[1]王秉,王子衡.非高斯噪声背景下计算机视觉目标跟踪方法[J].华侨大学学报(自然科学版),2016,37(6):774-777.[doi:10.11830/ISSN.1000-5013.201606023]
　WANG Bing,WANG Ziheng.Computer Vision Target Tracking Method UnderNon-Gauss Noise Background[J].Journal of Huaqiao University(Natural Science),2016,37(6):774-777.[doi:10.11830/ISSN.1000-5013.201606023]
点击复制

非高斯噪声背景下计算机视觉目标跟踪方法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第37卷
期数:
2016年第6期
页码:
774-777
栏目:
出版日期:
2016-11-20

文章信息/Info

Title:
Computer Vision Target Tracking Method UnderNon-Gauss Noise Background
文章编号:
1000-5013(2016)06-0774-04
作者:
王秉1;  王子衡2
1. 河南交通职业技术学院 航运海事系, 河南 郑州 450000;2. 达姆施塔特工业大学 电子信息工程系, 德国 达姆施塔特 64289
Author(s):
WANG Bing1;  WANG Ziheng2
1. Department of Maritime, Henan Vocational and Technical College of Communications, Zhengzhou 450005, China; 2. Department of Electrical Engineering and Information Technology, Technical University of Darmstadt, Darmstadt 64289, Germany
关键词:
计算机视觉;  非高斯噪声;  粒子滤波;  杂波环境;  跟踪精度
Keywords:
computer vision;  non-Gaussian noise;  particle filter;  clutter environment;  tracking accuracy
分类号:
TP391
DOI:
10.11830/ISSN.1000-5013.201606023
文献标志码:
A
摘要:
针对杂波背景下计算机视觉目标跟踪问题,提出一种非高斯噪声背景下计算机视觉目标跟踪方法.在视频目标运动模型和观测模型的基础上引入了柯西混合噪声模型,对非高斯噪声运动目标的状态进行建模;然后,在传统高斯噪声粒子滤波的框架内给出文中方法的具体实现步骤.针对大面积遮挡和夜晚光照改变的极端情况下对路上行驶的车辆进行实时跟踪实验,结果表明:文中方法明显提升极端杂波环境下的目标运动过程的建模精度,有效提升目标跟踪精度.
Abstract:
Aiming at the problem of computer vision target tracking in clutter background, a computer vision target tracking method under non Gauss noise background is proposed. Based on the vision target moving model and observation model, the Cauchy mixed noise model is introduced to model the non Gauss noise moving object, and the non Gauss noise moving target state is modeled. The proposed method concrete implementation steps is realized in the framework of the traditional Gauss noise particle filter. For driving large area occlusion and night illumination change under extreme conditions on the road of the vehicle real-time tracking, the experimental results show that this method significantly improve the modeling accuracy of extreme clutter target motion process, effectively improve the accuracy of target tracking.

参考文献/References:

[1] MORRIS J B T,TRIVEDI M M.Contextextual activity visualization from long-term video observations[J].IEEE Intelligent Systerms,2010,25(3):50-62.
[2] 刘晨光,程丹松,刘家锋,等.一种基于交互式滤波器的视频中多目标跟踪算法[J].电子学报,2011,39(2):260-267.
[3] 李春鑫,王孝通.基于Rao-Blackwellized粒子滤波的多特征融合多光谱目标自适应跟踪[J].光学精密工程,2009,17(9):2321-2326.
[4] CAO Jie,LI Wei,WU Di.Multi-feature fusion tracking based on a new particle filter[J].Journal of Computers,2012,12(7):2939-2947.
[5] 颜佳,吴敏渊.遮挡环境下采用在线Boosting的目标跟踪[J].光学精密工程,2012,20(2):439-446.
[6] 龚俊亮,何昕,巍仲慧,等.采用改进辅助粒子滤波的红外多目标跟踪[J].光学精密工程,2012,20(2):413-420.
[7] DOU Jianfang,LI Jianxun.Robust visual tracking base on adaptively multi-feature fusion and particle filter[J].Optik,2014,125(2014):1680-1686.
[8] MORSHIDI M,TJAHJADI T.Gravity optimised particle filter for hand tracking[J].Patter Recognition,2014,47(2014):194-207.
[9] 宋宇,李庆玲,康轶非,等.平方根容积 Rao-Blackwillised 粒子滤波SLAM算法[J].自动化学报,2014,40(2):357-367.
[10] 孙中森,孙俊喜,宋建中,等.一种抗遮挡的运动目标跟踪算法[J].光学精密工程,2007,15(2):268-271.
[11] WU Bingfei,KAO ChihChung,JEN Chenglung,et al.A relative discriminative histogram of oriented-gradients-based particle filter approach to vehicle occlusion handling and tracking[J].IEEE Transaction on Industrial Electronics,2014,61(8):4228-4237.
[12] 钟必能,潘胜男.选择性搜索和多深度学习模型融合的目标跟踪[J].华侨大学学报(自然科学版),2016,37(2):207-212.
[13] SAHA S,GUSTAFSSON F.Particle filtering with dependent noise processes[J].IEEE Transaction on Signal Processing,2012,60(9):4497-4508.

备注/Memo

备注/Memo:
收稿日期: 2016-10-18
通信作者: 王秉(1965-),男,副教授,主要从事计算机图形图像的研究.E-mail:wbjtxy@163.com.
基金项目: 国家自然科学基金资助项目(201411326136); 河南省科技厅资助项目(2013132300410337); 河南省教育厅资助项目(JYB2015037)
更新日期/Last Update: 2016-11-20