基于在线支持向量机的Mean Shift彩色图像跟踪

郭敬明; 何昕; 魏仲慧

doi:null

您当前的位置：

首页 >

文章列表页 >

基于在线支持向量机的Mean Shift彩色图像跟踪

成像技术与图像处理 | 更新时间：2020-08-12

- 基于在线支持向量机的Mean Shift彩色图像跟踪
- New mean shift tracking for color image based on online support vector machine
- 液晶与显示 2014年29卷第1期页码：120-128
- 作者机构：
  
  1. 中国科学院长春光学精密机械与物理研究所,吉林长春,中国,130033
  2. 中国科学院大学北京,100049
- 作者简介：
- 基金信息：
  
  国家863高技术研究发展计划（No.2005AA778032）();国家自然科学基金（No.60878052）()
- DOI：
  中图分类号： TP391
- 收稿日期：2013-04-12，
  
  修回日期：2013-12-20，
  
  纸质出版日期：2014-02-15
- 稿件说明：
移动端阅览
郭敬明, 何昕, 魏仲慧. 基于在线支持向量机的Mean Shift彩色图像跟踪[J]. 液晶与显示, 2014,29(1): 120-128

GUO Jing-ming, HE Xin, WEI Zhong-hui. New mean shift tracking for color image based on online support vector machine[J]. , 2014,29(1): 120-128
郭敬明, 何昕, 魏仲慧. 基于在线支持向量机的Mean Shift彩色图像跟踪[J]. 液晶与显示, 2014,29(1): 120-128 DOI：

GUO Jing-ming, HE Xin, WEI Zhong-hui. New mean shift tracking for color image based on online support vector machine[J]. , 2014,29(1): 120-128 DOI：

摘要

为了解决传统Mean Shift跟踪方法中目标模板只能从单一图像建立，且很难更新问题，提出了一种新的Mean Shift彩色图像跟踪方法。将RGB颜色空间投影到HSV颜色空间，建立了基于HSV颜色空间的统一直方图核函数模型。为了实现模板在线更新，引入在线支持向量机，推理了基于HSV空间的在线支持向量机的Mean Shift跟踪算法，从而适应目标因尺寸、姿态及光照造成的模型变化。为了验证算法的有效性，对两组国际通用的CAVIAR彩色图像序列进行了跟踪测试。实验结果表明，提出的改进算法在目标姿态、光照或背景发生较大变化时，能有效跟踪目标。当图像分辨率为384288（目标尺寸约为2080）时，最快处理速度达40 f/s，且跟踪精度比传统Mean Shift提高32.1%。

Abstract

In order to solve the problem that the object template of traditional Mean Shift tracking can only be built from a single image

and difficult to update

an improved Mean Shift tracking algorithm for color image is proposed. Firstly

RGB color space is projected to HSV color space

and a unified histogram kernel model based on HSV color space is set up. Secondly

in order to achieve template online update

an online support vector machine is introduced

and a Mean Shift tracking algorithm integrated with online SVM based on HSV color space is reasoned. By above operation

object modeling is adaptive to object size

posture or illumination changes. Finally

tracking test on two groups of international general CAVIAR color image sequence is taken to verify effectiveness of the algorithm. Experiments show that the improved algorithm performs well with great changes taken in target pose

illumination or background. When the image resolution is 384 pixel288 pixel(target size of about 20 pixel80 pixel)

the fastest processing speed reaches 40 f/s

as well as tracking precision increases by 32.1% than traditional Mean Shift.

关键词

Keywords

references

Comaniciu D, Ramesh V.Kernel-based object tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 24(5): 564-577.[2] ISARD M, BLAKE A.Condensation-conditional density propagation for visual tracking[J].International Journal of Computer Vision, 1998, 29(1): 5-28.[3] 杜超, 刘伟宁, 刘恋. 一种基于卡尔曼滤波及粒子滤波的目标跟踪算法[J]. 液晶与显示, 2011, 26(3):384-389. Du C, Liu W N, Liu L. Target tracking algorithm based on Kalman filter and particle filter[J].Chinese Journal of Liquid Crystals and Displays, 2011, 26(3):384-389.(in Chinese)[4] 王国良, 刘金国. 基于粒子滤波的多自由度运动目标跟踪[J]. 光学精密工程, 2011, 19(4):864-869. Wang G L, Liu J G. Moving object tracking with multi-degree-of-freedom based on particle filters[J].Optics and Precision Engineering, 2011, 19(4):864-869.(in Chinese)[5] 陈爱华, 孟勃, 朱明, 等. 多模式融合的目标跟踪算法[J]. 光学精密工程, 2009, 17(1):185-190. Chen A H, Meng B, Zhu M, et al.Multi-pattern fusion algorithm for target tracking[J].Optics and Precision Engineering, 2009, 17(1):185-190. (in Chinese)[6] Comaniciu D, Meer P. Mean shift: A Robust application toward feature space analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603-619.[7] 王田, 刘伟宁, 韩广良, 等. 基于改进Mean Shift的目标跟踪算法[J]. 液晶与显示, 2012, 27(3):396-400. Wang T, Liu W N, Han G L, et al.Target tracking algorithm based on improved Meanshift[J].Chinese Journal of Liquid Crystals and Displays, 2012, 27(3):396-400. (in Chinese)[8] 刘扬, 张云峰, 董月芳. 复杂背景下抗遮挡的运动目标跟踪算法[J]. 液晶与显示, 2010, 25(6):890-895. Liu Y, Zhang Y F, Dong Y F.Anti-occlusion algorithm of tracking moving object in clutter background[J].Chinese Journal of Liquid Crystals and Displays, 2010, 25(6):890-895. (in Chinese)[9] Jung U C, SEUNG H J, XU. FPGA-based real-time visual tracking system using adaptive color histograms[C]//Proceedings of the 2007th International Conference on Robotics and Biomimetics, Sanya, P.R. China:ICRB, 2007:172-177.[10] Sheng S H, Kim J, Wang H Z. Generalized kernel-based visual tracking[J].IEEE Transactions on Circuits and Systems for Video Thechnology, 2010, 20(1): 119-130.[11] AVIDAN S. Ensemble tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(2): 261-271.[12] Collins R T, Liu Y X, Leordeanu M. Online selection of discriminative tracking features[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1631-1643.[13] Syend N A, Liu H, Sung K. Incremental learning with support vector machines[C]//Proceedings of the Workshop on Support Vector Machines at the International Joint Conference on Artificial Intelligence, Stockholm, Sweden:IJCAI, 1999: 2165-2176.[14] 李国正, 王猛, 曾华军. 支持向量机导论[M]. 北京:电子工业出版社, 2004. Li G Z, Wang M, Zeng H J.An Introduction to Support Vector Machines and Other Kernel-based Learning Methods [M].Beijing: Publishing House of Electronics Industry, 2004.(in Chinese)[15] Perez P, Hue C, Vermaak J, et al.Color-Based Probabilistic tracking.[C]//Lecture Notes in Computer Science, Copenhagan, Denmark:Eccv, 2002:661-675.[16] The school of Information, University of Edinburgh.CAVIAR Test case Scenarios[DB/OL][2011-05-12].//http:groups.inf.ed.ac.uk/vision/CAVIAR/CAVIARDATA1/. 作者简介:

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

双分支金字塔网络的微光图像增强算法