全局块与局部块协作的相关滤波目标跟踪算法

doi:10.11896/jsjkx.190500078

计算机科学 ›› 2020, Vol. 47 ›› Issue (6): 157-163.doi: 10.11896/jsjkx.190500078

• 计算机图形学&多媒体 • 上一篇下一篇

全局块与局部块协作的相关滤波目标跟踪算法

喻露¹, 胡剑锋^1,2, 姚磊岳^1,2

1 南昌大学信息工程学院南昌330031
2 江西科技学院协同创新中心南昌330098

收稿日期:2019-05-17 出版日期:2020-06-15 发布日期:2020-06-10
通讯作者: 姚磊岳(leiyue_yao@163.com)
作者简介:lu_yu0413@163.com
基金资助:
国家自然科学基金(61762045);江西省科技厅项目(20171BAB202031);江西省科技厅科技攻关项目(20171BBE50060);江西省博士后援助项目(2017KY33);江西省教育厅项目(GJJ161143,GJJ151146);江西省科技厅科技计划专项重点研发项目(20181BBE50018)

Correlation Filter Object Tracking Algorithm Based on Global and Local Block Cooperation

YU Lu¹, HU Jian-feng^1,2, YAO Lei-yue^1,2

1 School of Information Engineering,Nanchang University,Nanchang 330031,China
2 Center of Collaboration and Innovation,Jiangxi University of Technology,Nanchang 330098,China

Received:2019-05-17 Online:2020-06-15 Published:2020-06-10
About author:YU Lu,born in 1994,postgraduate.His main research interests includecompu-ter vision,machine learning and object tracking.
YAO Lei-yue,born in 1982,Ph.D,professor,postgraduate supervisor.His main research interests include compu-ter vision and information processing.
Supported by:
This work was supported by the National Natural Science Foundation of China (61762045),Project of Department of Science and Technology of Jiangxi Province (20171BAB202031),Science and Technology Research Project of Jiangxi Science and Technology Agency (20171BBE50060),Postdoctoral Assistance Project of Jiangxi Province (2017KY33),Project of Department of Education of Jiangxi Province (GJJ161143,GJJ151146),and Science and Technology Plan Special Key Research and Development Project of Jiangxi Science and Technology Department (20181BBE50018)

摘要/Abstract

摘要： 针对传统相关滤波跟踪器在目标尺度变化和部分遮挡时效果不佳等问题,基于KCF提出了一种全局块与局部块协作的分块跟踪算法。该算法首先根据目标的外观特征,对跟踪目标进行水平或垂直分块,并分别训练两个局部滤波器和一个全局滤波器;然后在跟踪过程中使用局部滤波器对局部块进行跟踪,并根据局部块的跟踪结果对全局块的中心点位置进行初始预测。最后通过全局滤波器确定目标的最终位置,并将相关更新和尺度参数反馈给局部滤波器,以更新全局滤波器和局部滤波器。此外,不同于KCF使用单一的HOG特征,该算法合并了CN 特征,改善了HOG 特征对目标形变和运动模糊的表达能力。另外,为解决目标部分遮挡导致的模型漂移问题,提出了一种基于有效局部块来指导模型更新的方法,并给出了有效局部块的评价标准。同时,该算法通过分析前后两帧局部块之间的距离变化对目标的尺度进行估计,解决了因目标尺度变化带来的跟踪失败问题。实验在包含100个视频序列的公共数据集OTB-100上进行,在评价指标上,以 AUC得分为主,DP和OP为辅,对算法的性能进行评估。实验结果表明:所提出的算法能有效应对尺度变化和部分遮挡的问题,AUC得分在KCF的基础上提升了10%,总体性能也比KCF的其他4个改进算法更优,处理速度达到32 fps。

关键词: 部分遮挡, 尺度变化, 分块, 目标跟踪, 相关滤波

Abstract: Traditional correlation filter trackers are not effective in dealing with the problem that caused by target scale changing and partial occlusion.Aiming at sloving this problem,a block tracking algorithm based on KCF was proposed in this paper.In the first step,tracking object is divided horizontally or vertically according to its apperance feature.Then,in the tracking process,local filter is used to track local block,and center point position of the global block can be predicted by the tracked result of the local blocks.At last,the final position of the target is determined by the global filter.The relevant information renewal and scale parameters are fed back to the local filters to update both global and local filter.In addition,different from KCF,which only uses HOG feature,CN feature is imported in the proposed algorithm to enhace the ability of traget deformation tracing and motion blurring tracing.Moreover,in order to solve model drift problem caused by partial occlusion,a method based on effective local block is raised to guide model updating.Criteria of evaluating effective local block also defined.Furthermore,the scale of the target can be effectively estimated by analyzing the distance between local blocks,which solves tracking failure problem caused by target scale changing.The algorithm is evaluated on the public dataset OTB-100,which contains 100 video samples.The results show that the proposed algorithm performs quite well in the situation of scale changing and partial occlusion.Compared with KCF,the accuracy of the proposed algorithm is improved by 10%,and the overall performance is better than other four KCF based algorithms.The processing speed of the algorithm reaches 32 fps.

Key words: Block, Correlation filter, Partial occlusion, Scale change, Visual tracking

中图分类号:

TP391

喻露, 胡剑锋, 姚磊岳. 全局块与局部块协作的相关滤波目标跟踪算法[J]. 计算机科学, 2020, 47(6): 157-163. https://doi.org/10.11896/jsjkx.190500078

YU Lu, HU Jian-feng, YAO Lei-yue. Correlation Filter Object Tracking Algorithm Based on Global and Local Block Cooperation[J]. Computer Science, 2020, 47(6): 157-163. https://doi.org/10.11896/jsjkx.190500078

参考文献

[1]ZHANG W,KANG B S.Recent Advances in Correlation Filter-based Object Tracking:A Review[J].Journal of Image and Graphics,2017,22(8):1017-1033.
[2]MENG L,YANG X.A Survey of Object Tracking Algorithms[J].Acta Automatica Sinica,2019,45(7):1244-1260.
[3]BOLME D S,BEVERIDGE J R,DRAPER B A,et al.Visual Object Tracking using Adaptive Correlation Filters[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2010:2544-2550.
[4]HENRIQUES J F,CASEIRO R,MARTINS P,et al.Exploiting the Circulant Structure of Tracking-by-Detection with Kernels[C]//Proceedings of the 12th European Conference on ComputerVision.Heidelberg:Springer,2012,7575:702-715.
[5]DALAL N,TRIGGS B.Histograms of Oriented Gradients for Human Detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2005:886-893.
[6]HENRIQUES J F,CASEIRO R,MARTINS P,et al.HighSpeed Tracking with Kernelized Correlation Filters[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(3):583-596.
[7]DANELLJAN M,KHAN F S,FELSBERG M,et al.Adaptive Color Attributes for Real-time Visual Tracking[C]//Procee-dings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2014:1090-1097.
[8]LI Y,ZHU J K.A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration[C]//Proceedings of the European Conference on Computer Vision.Heidelberg:Springer,2014:254-265.
[9]DANELLJAN M,HAGER G,KHAN F S,et al.Discriminative Scale Space Tracking[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2017,39(8):1561-1575.
[10]MA C,HUANG J B,YANG X K,et al.Hierarchical Convolutional Features for Visual Tracking[C]//Proceedings of the IEEE International Conference on Computer Vision.Los Alamitos:IEEE Computer Society Press,2015:3074-3082.
[11]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.Los Alamitos:IEEE Computer Society Press,2016:1401-1409.
[12]GALOOGAHI H K,FAGG A,LUCEY S.Learning Background-Aware Correlation Filters for Visual Tracking[C]//Proceedings of the IEEE International Conference on Computer Vision.Los Alamitos:IEEE Computer Society Press,2017:1144-1152.
[13]MUELLER M,SMITH N,Ghanem B.Context-Aware Correlation Filter Tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2017:1387-1395.
[14]DANELLJAN M,HAGER G,KHAN F S,et al.Learning Spatially Regularized Correlation Filters for Visual Tracking[C]//Proceedings of the IEEE International Conference on Computer Vision.Los Alamitos:IEEE Computer Society Press,2015:4310-4318.
[15]DANELLJAN M,HAGER G,KHAN F S,et al.Accurate Sale Estimation for Robust Visual Tracking[C]//Proceedings of British Machine Vision Conference.Swansea:BMVA Press,2014:65.1-65.11.
[16]DANELLJAN M,HAGER G,KHAN F S,et al.Adaptive Decontamination of the Training Set:A Unified Formulation for Discriminative Visual Tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2016:1430-1438.
[17]DANELLJAN M,BHAT G,KHAN F S,et al.ECO:EfficientConvolution Operators for Tracking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2017:6931-6939.
[18]DANELLJAN M,HAGER G,KHAN F S,et al.Convolutional Features for Correlation Filter based Visual Tracking[C]//Proceedings of IEEE International Conference on Computer Vision Workshop.Los Alamitos:IEEE Computer Society Press,2015:621-629.
[19]BHAT G,JOHNANDER J,DANELLJAN M,et al.Unveiling the Power of Deep Tracking[C]//Proceedings of the European Conference on Computer Vision.Heidelberg:Springer,2018:493-509.
[20]ZHU H J,ZHU F,FAN Z F,et al.Visual Object Tracking Method with Motion Estimation and Scale Estimation[J].Computer Science,2017,44(S2):193-198.
[21]QU Z,ZHAO C M.Anti-occlusion Adaptive-scale Object Trac-king Algorithm [J].Computer Science,2018,45(4):296-300.
[22]ZHANG J M,MA S G,SCLAROFF S.MEEM:Robust Trac-king via Multiple Experts using Entropy Minimization[M]// Lecture Notes in Computer Science.Heidelberg:Springer,2014,8694:188-203.
[23]WANG M M,LIU Y,HUANG Z Y.Large Margin Object Tracking With Circulant Feature Maps[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2017:4800-4808.
[24]JING X S,ZOU W J,XIA T,et al.Adaptive ComplementaryLearners with Diversified Color Attributes for Object Tracking[J].Journal of Computer-Aided Design & Computer Graphics,2018,30(12):63-71.
[25]MA C,YANG X K,ZHANG C Y,et al.Long-Term Correlation Tracking[C]//Proceedings of the IEEE Conference on ComputerVision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2015:5388-5396.
[26]LUKEZIC A,VOJIR T,ZAJC L C,et al.Discriminative Correlation Filter with Channel and Spatial Reliability[C]//Procee-dings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos:IEEE Computer Society Press,2016:4847-4856.
[27]MAO N,YANG D D,CAI Y Z,et al.Reliable Patch Tracking Based on Multi-feature Correlation Filter[J].Control Enginee-ring of China,2018,25(4):650-656.
[28]WU Y,LIM,YANG M H.Object Tracking Benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(9):1834-1848.

相关文章 15

[1]	沈祥培, 丁彦蕊. 多检测器融合的深度相关滤波视频多目标跟踪算法 Multi-detector Fusion-based Depth Correlation Filtering Video Multi-target Tracking Algorithm 计算机科学, 2022, 49(8): 184-190. https://doi.org/10.11896/jsjkx.210600004
[2]	纪璎芮, 袁良, 张云泉. 红黑Gauss-Seidel Stencil并行性和局部性优化 Parallelization and Locality Optimization for Red-Black Gauss-Seidel Stencil 计算机科学, 2022, 49(5): 363-370. https://doi.org/10.11896/jsjkx.220100119
[3]	文成宇, 房卫东, 陈伟. 多目标跟踪的对象初始化综述 Object Initialization in Multiple Object Tracking:A Review 计算机科学, 2022, 49(3): 152-162. https://doi.org/10.11896/jsjkx.210200048
[4]	赵越, 余志斌, 李永春. 基于互注意力指导的孪生跟踪算法 Cross-attention Guided Siamese Network Object Tracking Algorithm 计算机科学, 2022, 49(3): 163-169. https://doi.org/10.11896/jsjkx.210300066
[5]	左杰格, 柳晓鸣, 蔡兵. 基于图像分块与特征融合的户外图像天气识别 Outdoor Image Weather Recognition Based on Image Blocks and Feature Fusion 计算机科学, 2022, 49(3): 197-203. https://doi.org/10.11896/jsjkx.201200263
[6]	苏尔. 初等稳定矩阵约化A₀为上Hessenberg型的方法研究 Research on Method of Reducing A₀ to Upper Hessenberg Type with Elementary Stability Matrix 计算机科学, 2021, 48(6A): 649-657. https://doi.org/10.11896/jsjkx.200800063
[7]	朱雨, 庞建民, 徐金龙, 陶小涵, 王军. 面向SW26010处理器的三维Stencil自适应分块参数算法 Adaptive Tiling Size Algorithm for 3D Stencil Computation on SW26010 Many-core Processor 计算机科学, 2021, 48(6): 10-18. https://doi.org/10.11896/jsjkx.200700059
[8]	钱心缘, 吴文渊. 基于R-SIS和R-LWE构建的IBE加密方案 Identity-based Encryption Scheme Based on R-SIS/R-LWE 计算机科学, 2021, 48(6): 315-323. https://doi.org/10.11896/jsjkx.200700215
[9]	陈媛, 惠燕, 胡秀华. 一种自适应尺度与学习速率调整的背景感知相关滤波跟踪算法 Background-aware Correlation Filter Tracking Algorithm with Adaptive Scaling and Learning Rate Adjustment 计算机科学, 2021, 48(5): 177-183. https://doi.org/10.11896/jsjkx.200300109
[10]	程旭, 崔一平, 宋晨, 陈北京, 郑钰辉, 史金钢. 基于时空注意力机制的目标跟踪算法 Object Tracking Algorithm Based on Temporal-Spatial Attention Mechanism 计算机科学, 2021, 48(4): 123-129. https://doi.org/10.11896/jsjkx.200800164
[11]	张开华, 樊佳庆, 刘青山. 视觉目标跟踪十年研究进展 Advances on Visual Object Tracking in Past Decade 计算机科学, 2021, 48(3): 40-49. https://doi.org/10.11896/jsjkx.201100186
[12]	叶阳, 卢奇, 程时伟. 基于质心法的车联网目标跟踪方法与应用 Centroid Method Based Target Tracking and Application for Internet of Vehicles 计算机科学, 2021, 48(11A): 340-344. https://doi.org/10.11896/jsjkx.210200004
[13]	刘彦, 秦品乐, 曾建朝. 基于YOLOv3与分层数据关联的多目标跟踪算法 Multi-object Tracking Algorithm Based on YOLOv3 and Hierarchical Data Association 计算机科学, 2021, 48(11A): 370-375. https://doi.org/10.11896/jsjkx.201000115
[14]	赵会群, 吴凯锋. 一种大数据估价算法 Big Data Valuation Algorithm 计算机科学, 2020, 47(9): 110-116. https://doi.org/10.11896/jsjkx.191000156
[15]	赵钦炎, 李宗民, 刘玉杰, 李华. 基于信息熵的级联Siamese网络目标跟踪 Cascaded Siamese Network Visual Tracking Based on Information Entropy 计算机科学, 2020, 47(9): 157-162. https://doi.org/10.11896/jsjkx.190800160

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

全局块与局部块协作的相关滤波目标跟踪算法

Correlation Filter Object Tracking Algorithm Based on Global and Local Block Cooperation

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0