|Table of Contents|

Movement target tracking algorithm by using Gaussian mixture model(PDF)


Research Field:
Publishing date:


Movement target tracking algorithm by using Gaussian mixture model
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
Gaussian mixture model target tracking wireless sensor node nodes collaboration mean shift algorithm simulation experiment
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.


[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.
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.
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.
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.
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.
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.
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.


Last Update: 2017-02-28