计算机科学 ›› 2019, Vol. 46 ›› Issue (9): 271-276.doi: 10.11896/j.issn.1002-137X.2019.09.041

• 图形图像与模式识别 • 上一篇    下一篇

基于核相关滤波器和分层卷积特征的长时间目标跟踪

陈威1, 李决龙2, 邢建春1, 杨启亮1, 周启臻1   

  1. (陆军工程大学国防工程学院 南京210007)1;
    (海军海防工程研究中心 北京100841)2
  • 收稿日期:2018-08-15 出版日期:2019-09-15 发布日期:2019-09-02
  • 通讯作者: 陈 威(1994-),男,硕士生,主要研究方向为计算机视觉,E-mail:johnny185@126.com
  • 作者简介:李决龙(1959-),男,硕士,教授,主要研究方向为复杂智能信息系统;邢建春(1964-),男,博士,教授,CCF会员,主要研究方向为复杂智能信息系统;杨启亮(1975-),男,博士,副教授,CCF会员,主要研究方向为复杂智能信息系统;周启臻(1993-),男,博士生,CCF会员,主要研究方向为无线感知与图像处理。
  • 基金资助:
    江苏省自然科学基金项目(BK20151451)

Long-term Object Tracking Based on Kernelized Correlation Filter and Hierarchical Convolution Features

CHEN Wei1, LI Jue-long2, XING Jian-chun1, YANG Qi-liang1, ZHOU Qi-zhen1   

  1. (National Defense Engineering College,Army Engineering University of PLA,Nanjing 210007,China)1;
    (Research Center of Coastal Defense Engineering,Beijing 100841,China)2
  • Received:2018-08-15 Online:2019-09-15 Published:2019-09-02

摘要: 针对长时间目标跟踪中出现的目标形变、尺度变化、目标遮挡以及离开视野等问题,提出一种基于核相关滤波器和分层卷积特征的长时目标跟踪算法。首先,利用预训练的卷积神经网络模型提取分层卷积特征来训练核相关滤波器,进行位置估计。其次,构建目标尺度金字塔,进行尺度估计。最后,为了应对目标遮挡以及离开视野导致跟踪失败的情况,训练一个在线支持向量机进行目标再检测,从而实现长时间目标跟踪。在长时间目标跟踪数据集上的测试结果表明:所提算法的精度分别比其他几种主流跟踪算法HCF,LCT,DSST,KCF和TLD高出7%,15%,17%,21%和50%。

关键词: 长时目标跟踪, 分层卷积特征, 核相关滤波器, 支持向量机

Abstract: Aiming at the problems such as deformation,scale variation,target occlusion,and out of sight during long-term object tracking,this paper proposed a long-term object tracking algorithm based on kernelized correlation filter and hierarchical convolution feature.Firstly,the pre-trained convolution neural network is applied to extract the hierarchical convolution feature,so as to train correlation filter and estimate location.Then the target scale pyramid is constructed to estimate scale.In order to prevent tracking failure caused by target occlusion and tanget leaving the field of vision,an online support vector machine is trained for target re-detection to achieve long-term tracking.Experimental results on long-term object tracking dataset show that the accuracy of the proposed algorithm is 7%,15%,17%,21% and 50% higher than that of HCF,LCT,DSST,KCF and TLD.

Key words: Hierarchical convolution features, Kernelized correlation filter, Long-term object tracking, Support vector machine

中图分类号: 

  • TP391.41
[1]ORON S,BAR-HILLEL A,LEVI D,et al.Locally orderlesstracking[J].International Journal of Computer Vision,2015,111(2):213-228.
[2]BABENKO B,YANG M H,BELONGIE S.Robust object trac-king with online multiple instance learning[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2011,33(8):1619-1632.
[3]BOLME D S,BEVERIDGE J R,DRAPER B A,et al.Visual object tracking using adaptive correlation filters[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2010:2544-2550.
[4]HENRIQUES J F,RUI C,MARTINS P,et al.Exploiting the circulant structure of tracking-by-detection with kernels[C]//European Conference on Computer Vision.Springer-Verlag,2012:702-715.
[5]HENRIQUES J F,RUI C,MARTINS P,et al.High-speedtracking with kernelized correlation filters[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2015,37(3):583-596.
[6]DANELLJAN M,HÄGER G,KHAN F S.Accurate scale estimation for robust visual tracking[C]//British Machine Vision Conference.2014:65.1-65.11.
[7]KALAL Z,MIKOLAJCZYK K,MATAS J.Tracking-Learning-Detection[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2012,34(7):1409-22.
[8]MA C,YANG X,ZHANG C,et al.Long-term correlation trac-king[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2015:5388-5396.
[9]WANG N,YEUNG D Y.Learning a deep compact image representation for visual tracking[C]//International Conference on Neural Information Processing Systems.Curran Associates Inc.,2013:809-817.
[10]WANG L,OUYANG W,WANG X,et al.Visual tracking with fully convolutional networks[C]//IEEE International Confe-rence on Computer Vision.IEEE Computer Society,2015:3119-3127.
[11]MA C,HUANG J B,YANG X,et al.Hierarchical convolutional features for visual tracking[C]//IEEE International Conference on Computer Vision.IEEE,2016:3074-3082.
[12]DENG J,DONG W,SOCHER R,et al.ImageNet:A large-scale hierarchical image database[C]//IEEE Conference on Computer Vision and Pattern Recognition.IEEE,2009:248-255.
[13]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv:1409.1556,2014.
[14]KUMAR B V K V,MAHALANOBIS A,JUDAY R D.Correlation Pattern Recognition[M].Cambridge University Press,2005.
[15]MOUDGIL A,GANDHI V.Long-Term Visual Object Tracking Benchmark[J].arXiv:1712.01358,2017.
[16]DANELLJAN M,HÄGER G,KHAN F,et al.Accurate scaleestimation for robust visual tracking[C]//British Machine Vision Conference.Nottingham:BMVA Press,2014.
[1] 单晓英, 任迎春.
基于改进麻雀搜索优化支持向量机的渔船捕捞方式识别
Fishing Type Identification of Marine Fishing Vessels Based on Support Vector Machine Optimized by Improved Sparrow Search Algorithm
计算机科学, 2022, 49(6A): 211-216. https://doi.org/10.11896/jsjkx.220300216
[2] 陈景年.
一种适于多分类问题的支持向量机加速方法
Acceleration of SVM for Multi-class Classification
计算机科学, 2022, 49(6A): 297-300. https://doi.org/10.11896/jsjkx.210400149
[3] 侯夏晔, 陈海燕, 张兵, 袁立罡, 贾亦真.
一种基于支持向量机的主动度量学习算法
Active Metric Learning Based on Support Vector Machines
计算机科学, 2022, 49(6A): 113-118. https://doi.org/10.11896/jsjkx.210500034
[4] 邢云冰, 龙广玉, 胡春雨, 忽丽莎.
基于SVM的类别增量人体活动识别方法
Human Activity Recognition Method Based on Class Increment SVM
计算机科学, 2022, 49(5): 78-83. https://doi.org/10.11896/jsjkx.210400024
[5] 武玉坤, 李伟, 倪敏雅, 许志骋.
单类支持向量机融合深度自编码器的异常检测模型
Anomaly Detection Model Based on One-class Support Vector Machine Fused Deep Auto-encoder
计算机科学, 2022, 49(3): 144-151. https://doi.org/10.11896/jsjkx.210100142
[6] 侯春萍, 赵春月, 王致芃.
基于自反馈最优子类挖掘的视频异常检测算法
Video Abnormal Event Detection Algorithm Based on Self-feedback Optimal Subclass Mining
计算机科学, 2021, 48(7): 199-205. https://doi.org/10.11896/jsjkx.200800146
[7] 郭福民, 张华, 胡瑢华, 宋岩.
一种基于表面肌电信号的腕部肌力估计方法研究
Study on Method for Estimating Wrist Muscle Force Based on Surface EMG Signals
计算机科学, 2021, 48(6A): 317-320. https://doi.org/10.11896/jsjkx.200600021
[8] 卓雅倩, 欧博.
噪声环境下的人脸防伪识别算法研究
Face Anti-spoofing Algorithm for Noisy Environment
计算机科学, 2021, 48(6A): 443-447. https://doi.org/10.11896/jsjkx.200900207
[9] 雷剑梅, 曾令秋, 牟洁, 陈立东, 王淙, 柴勇.
基于整车EMC标准测试和机器学习的反向诊断方法
Reverse Diagnostic Method Based on Vehicle EMC Standard Test and Machine Learning
计算机科学, 2021, 48(6): 190-195. https://doi.org/10.11896/jsjkx.200700204
[10] 王友卫, 朱晨, 朱建明, 李洋, 凤丽洲, 刘江淳.
基于用户兴趣词典和LSTM的个性化情感分类方法
User Interest Dictionary and LSTM Based Method for Personalized Emotion Classification
计算机科学, 2021, 48(11A): 251-257. https://doi.org/10.11896/jsjkx.201200202
[11] 曹素娥, 杨泽民.
基于聚类分析算法和优化支持向量机的无线网络流量预测
Prediction of Wireless Network Traffic Based on Clustering Analysis and Optimized Support Vector Machine
计算机科学, 2020, 47(8): 319-322. https://doi.org/10.11896/jsjkx.190800075
[12] 徐翔燕, 侯瑞环.
基于GM(1,1)-SVM组合模型的中长期人口预测研究
Medium and Long-term Population Prediction Based on GM(1,1)-SVM Combination Model
计算机科学, 2020, 47(6A): 485-487. https://doi.org/10.11896/JsJkx.190900168
[13] 马创, 吕孝飞, 梁炎明.
基于GA-SVM的农产品质量分类
Agricultural Product Quality Classification Based on GA-SVM
计算机科学, 2020, 47(6A): 517-520. https://doi.org/10.11896/JsJkx.190900184
[14] 宋岩, 胡瑢华, 郭福民, 袁新亮, 熊睿洋.
基于sEMG的改进SVM+BP肌力预测分层算法
Improved SVM+BP Algorithm for Muscle Force Prediction Based on sEMG
计算机科学, 2020, 47(6A): 75-78. https://doi.org/10.11896/JsJkx.190900143
[15] 方梦琳, 唐文兵, 黄鸿云, 丁佐华.
基于模糊信息分解与控制规则的移动机器人沿墙导航
Wall-following Navigation of Mobile Robot Based on Fuzzy-based Information Decomposition and Control Rules
计算机科学, 2020, 47(6A): 79-83. https://doi.org/10.11896/JsJkx.191000158
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!