显著性直方图模型的Camshift跟踪方法

修春波; 魏世安

doi:10.3788/OPE.20152306.1749

您当前的位置：

首页 >

文章列表页 >

显著性直方图模型的Camshift跟踪方法

信息科学 | 更新时间：2020-08-13

- 显著性直方图模型的Camshift跟踪方法
- Camshift tracking with saliency histogram
- 光学精密工程 2015年23卷第6期页码：1749-1757
- 作者机构：
  
  1. 天津工业大学电气工程与自动化学院天津,300387
  2. 天津工业大学电工电能新技术天津市重点实验室天津,300387
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No.61203302)();天津市应用基础与前沿技术研究计划资助项目(No.14JCYBJC18900)()
- DOI：10.3788/OPE.20152306.1749
  中图分类号： TP391.4
- 收稿日期：2015-01-20，
  
  修回日期：2015-03-12，
  
  纸质出版日期：2015-06-25
- 稿件说明：
移动端阅览
修春波, 魏世安,. 显著性直方图模型的Camshift跟踪方法[J]. 光学精密工程, 2015,23(6): 1749-1757

XIU Chun-bo, WEI Shi-an,. Camshift tracking with saliency histogram[J]. Editorial Office of Optics and Precision Engineering, 2015,23(6): 1749-1757
修春波, 魏世安,. 显著性直方图模型的Camshift跟踪方法[J]. 光学精密工程, 2015,23(6): 1749-1757 DOI： 10.3788/OPE.20152306.1749.

XIU Chun-bo, WEI Shi-an,. Camshift tracking with saliency histogram[J]. Editorial Office of Optics and Precision Engineering, 2015,23(6): 1749-1757 DOI： 10.3788/OPE.20152306.1749.

摘要

针对在复杂背景下跟踪运动目标的要求

建立了目标的显著性直方图模型

提出了改进的连续自适应均值漂移(Camshift)跟踪方法.通过比较目标区与背景区的色调差异

计算目标不同色调等级的显著性值;基于加权的方式强化显著性色调在目标识别过程中的作用

弱化非显著性色调的作用

从而抑制背景区对目标识别的干扰.利用加权直方图模型反向投影

建立了跟踪图像的概率投影图

利用均值漂移方法完成目标跟踪任务.将该方法分别应用于标准测试库视频图像的跟踪以及实际运动目标的跟踪实验中并与传统方法进行了比较.结果显示

该方法能够利用显著性色调很好地将目标从背景中区分出来

在计算量增加不多、且满足电视跟踪系统实时性要求的情况下

提高了目标识别的准确性和稳定性

目标定位的最大偏差与被跟踪目标区的尺寸比小于25%

能够确保被跟踪目标不丢失.

Abstract

According to the target tracking requirements in complex backgrounds

an improved Continuously Adaptive Meanshift(Camshift) tracking method was proposed by modeling a saliency histogram of the target. The saliency values of different hues in the target area were calculated by comparing the difference between the target and the background area. The weighted histogram was used to strengthen the roles of the saliency hues and weaken the roles of the non-saliency hues

by which the interference from the background was restrained. By using the back projection of the weighted histogram

the probability projection image of the tracking image was obtained by the back projection

then the target tracking task was completed by mean shift method. The proposed method was applied to an actual target in tracking experiments and that in the video of the standard test libraries and obtained results were compared with that of traditional methods. The simulation results show that the target is easily recognized from the background by the saliency hues

and the accuracy and the stability of the target recognition are improved with satisfied real time ability and without too much computation cost. The ratio of the max deviation to the size of the target is less than 25%

which ensures the target not to be lost.

关键词

Keywords

references

MORSHIDIM, TJAHJADI T. Gravity optimised particle filter for hand tracking [J]. Pattern Recognition, 2014, 47 (1): 194-207.

李一芒,何昕,魏仲慧,等. 采用降维技术的红外目标检测与识别[J]. 光学精密工程, 2013, 21(5):1297-1303. LI Y M, HE X, WEI ZH H, et al.. Infrared target detection and recognition using dimension reduction technology [J].Opt. Precision Eng., 2013, 21(5):1297-1303. (in Chinese)

孙晓燕,常发亮. 梯度特征稀疏表示目标跟踪[J]. 光学精密工程, 2013, 21(12): 3191-3197. SUN X Y, CHANG F L. Object tracking based on sparse representation of gradient feature [J].Opt. Precision Eng., 2013, 21(12): 3191-3197. (in Chinese)

黄伟国,顾超,朱忠奎. 用于目标识别的PAC-SC形状匹配算法[J]. 光学精密工程,2013,21(8):2103-2110. HUANG W G, GU CH, ZHU ZH K. PAC-SC shape matching for object recognition [J].Opt. Precision Eng., 2013, 21(8):2103-2110. (in Chinese)

BELAROUSSI R, MILGRAM M. A comparative study on face detection and tracking algorithms [J]. Expert Systems with Applications, 2012, 39 (8): 7158-7164.

SHEN C F, LIN X Y, SHI Y C. Moving object tracking under varying illumination conditions [J]. Pattern Recognition Letters, 2006, 27(14): 1632-1643.

修春波,魏世安,万蓉凤. 二维联合特征模型的自适应均值漂移目标跟踪[J]. 光电子·激光,2015,26(2):342-351. XIU CH B, WEI SH A, WAN R F. CamShift target tracking based on two-dimensional joint characteristic [J]. Journal of Optoelectronics·Laser, 2015, 26(2): 342-351. (in Chinese)

KARASULUB, KORUKOGLU S. Moving object detection and tracking by using annealed background subtraction method in videos: Performance optimization [J]. Expert Systems with Applications, 2012, 39 (1): 33-43.

COMANICIU D, RAMESH V, MEER P. Kernel-based object tracking [J]. IEEE Transactions Pattern Analysis and Machine Intelligence, 2003, 25 (5) : 564-577.

WANG J, YAGI Y. Integrating color and shape-texture features for adaptive real-time object tracking [J]. IEEE Transactions on Image Processing, 2008, 2(17): 235-240.

BRADSKI G R. Computer vision face tracking for use in a perceptual user interface [J]. Intel Technology Journal, 1998, 2 (2): 1-15.

YIN M H, ZHANG J, SUN H G, et al.. Multi-cue-based CamShift guided particle filter tracking [J]. Expert Systems with Applications, 2011, 38 (5): 6313-6318.

WANG Z W, YANG X K, XU Y, et al.. CamShift guided particle filter for visual tracking [J]. Pattern Recognition Letters, 2009, 30(4): 407-413.

MUNOZ-SALINASR, AGUIRRE E, GARCIA-SILVENTE M, GONZALEZ A. A multiple object tracking approach that combines colour and depth information using a confidence measure [J]. Pattern Recognition Letters, 2008, 29 (10): 1504-1514.

修春波,卢少磊,任晓. 基于微分信息融合的Mean Shift改进跟踪算法[J]. 系统工程与电子技术,2014,36(5):1004-1009. XIU CH B, LU SH L, REN X. Improved Mean Shift tracking algorithm based on differential information [J]. Systems Engineering and Electronics, 2014, 36(5): 1004-1009. (in Chinese)

云霄,肖刚. 基于Camshift的多特征自适应融合船舶跟踪算法[J]. 光电工程, 2011, 38 (5): 52-58. YUN X,XIAO G. Camshift ship tracking algorithm based on multi-feature adaptive fusion [J]. Opto-Electronic Engineering, 2011, 38 (5): 52-58.(in Chinese)

林建华,刘党辉,邵显奎. 多特征融合的Camshift算法及其进一步改进[J]. 计算机应用, 2012, 32 (10): 2814-2816. LIN J H, LIU D H,SHAO X K, Multi-feature fusion Camshift algorithm and its further improvement [J]. Journal of Computer Applications, 2012, 32 (10): 2814-2816. (in Chinese)

浏览量

344

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

数据驱动的多模复合制导信息融合及其试验验证

顾及最优分配和最佳掩码的点云部件分割

基于非机动单站的目标运动状态无偏估计

地基大口径望远镜动态目标跟踪中压电式快速反射镜迟滞效应的补偿

基于级联滑模控制的高精度光电跟踪与捕获