[1]郝向东,毛晓波,梁静.基于ELM与Mean Shift的抗遮挡目标跟踪算法[J].郑州大学学报(工学版),2016,37(01):1-5.[doi:10.3969/j.issn.1671-6833.201503043]
　Mao Xiaobo,Hao Xiangdong,Liang Jing.Algorithm of Target Tracking Based on Mean Shift with ELM[J].Journal of Zhengzhou University (Engineering Science),2016,37(01):1-5.[doi:10.3969/j.issn.1671-6833.201503043]
点击复制

基于ELM与Mean Shift的抗遮挡目标跟踪算法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
37
期数:
2016年01期
页码:
1-5
栏目:
出版日期:
2016-02-28

文章信息/Info

Title:
Algorithm of Target Tracking Based on Mean Shift with ELM
作者:
郝向东; 毛晓波; 梁静
郑州大学 电气工程学院,河南 郑州,450001
Author(s):
Mao Xiaobo;  Hao Xiangdong;  Liang Jing
School of Electrical Engineering, Zhengzhou University, Zhengzhou, Henan 450001 
关键词:
目标跟踪; 遮挡; MeanShift; ELM
Keywords:
DOI:
10.3969/j.issn.1671-6833.201503043
文献标志码:
A
摘要:
针对目标跟踪过程中发生遮挡时跟踪出现偏差的情况,在传统Mean Shift跟踪算法的基础上引入极限学习机( extreme learning machine,ELM) ,提出了基于ELM与Mean Shift的目标跟踪算法. 该算法根据过去3个时刻的目标位置信息,利用ELM预测出目标当前可能位置,代替目标前一时刻位置作为Mean Shift迭代起始点,并在邻域范围内进行迭代,得到目标的真实位置.实验结果表明,与现有的改进算法相比,新算法减少了迭代次数和运算时间,同时在遮挡情况下能够准确定位目标位置并进行跟踪,提高了跟踪系统的实时性和鲁棒性.
Abstract:
In view of the problem of object deviation when occlusions occur during the target tracking, a new algorithm using Mean Shift with ELM is proposed. According to the formal information of the object’ s loca-tion, current possible location was predicted by ELM, the iteration was started from the possible location in-stead of formal location, and the object’ s real center is calculated by mean shift algorithm. The simulation re-sults show that proposed algorithm can track precisely target occluded, operation time and number of iteration are reduced so that efficiency and robustness are improved.

相似文献/References:

[1]冯冬青邢凯丽.基于能量平衡的无线传感网络分布式成簇机制[J].郑州大学学报(工学版),2015,36(03):6.[doi:10.3969/ j. issn.1671 -6833.2015.03.002]
　FENG Dong-qing,XING Kai-li.A Distributed Clustering Mechanism Based on Energy Balancein Wireless Sensor Networks[J].Journal of Zhengzhou University (Engineering Science),2015,36(01):6.[doi:10.3969/ j. issn.1671 -6833.2015.03.002]
[2]毛晓波,周晓东,刘艳红.基于FAST特征点改进的TLD目标跟踪算法[J].郑州大学学报(工学版),2018,39(02):1.[doi:10.13705/j.issn.1671-6833.2018.02.001]
　Mao Xiaobo,Zhou Xiaodong,Liu Yanhong.Improved TLD Object Tracking Algorithm Based On FAST Teature Points[J].Journal of Zhengzhou University (Engineering Science),2018,39(01):1.[doi:10.13705/j.issn.1671-6833.2018.02.001]
[3]王希鹏,李永,李智,等.融合图像深度的抗遮挡目标跟踪算法[J].郑州大学学报(工学版),2021,42(05):19.[doi:10.13705/j.issn.1671-6833.2021.05.011]
　Wang Xipeng,Li Yong,Li Zhi,et al.Anti-occlusion Target Tracking Algorithm Based on Image Depth[J].Journal of Zhengzhou University (Engineering Science),2021,42(01):19.[doi:10.13705/j.issn.1671-6833.2021.05.011]
[4]毛晓波,朱东伟,陈铁军..融合颜色和梯度方向直方图的粒子滤波跟踪算法[J].郑州大学学报(工学版),2012,33(04):81.[doi:10.3969/j.issn.1671-6833.2012.04.019]
　MAO Xiaobo,ZHU Dongwei,CHEN Tiejun.Particle Filter Object Tracking Based on Histograms of Oriented Grads and Colors[J].Journal of Zhengzhou University (Engineering Science),2012,33(01):81.[doi:10.3969/j.issn.1671-6833.2012.04.019]

更新日期/Last Update: