|Table of Contents|

Optimization Analysis of Target Tracking Learning Rate via Color Feature(PDF)

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2019年03期
Page:
59-
Research Field:
计算机工程
Publishing date:

Info

Title:
Optimization Analysis of Target Tracking Learning Rate via Color Feature
Author(s):
Ou Fenglin1; Wu Huijun1; Yang Wenyuan2
(1.School of Information Engineering,Zhangzhou Institute of Technology,Zhangzhou 363000,China)(2.Fujian Key Laboratory of Granular Computing and Application,Minnan Normal University,Zhangzhou 363000,China)
Keywords:
computer vision; video target tracking; color characteristics; optimization analysis; learning rate; similarity measure
PACS:
TP391.4
DOI:
10.3969/j.issn.1672-1292.2019.03.009
Abstract:
Target tracking is one of the key technologies in the intelligent video monitoring system. Aiming at this problem,this paper analyzes and optimizes the learning rate on the basis of color features to suppress drift and improve the accuracy of target tracking. Firstly,the target background and interference perception target model are established by using RGB color features.Secondly,the probability and distance values of the interference region and the target region of the target tracking object are calculated according to the disturbance perception model. Finally,different learning rates are introduced to optimize the target location of the probability value and distance value in the target tracking,and the optimal value of the tracking result is obtained. In this paper,the effectiveness of the optimization analysis is verified by using the VOT2016 evaluation benchmark group of 60 video sequences. The experimental results show that the optimization of learning rate,the accuracy and speed of target tracking are improved to a certain extent.

References:

[1] YANG H,SHAO L,ZHENG F,et al. Recent advances and trends in visual tracking:a review[J]. Neurocomputing,2011,74(18):3823-3831.
[2]WANG D,LU H,YANG M H. Least soft-threshold squares tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Portland Oregon,USA,2013.
[3]JO?O F H,CASEIRO R,MARTINS P,et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]//Proceedings of the European Conference on Computer Vision. Florence,Italy,2012.
[4]胡良梅,段琳琳,张旭东,等. 融合颜色信息与深度信息的运动目标检测方法[J]. 电子与信息学报,2014,36(9):2047-2052.
HU L M,DUAN L L,ZHANG X D,et al. Moving object detection based on the fusion of color and depth information[J]. Journal of electronics & information technology,2014,36(9):2047-2052.(in Chinese)
[5]POSSEGGER H,MAUTHNER T,BISCHOF H. In defense of color-based model-free tracking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Prague Czech Republic,2015.
[6]张焱,张志龙,沈振康,等. 基于动态显著性特征的粒子滤波多目标跟踪算法[J]. 电子学报,2008,36(12):2306-2311.
ZHANG Y,ZHANG Z L,SHEN Z K,et al. The images tracking algorithm using particle filter based on dynamic salient features of targets[J]. Acta automatica sinica,2008,36(12):2306-2311.
[7]王欢,王江涛,任明武,等. 一种鲁棒的多特征融合目标跟踪新算法[J]. 中国图象图形学报,2009(3):489-498.
WANG H,WANG J T,REN M W,et al. A new robust object tracking algorithm by fusing multi-features[J]. Journal of image and graphics,2009,14(3):489-498.(in Chinese)
[8]DANELLJAN M,KHAN F S,FELSBERG M,et al. Adaptive color attributes for real-time visual tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Columbus Ohio,2014.
[9]顾鑫,王海涛,汪凌峰,等. 基于不确定性度量的多特征融合跟踪[J]. 自动化学报,2011,37(5):550-559.
GU X,WANG H T,WANG L F,et al. Fusing multiple features for object tracking based on uncertainty measurement[J]. Acta automatica sinica,2011,37(5):550-559.(in Chinese)
[10]VAN D W J,SCHMID C,VERBEEK J,et al. Learning color names for real-world applications[J]. IEEE transactions on image processing,2009,18(7):1512-1523.
[11]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.
[12]KHAN F S,WEIJER J V,VANRELL M. Modulating shape features by color attention for object recognition[J]. International journal of computer vision,2012,98(1):49-64.
[13]田鹏,吕江花,马世龙,等. 基于局部差别性分析的目标跟踪算法[J]. 电子与信息学报,2017,39(11):2635-2643.
TIAN P,Lü J H,MA S L,et al. Robust object tracking based on local discriminative analysis[J]. Journal of electronics and information technology,2017,39(11):2635-2643.(in Chinese)
[14]YILMAZ A. Kernel-based object tracking using asymmetric kernels with adaptive scale and orientation selection[J]. Machine vision and applications,2011,22(2):255-268.
[15]许婉君,侯志强,余旺盛,等. 基于颜色和空间信息的多特征融合目标跟踪算法[J]. 应用光学,2015,36(5):755-761.
XU W J,HOU Z Q,YU W S,et al. Fusing multi-feature for object tracking algorithm based on color and space information[J]. Journal of applied optics,2015,36(5):755-761.(in Chinese)
[16]LU H,JIA X,YANG M H,et al. Visual tracking via adaptive structural local sparse appearance model[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Springer Berlin Heidelberg,2012.
[17]NEBEHAY G,PFLUGFELDER R. Consensus-based matching and tracking of keypoints for object tracking[C]//Proceedings of the IEEE Winter Conference on Applications of Computer Vision. Colorado,USA,2014.
[18]PREZ P,HUE C,VERMAAK J,et al. Color-based probabilistic tracking[C]//Proceedings of European Conference on Computer Vision. Copenhagen Denmark,2002.
[19]HE S,YANG Q,LAU R,et al. Visual tracking via locality sensitive histograms[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Washington DC,USA,2013.
[20]毕笃彦,库涛,查宇飞,等. 基于颜色属性直方图的尺度目标跟踪算法研究[J]. 电子与信息学报,2016,38(5):1099-1106.
BI D Y,KU T,ZHA Y F,et al. Scale-adaptive object tracking based on color names histogram[J]. Journal of electronics and information technology,2016,38(5):1099-1106.
[21]KRISTAN M,LEONARDIS A,MATAS J,et al. The visual object tracking VOT2016 challenge results[C]//Proceedings of European Conference on Computer Vision. Amsterdam Netherlands,2016.
[22]ZHANG M,XING J,GAO J,et al. Robust visual tracking using joint scale-spatial correlation filters[C]//Proceedings of the IEEE International Conference on Image Processing. Quebec City,Canada,2015.
[23]DANELLJAN M,KHAN F S,FELSBERG M,et al. Accurate scale estimation for robust visual tracking[C]//Proceedings of British Machine Vision Conference. University of Nottingham,2014.
[24]LI Y,ZHU J K. A scale adaptive kernel correlation filter tracker with feature integration[C]//Proceedings of European Conference on Computer Vision. Zurich Switzerland,2014.
[25]BERTINETTO L,VALMADRE J,GOLODETZ S,et al. Staple:complementary learners for real-time tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Lasvegas Nevada,USA,2016.
[26]MA C,YANG X K,ZHANG C Y,et al. Longterm correlation tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Prague Czech Republic,2015.
[27]DANELLJAN M,BHAT G,KHAN FAHAD S,et al. ECO:Efficient convolution operators for tracking[C]//Computer Vision and Pattern Recognition. Lasvegas Nevada,USA,2016.

Memo

Memo:
-
Last Update: 2019-09-30