多粒度相关滤波视频跟踪方法

doi:10.19678/j.issn.1000-3428.0054917

摘要/Abstract

摘要： 视频跟踪是计算机视觉领域的一个重要研究方向，跟踪算法往往通过融合多种类型的特征来实现较高的性能，但其中多数算法未能充分利用多个特征之间的粒度关系。为此，提出一种基于粒计算思维的多粒度相关滤波视频跟踪算法。对视频图像的特征进行划分，构造出基于各个粒度的相关滤波器并进行独立跟踪，在每帧中根据稳健性评估得分的高低选择最优结果。在此基础上，汇总各帧下的跟踪结果并作为最终输出。在OTB-2013和OTB-2015 2个公开数据集上进行实验，结果表明，与视频跟踪算法DCFNet相比，该算法在空间鲁棒性与时间鲁棒性上的精准度较高，特别是在快速运动、平面内外旋转和尺度变化的情况下，其具有良好的视频处理能力。

关键词: 计算机视觉, 目标跟踪, 粒度关系, 相关滤波, 鲁棒性评估

Abstract: Video tracking is an important direction in research of computer vision.Many tracking algorithms achieve high performance by integrating multiple types of features,but most of them fail to fully exploit the granularity relationship between multiple features.To address the problem,this paper proposes a multi-granularity video tracking algorithm using multi-granulairty correlation filters based on the concept of granular computing.First,the characteristics of video images are divided and the correlation filters based on different granularities are constructed.Then,the correlation filters implement tracking independently,and select the optimal result based on the score of robustness evaluation in each frame.On this basis,the tracking results of each frame are integrated as the final result.Experiments on two open datasets,OTB-2013 and OTB-2015,show that compared with the video tracking algorithm DCFNet,the proposed algorithm has higher accuracy in space and time robustness.It has excellent video tracking performance especially in the case of fast motion,in/out-of-plane rotation and scale change.

Key words: computer vision, target tracking, granularity relationship, correlation filters, robustness assessment

中图分类号:

TP391.4

沈泽君, 丁飞飞, 杨文元. 多粒度相关滤波视频跟踪方法[J]. 计算机工程, 2020, 46(5): 274-281.

SHEN Zejun, DING Feifei, YANG Wenyuan. Video Tracking Method Using Multi-granularity Correlation Filters[J]. Computer Engineering, 2020, 46(5): 274-281.

http://www.ecice06.com/CN/Y2020/V46/I5/274

图/表 10

20200513205118

20200513205122

20200513205126

20200513205130

20200513205134

20200513205137

20200513205142

20200513205146

20200513205151

20200513205156

参考文献

[1] WU Xiaojun,XU Tianyang,XU Wenbo.Review of target tracking algorithms in video based on correlation filter[J].Command Information System and Technology,2017,8(3):1-5.(in Chinese)吴小俊,徐天阳,须文波.基于相关滤波的视频目标跟踪算法综述[J].指挥信息系统与技术,2017,8(3):1-5.
[2] YUAN H,JIANG W T,LIU W J,et al.Visual node prediction for visual tracking[J].Multimedia Systems,2019(2):1-10.
[3] SUI Y,WANG G,ZHANG L.Correlation filter learning toward peak strength for visual tracking[J].IEEE Transactions on Cybernetics,2018,48(4):1290-1303.
[4] LIU Yiming,ZHOU Shangbo.Video tracking algorithm of particle filtering based on multi-feature fusion[J].Computer Engineering,2010,36(22):228-230.(in Chinese)刘一鸣,周尚波.基于多特征融合的粒子滤波视频跟踪算法[J].计算机工程,2010,36(22):228-230.
[5] LIU Qiaoyuan,WANG Yuru,ZHANG Jinling.Research progress of visual tracking methods based on correlation filter[J].Acta Automatica Sinica,2019,45(2):34-44.(in Chinese)刘巧元,王玉茹,张金玲.基于相关滤波器的视频跟踪方法研究进展[J].自动化学报,2019,45(2):34-44.
[6] LU H,JIA X,YANG M H.Visual tracking via adaptive structural local sparse appearance model[C]//Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:1822-1829.
[7] ZHONG W,LU H,YANG M H.Robust object tracking via sparse collaborative appearance model[J].IEEE Transactions on Image Processing,2014,23(5):2356-2368.
[8] BOLME D S,BEVERIDGE J R,DRAPER B A,et al.Visual object tracking using adaptive correlation filters[C]//Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2010:2544-2550.
[9] JOÃO F H,CASEIRO R,MARTINS P,et al.Exploiting the circulant structure of tracking-by-detection with kernels[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2012:702-715.
[10] LI Daxiang,WU Lingfeng,LI Na,et al.Improved SAMF object tracking algorithm[J].Computer Engineering,2019,45(2):258-264.(in Chinese)李大湘,吴玲风,李娜,等.改进的SAMF目标跟踪算法[J].计算机工程,2019,45(2):258-264.
[11] LI Yang,ZHU Jianke.A scale adaptive kernel correlation filter tracker with feature integration[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2014:254-265.
[12] MA Chao,YANG Xiaokang,ZHANG Chongyang,et al.Long-term correlation tracking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:5388-5396.
[13] CHEN Zhi,LIU Peizhong,DU Yongzhao,et al.Long-term correlation tracking via spatial-temporal context[J].The Visual Computer,2019(7):1-18.
[14] WANG Ning,ZHOU Wengang,LI Houqiang.Reliable re-detection for long-term tracking[J].IEEE Transactions on Circuits and Systems for Video Technology,2019,29(3):730-743.
[15] VALMADRE J,BERTINETTO L,HENRIQUES J F,et al.End-to-end representation learning for correlation filter based tracking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:2805-2813.
[16] SONG Y,MA C,GONG L,et al.CREST:convolutional residual learning for visual tracking[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2017:2555-2564.
[17] JIANG Weichuang,ZHANG Junwei,GUI Jiangsheng.Target tracking algorithm based on improved kernel correlation filter[J].Computer Engineering,2018,44(11):228-233.(in Chinese)江维创,张俊为,桂江生.基于改进核相关滤波器的目标跟踪算法[J].计算机工程,2018,44(11):228-233.
[18] HU Cong.Target tracking algorithm based on kernel correlation filtering[D].Guangzhou:South China University of Technology,2019.(in Chinese)胡聪.基于核相关滤波的目标跟踪算法研究[D].广州:华南理工大学,2019.
[19] LUKEZIC A,VOJIR T,ZAJC L C,et al.Discriminative correlation filter with channel and spatial reliability[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:6309-6318.
[20] MUELLER M,SMITH N,GHANEM B.Context-aware correlation filter tracking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:1396-1404.
[21] GALOOGAHI H K,FAGG A,LUCEY S.Learning background-aware correlation filters for visual tracking[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2017:1135-1143.
[22] WANG Ning,ZHOU Wengang,TIAN Qi,et al.Multi-cue correlation filters for robust visual tracking[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:4844-4853.
[23] OU Weiqi,YIN Hui,XU Hongli.A multi-object tracking algorithm based on trajectory reconstruction on Multi-Egocentric video[J].CAAI Transactions on Intelligent Systems,2019,14(2):246-253.(in Chinese)欧伟奇,尹辉,许宏丽.一种基于Multi-Egocentric视频运动轨迹重建的多目标跟踪算法[J].智能系统学报,2019,14(2):246-253.
[24] ZHANG Wentao,XU Zhiguo,ZHENG Lin,et al.Slow moving target detection based on multi-dimensional feature fusion using deep autoencoder[J].Computer Engineering,2019,45(5):143-148,154.(in Chinese)张文涛,许治国,郑霖,等.基于深度自编码多维特征融合的慢动目标检测[J].计算机工程,2019,45(5):143-148,154.
[25] LIU H,COCEA M,DING W.Multi-task learning for intelligent data processing in granular computing context[J].Granular Computing,2018(1):1-17.
[26] MIAO Duoqian.Granular computing:past,present and future[M].Beijing:Science Press,2007.(in Chinese)苗夺谦.粒计算:过去、现在与展望[M].北京:科学出版社,2007.
[27] NGUYEN H T,SMEULDERS A W M.Fast occluded object tracking by a robust appearance filter[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(8):1099-1104.
[28] COMANICIU D,RAMESH V,MEER P.Real-time tracking of non-rigid objects using mean shift[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2000:142-149.
[29] FEI Xia,TANG Hongxiang.Information structures in set-valued information systems from granular computing viewpoint[J].Expert Systems,2018,35(5):e12290.
[30] DALAL N,TRIGGS B.Histograms of oriented gradients for human detection[C]//Proceedings of International Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2005:886-893.
[31] FELZENSZWALB P,GIRSHICK R,MCALLESTER D,et al.Visual object detection with deformable part models[J].Communications of the ACM,2013,56(9):97-105.

选择文件类型/文献管理软件名称

选择包含的内容