Multi-template collaborative correlation tracking with multi-feature fusion

Ning MAO; De-dong YANG; Fu-cai YANG; Yu-zhu CAI

doi:10.3788/YJYXS20173202.0153

您当前的位置：

首页 >

文章列表页 >

Multi-template collaborative correlation tracking with multi-feature fusion

Display and Image | 更新时间：2020-07-07

- Multi-template collaborative correlation tracking with multi-feature fusion
- Chinese Journal of Liquid Crystals and Displays Vol. 32, Issue 2, Pages: 153-162(2017)
- 作者机构：
  
  河北工业大学控制科学与工程学院, 天津 300130
- 作者简介：
- 基金信息：
- DOI：10.3788/YJYXS20173202.0153
  CLC： TP391
- Received：23 September 2016，
  
  Accepted：19 October 2016，
  
  Published：05 February 2017
- 稿件说明：
移动端阅览
Ning MAO, De-dong YANG, Fu-cai YANG, et al. Multi-template collaborative correlation tracking with multi-feature fusion[J]. Chinese journal of liquid crystals and displays, 2017, 32(2): 153-162.
DOI：

Ning MAO, De-dong YANG, Fu-cai YANG, et al. Multi-template collaborative correlation tracking with multi-feature fusion[J]. Chinese journal of liquid crystals and displays, 2017, 32(2): 153-162. DOI： 10.3788/YJYXS20173202.0153.

摘要

针对目标跟踪中的目标尺度变化、遮挡、光照变化、相似目标混淆等问题，本文提出多特征融合的协同相关跟踪算法。首先，本文用多种特征构建目标外观模型，提高目标模型的鲁棒性，增强跟踪的抗形变能力和抗光照变化能力。然后，利用定点优化策略，解决多模板滤波优化问题，获得最佳滤波参数，通过多模板相关滤波算法估计目标位置，利用改进的尺度池方法解决目标尺度变化问题。最后，利用目标置信度判别跟踪目标是否发生遮挡，当目标发生遮挡时，利用CUR滤波模块重新检测目标，解决遮挡情况下跟踪任务。本文利用OTB-2013数据集中的方法测试本文算法，实验表明本文算法的整体成功率和精确度为0.622和0.830，本文算法在目标发生尺度变化、遮挡、光照变化、相似目标混淆等问题情况下，能准确、可靠地跟踪目标，具有一定研究价值。

Abstract

In order to solve the problem of target scale change

occlusion

illumination change

similar target confusion in target tracking

the paper proposes multi-template collaborative correlation tracking by multi-feature fusion algorithm. First

this paper constructs the target appearance model with various features

improves the robustness of the target model

and enhances the ability of anti deformation and the ability of light variation. Then

the fixed-point optimization strategy is used to solve the multi template filtering optimization problem

the optimal filter parameters are obtained and the target position is estimated by the multi-template correlation filtering algorithm. Target scale change is solved by the improved scale pool method. Finally

the target confidence is used to judge whether the tracking target is occluded. When the target is occluded

the CUR filter module is used to re-detect the target. The tracking task in the occlusion case is resolved. In this paper

we use the method of OTB-2013 dataset to test the algorithm. Experimental results show that the overall success rate and accuracy of the algorithm are 0.622 and 0.830.Under the situation of occlusion

scale change

similar target interfere and illumination variation

the algorithm can accurately and reliably track the target which has certain research value.

关键词

Keywords

references

HARE S, SAFFARI A, TORR P H S. Struck:structured output tracking with kernels[C]// Proceedings of 2011 IEEE International Conference on Computer Vision, Barcelona:IEEE, 2011:263-270.

KALAL Z, MIKOLAJCZYK K, MATAS J. Tracking-learning-detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2012, 34(7):1409-1422.

李静宇, 王延杰.基于子空间的目标跟踪算法研究[J].液晶与显示, 2014, 29(4):617-622.

LI J Y, WANG Y J. Subspace based target tracking algorithm[J]. Chinese Journal of Liquid Crystals and Displays , 2014, 29(4):617-622. (in Chinese)

ROSS D A, LIM J, LIN R S, et al. Incremental learning for robust visual tracking[J]. International Journal of Computer Vision, 2008, 77(1/3):125-141.

张雷, 王延杰, 孙宏海, 等.采用核相关滤波器的自适应尺度目标跟踪[J].光学精密工程, 2016, 24(2):448-459.

ZHANG L, WANG Y J, SUN H H, et al. Adaptive scale object tracking with kernelized correlation filters[J]. Optics and Precision Engineering , 2016, 24(2):448-459. (in Chinese)

程帅, 孙俊喜, 曹永刚, 等.增量深度学习目标跟踪[J].光学精密工程, 2015, 23(4):1161-1170.

CHEN S, SUN J X, CAO Y G, et al. Target tracking based on incremental deep learning[J]. Optics and Precision Engineering, 2015, 23(4):1161-1170. (in Chinese)

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 C B, WEI S A. Camshift tracking with saliency histogram[J]. Optics and Precision Engineering, 2015, 23(6):1749-1757. (in Chinese)

HENRIQUES J F, CASEIRO R, MARTINS P, et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]// Proceedings of the 12the European Conference on Computer Vision-ECCV 2012 , Berlin Heidelberg:Springer, 2012:702-715.

DANELLJAN M, HÄGER G, KHAN F S, et al. Accurate scale estimation for robust visual tracking[C]// Proceedings of the 2014 British Machine Vision Conference. Nottingham:BMVA, 2014:1-5.

LI Y, ZHU J K. A scale adaptive kernel correlation filter tracker with feature integration[C]// European Conference on Computer Vision Workshop VOT2014, Switzerland:Springer, 2014:254-265.

HENRIQUES J F, CASEIRO R, MARTINS P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2015, 37(3):583-596.

ZHU G B, WANG J Q, WU Y, et al. Collaborative correlation tracking[C]. Proceedings of the 2015 British Machine Vision Conference, Swansea:BMVA, 2015:1-12.

WUL, LIM J, YANG M H. Online object tracking:a benchmark[C]// Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition , Portland, OR:IEEE, 2013:2411-2418.

WANG S S, ZHANG Z H. Improving CUR matrix decomposition and the Nyström approximation via adaptive sampling[J]. The Journal of Machine Learning Research, 2013, 14(1):2729-2769.

XU M, JIN R, ZHOU Z H. CUR algorithm for partially observed matrices[C]// Proceedings of the 32nd International Conference on Machine Learning. Lille, France:JMLR, 2015:1412-1421.

BIBI A, GHANEM B. Multi-template scale-adaptive kernelized correlation filters[C]// Proceedings of 2015 IEEE International Conference on Computer Vision Workshop , Santiago:IEEE, 2015:613-620.

HE S F, YANG Q X, LAU R W H, et al. Visual tracking via locality sensitive histograms[C]// Proceedings of 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR:IEEE, 2013:2427-2434.

ZHONG W, LU H C, YANG M H. Robust object tracking via sparsity-based collaborative model[C]// Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI:IEEE, 2012:1838-1845.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Anti-UAV object tracking with enhanced backbone and feature rearrangement

Multi-feature fusion target tracking algorithm

Multi-feature fusion gesture recognition based ondeep convolutional neural network

Saliency detection algorithm integrating multiple features of high and low level

Response adaptive tracking based on convolution neural network

Related Author

DING Yufeng

YANG Zhigang

ZHENG Binxi

Hui-hui LIANG

Qiu-sheng HE

Wei-zhen JIA

Wei-feng ZHANG

Wei-guo YUN

Related Institution

College of Information and Communication Engineering， Harbin Engineering University

School of Electronic Information Engineering, Taiyuan University of Science and Technology

School of Information and Control Engineering, Xi'an University of Architecture and Technology

College of Computer Science and Technology, Henan Polytechnic University

School of Physics & Electronic Information Engineering, Henan Polytechnic University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰