要:
运动目标跟踪是计算机视觉研究中的一项关键技术,针对当前运动目标跟踪算法存在的跟踪精度低,实时性差等不足,提出了基于高斯混合模型的运动目标检测与跟踪算法。首先收集目标的信息,并采用混合高斯模型对运动目标背景进行建模,然后采用均值漂移算法对目标进行跟踪,最后采用VC6.0++实现运动目标跟踪仿真实验。结果表明,该文提高了运动目标跟踪的精度,加快了运动目标跟踪的速度,并对遮挡、场景变化具有良好鲁棒性,性能要优于当前其他运动目标跟踪算法,具有更高的实际应用价值。
Abstract:
Video object tracking is a key technology in computer vision research,and current video target tracking algorithms has defects such as low tracking precision,poor real-time,a novel video object tracking algorithm based on Gaussian Mixture model is proposed in this paper.Firstly,wireless sensor network is used to collect target information,and secondly Gaussian Mixture model is used to model video background while mean shift algorithm is used to track the target,finally,video object tracking simulation experiment is carried out on VC 6.0++.The results show that the propose algorithm can improve accuracy of video target tracking and fasten tracking speed which has good robustness to occlusion and illumination change,it has better performance than other video target tracking algorithms and has higher practical value.

参考文献/References:

[1] Xie Yuan,Qu Yanyun,Li Cuihua,et al.Online multiple instance gradient feature selection for robust visual tracking[J].Pattern Recognition Letters,2012,33(9):1075-1082.
[2]Leichter I,Lindenbaum M,Rivlin E.Mean shift tracking with multiple references color histograms[J].Computer Vision and Image Understanding,2010,114(3):400-408.
[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]Kalal Z,Mikolajczyk K,Matas J.Tracking-learning-detection[J].Pattern Analysis and Machine Intelligence,IEEE Transactions on,2012,34(7):1409-1422.
[5]徐天阳,吴小俊.基于多特征级联的目标跟踪算法研究[J].南京理工大学学报,2015,39(3):286-290.
Xu Tianyang,Wu Xiaojun.Object tracking algorithm based on multiple features cascade[J].Journal of Nanjing University of Science and Technology,2015,39(3):286-290.
[6]戴洪德,邹杰,徐胜红,等.含预测和容错的自适应Kalman目标跟踪[J].南京理工大学学报,2015,39(1):108-114.
Dai Hongde,Zou Jie,Xu Shenghong,et al.Adaptive Kalman filter combined with prediction and fault tolerance for target tracking[J].Journal of Nanjing University of Science and Technology,2015,39(1):108-114.
[7]宋晓林,王文涛,张伟伟.基于LBP纹理和改进Camshift算子的车辆检测与跟踪[J].湖南大学学报(自然科学版),2013,40(8):52-57.
Song Xiaolin,Wang Wentao,Zhang Weiwei.Vehicle detection and tracking based on the Local Binary Pattern texture and improved Camshift operator[J].Journal of Hunan University(Natural Sciences),2013,40(8):52-57.
[8]王保云,范保杰.基于颇色纹理联合直方图的自适应Meanshift跟踪算法[J].南京邮电大学学报(自然科学版),2013,33(3):18-25.
Wang Baoyun,Fang Baojie.Adoptive meanshift tracking algorithm based on the combined feature histogram of color and texture[J].Journal of Nanjing University of Posts and Telecommunications(Natural Sciences),2013,33(3):18-25.
[9]Liang Liu,Xi Zhang.Optimal node selection for target localization in wireless camera senor networks[J].IEEE Transactions on Vehicular Technology,2010,59(7):120-127.
[10]刘明,赵孝磊.一种改进的Camshift目标跟踪算法[J].南京理工大学学报,2013,37(5):755-759.
Liu Ming,Zhao Xiaolei.Target tracking based on improved Camshift algorithm[J].Journal of Nanjing University of Science and Technology,2013,37(5):755-759.
[11]席涛,张胜修,原魁,等.基于遗传进化策略的粒子滤波运动目标跟踪[J].光电工程,2009,36(3):28-31.
Xi Tao,Zhang Shengxiu,Yuan Kui,et al.Video object tracking based on particle filter with genetic evolution strategy[J].Opto-Electronic Engineering,2009,36(3):28-31.
[12]王玲玲,裴东,王全州.一种改进的 Camshift 运动目标跟踪算法[J].激光与红外,2015,45(10):1266-1271.
Wang Linlin,Pei Dong,Wang Quanzhou.Video target tracking algorithm based on improved Camshift[J].Laser & Infrared,2015,45(10):1266-1271.
[13]刘晴,唐林波,赵保军.跟踪窗自适应的Mean Shift标跟踪算法[J].系统工程与电子技术,2012,34(2):409-412.
Liu Qing,Tang Linbo,Zhao Baojun.Algorithm of target tracking based on Mean Shift with adaptive tracking window[J].Journal of Systems Engineering and Electronics,2012,34(2):409-412.

相似文献/References:

[1]程相权,王远钢,郭治.满足滞留度指标的图像波门预测技术研究[J].南京理工大学学报(自然科学版),2001,(04):346.
 ChengXiangquan WangYuangang GuoZhi.Prediction Study of Tracking Window with Specified Residence Index[J].Journal of Nanjing University of Science and Technology,2001,(01):346.
[2]杨春玲,孙泓波,倪晋麟,等.多传感器远距离目标跟踪精度分析[J].南京理工大学学报(自然科学版),1999,(03):53.
 YangChunling SunHongbo NiJinlin LiuGuosui.Research of Multisensor for long Range Target Tracking Accuracy[J].Journal of Nanjing University of Science and Technology,1999,(01):53.
[3]刘华军,赖少发.汽车毫米波雷达目标跟踪的快速平方根CKF算法[J].南京理工大学学报(自然科学版),2016,40(01):56.
 Liu Huajun,Lai Shaofa.Fast square root CKF for automotive millimeter-waveradar target tracking[J].Journal of Nanjing University of Science and Technology,2016,40(01):56.
[4]茅正冲,黄舒伟.基于结构化判别稀疏表示的目标跟踪[J].南京理工大学学报(自然科学版),2018,42(03):271.[doi:10.14177/j.cnki.32-1397n.2018.42.03.003]
 Mao Zhengchong,Huang Shuwei.Structured discriminant sparse representation based object tracking[J].Journal of Nanjing University of Science and Technology,2018,42(01):271.[doi:10.14177/j.cnki.32-1397n.2018.42.03.003]
[5]娄 康,朱志宇,葛慧林.基于目标运动特征的红外目标检测与跟踪方法[J].南京理工大学学报(自然科学版),2019,43(04):455.[doi:10.14177/j.cnki.32-1397n.2019.43.04.011]
 Lou Kang,Zhu Zhiyu,Ge Huilin.Infrared target detection and tracking method based ontarget motion feature[J].Journal of Nanjing University of Science and Technology,2019,43(01):455.[doi:10.14177/j.cnki.32-1397n.2019.43.04.011]

备注/Memo

备注/Memo:
收稿日期:2016-10-19 修回日期:2017-01-02
作者简介:杜鹃(1982-),女,讲师,主要研究方向:数据挖掘、人工智能,E-mail:42349053@qq.com; 通讯作者:吴芬芬(1979-),女,讲师,主要研究方向:软件工程、数据库,E-mail:32154446@qq.com。
引文格式:杜鹃,吴芬芬.高斯混合模型的运动目标检测与跟踪算法[J].南京理工大学学报,2017,41(1):41-46.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2017-02-28