基于多特征和尺度估计的KCF_MTSA算法

doi:10.19678/j.issn.1000-3428.0058414

摘要/Abstract

摘要： 多模板尺度自适应核相关滤波器（KCF_MTSA）跟踪算法在目标移动模糊、旋转和尺度变化时跟踪距离精度与成功率较低。针对该问题，提出一种结合多特征和尺度估计的改进KCF_MTSA目标跟踪算法。采用方向梯度直方图和颜色名两种特征对目标进行表征，在训练阶段分别使用多模板核相关滤波器对上述特征进行训练，同时在检测阶段将两个滤波器的响应以权重形式进行自适应融合获取响应图实现目标定位，并使用一维相关滤波器进行目标尺度估计。实验结果表明，该算法的跟踪距离精度和准确率较改进前KCF_MTSA算法有明显提升，其距离精度和准确率分别提高15.8%和28.5%。

Abstract: The Kernelized Correlation Filter based on Multiple-Template Scale Adaptation(KCF_MTSA)tracking algorithm encounters a reduction in the tracking range precision and success rate when the target moves blurred,rotates and scales change rapidly.To address the problem,this paper proposes an improved KCF_MTSA target tracking algorithm combining multiple features and scale estimation.The Histogram of Oriented Gradient (HOG) and Color Name(CN)are used to represent the target.In the training phase,the multiple template Kernelized Correlation Filter (KCF) is used to train the above features.At the same time,in the detection phase,the responses of the two filters are adaptively fused in the form of weight to obtain the response map to realize the target localization,and the one-dimensional correlation filter is used to estimate the target scale.Experimental results show that the tracking range precision and accuracy of the proposed algorithm are significantly higher than the original KCF_MTSA algorithm,it improves the range precision and accuracy by 15.8% and 28.5% respectively.

Key words: Kernelized Correlation Filter(KCF), adaptive feature fusion, object tracking, Color Name(CN) feature, multiple templates

中图分类号:

TP391.41

尚桠朝, 孟令军. 基于多特征和尺度估计的KCF_MTSA算法[J]. 计算机工程, 2021, 47(3): 102-108,116.

SHANG Yachao, MENG Lingjun. KCF_MTSA Algorithm Based on Multiple Features and Scale Estimation[J]. Computer Engineering, 2021, 47(3): 102-108,116.

https://www.ecice06.com/CN/Y2021/V47/I3/102

图/表 6

20210322171114

20210322171118

20210322171122

20210322171125

20210322171205

20210322171208

参考文献

[1] TIAN Bin,YAO Qingming,GU Yuan,et al.Video processing techniques for traffic flow monitoring:a survey[C]//Proceedings of 2011 IEEE Conference on Intelligent Transportation Systems.Washington D.C.,USA:IEEE Press,2011:1103-1108.
[2] BROWN M,FUNKE J,ERLIEN S,et al.Safe driving envelopes for path tracking in autonomous vehicles[J].Control Engineering Practice,2017,61(4):307-316.
[3] AGGARWAL J K,XIA L.Human activity recognition from 3D data:a review[J].Pattern Recognition Letters,2014,48(10):70-80.
[4] XU Tao,MA Ke,LIU Caihua.Multi object pedestrian tracking based on deep learning[J].Journal of Jilin University(Engineering and Technology Edition),2021,51(1):27-38.(in Chinese)徐涛,马克,刘才华.基于深度学习的行人多目标跟踪方法[J].吉林大学学报(工学版),2021,51(1):27-38.
[5] MENG Lu,LI Chengxin.Brief review of object tracking algorithms in recent years:correlated filtering and deep learning[J].Journal of Image and Graphics,2019,24(7):1011-1016.(in Chinese)孟琭,李诚新.近年目标跟踪算法短评——相关滤波与深度学习[J].中国图象图形学报,2019,24(7):1011-1016.
[6] LU Huchuan,LI Peixia,WANG Dong.Visual object tracking:a survey[J].Pattern Recognition and Artifical Intelligence,2018,31(1):61-76.(in Chinese)卢湖川,李佩霞,王栋.目标跟踪算法综述[J].模式识别与人工智能,2018,31(1):61-76.
[7] HENRIQUES J F,RUI C,MARTINS P,et al.High-speed tracking with kernelized correlation filters[J].IEEE Transactions on Pattern Analysis and Marchine Intelligence,2015,37(3):583-596.
[8] LI Yang,ZHU Jianke.A scale adaptive kernel correlation filters tracker with feature integration[C]//Proceedings of 2014 European Conference on Computer Vision.Berlin,Germany:Springer,2014:254-265.
[9] DANELLJAN M,HAGER G,KHAN F S,et al.Discriminative scale space tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(8):1561-1575.
[10] BIBI A,GHANEM B.Multi-template scale-adaptive kernelized correlation filters[C]//Proceedings of 2015 International Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:50-57.
[11] BERTINETTO L,VALMADRE J,GOLODETZ S.Staple:complementary learners for real-time tracking[C]//Proceedings of 2016 International Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:1401-1409.
[12] KIANI H,FAGG A,LUCEY S.Learning background-aware correlation filters for visual tracking[C]//Proceedings of 2017 International Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:1135-1143.
[13] DANELLJAN M,ROBINSON A,KHAN F S,et al.Beyond correlation filters:learning continus convolution operators for visual tracking[C]//Proceedings of 2016 European Conference on Computer Vision.Berlin,Germany:Springer,2016:472-488.
[14] DANELLJAN M,BHAT G,SHAHBAZKHAN F,et al.Eco:efficient convolution operators for tracking[C]//Proceedings of 2017 International Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:6638-6646.
[15] SQUARES R L,RIFKIN R,YEO G W,et al.Regularized least-squares classification[EB/OL].[2020-04-10].https://www.researchgate.net/publication/2833962_Regularized_Least-Squares_Classification.
[16] HUANG Yuqing,LI Leimin,HU Hong.Particle filter tracking combined with HOG and ARMA model[J].Computer Engineering,2012,38(22):126-129.(in Chinese)黄玉清,李磊民,胡红.融合HOG与ARMA模型的粒子滤波跟踪[J].计算机工程,2012,38(22):126-129.
[17] DANELLJAN M,KHAN F S,FELSBERG M.Adaptive color attributes for real-time visual tracking[C]//Proceedings of 2014 International Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:1090-1097.
[18] BOLME D S,BEVERIDGE J R,DRAPER B A,et al.Visual object tracking using adaptive correlation filters[C]//Proceedings of 2010 International Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2010:2544-2550.
[19] HU Yunceng,LU Hong,YANG Chen,et al.Scale adaptive tracking algorithm combining DSST and KCF[J].Computer Engineering and Design,2019,40(12):3563-3568.(in Chinese)胡云层,路红,杨晨,等.融合DSST和KCF的尺度自适应跟踪算法[J].计算机工程与设计,2019,40(12):3563-3568.
[20] WU Y,LIM J,YANG M H,et al.Object tracking benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1834-1848.
[21] MUELLER M,SMITH N,GHANEM B.Context-aware correlation filter tracking[C]//Proceedings of 2017 International Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:1396-1404.
[22] BIBI A,MUELLER M,GHANEM B.Target response adaptation for correlation filter tracking[C]//Proceedings of 2016 European Conference on Computer Vision.Berlin,Germany:Springer,2016:419-433.

选择文件类型/文献管理软件名称

选择包含的内容