时间驱动的异常学习相关滤波器的目标跟踪

程月英, 邓丽珍, 彭浩, 李飞

程月英, 邓丽珍, 彭浩, 李飞. 时间驱动的异常学习相关滤波器的目标跟踪[J]. 信号处理, 2021, 37(1): 28-39. DOI: 10.16798/j.issn.1003-0530.2021.01.004
引用本文: 程月英, 邓丽珍, 彭浩, 李飞. 时间驱动的异常学习相关滤波器的目标跟踪[J]. 信号处理, 2021, 37(1): 28-39. DOI: 10.16798/j.issn.1003-0530.2021.01.004
shu
CHENG Yueying, DENG Lizhen, PENG Hao, LI Fei. Aberrance Learning via Time-driven Correlation Filter for Object Tracking[J]. JOURNAL OF SIGNAL PROCESSING, 2021, 37(1): 28-39. DOI: 10.16798/j.issn.1003-0530.2021.01.004
Citation: CHENG Yueying, DENG Lizhen, PENG Hao, LI Fei. Aberrance Learning via Time-driven Correlation Filter for Object Tracking[J]. JOURNAL OF SIGNAL PROCESSING, 2021, 37(1): 28-39. DOI: 10.16798/j.issn.1003-0530.2021.01.004
shu

时间驱动的异常学习相关滤波器的目标跟踪

  • 南京邮电大学通信与信息工程学院

详细信息

  • 中图分类号: TP391

Aberrance Learning via Time-driven Correlation Filter for Object Tracking

  • School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications

摘要

    摘要
  • 摘要: 为了解决传统的相关滤波跟踪算法在复杂环境中容易跟踪失败的问题，本文提出时间驱动的异常学习相关滤波器，旨在提高模型在复杂环境下的适应性，实现安全有效的目标跟踪。通过引入结合异常学习的时间正则项，该模型不仅可以结合滤波器响应相似度和时间域特征搜索到目标，达到抑制异常的效果，还可以提高外观模型在时域中的鲁棒性，缓解时间滤波器退化。另外，本文采用交替方向乘子法(Alternating Direction Method of Multipliers，ADMM)算法实现模型的优化过程，大大减少模型的计算复杂度。大量的实验结果证实了所提出的跟踪算法性能的优越性。
    Abstract: In order to solve the problem that the traditional correlation filter tracking algorithm is easy to fail in complex environments, this paper proposes time-driven correlation filter with aberrance learning (ALTCF) to improve the adaptability of the model in complex environments and achieve safe and effective object tracking. By introducing temporal regularization term with aberrance learning, the model in this paper can not only search for objects by combining the similarity of filter response maps and temporal features to achieve the effect of suppressing aberrance, but also improve the robustness of appearance model and alleviate temporal filter degradation. In addition, this paper uses the alternating direction method of multipliers (ADMM) algorithm to achieve the optimization process of the model, which greatly reduces the computational complexity of the model. A large number of experiments confirm the superiority of ALTCF tracking performance.
    • HTML全文
    • 参考文献(29)
  • [1] 卢湖川, 李佩, 王栋. 目标跟踪算法综述[J]. 模式时别与人工智能, 2018, 31(1): 61-76.
    [2] Lu Huchuan, Li Peixia, Wang Dong. Visual Object Tracking: A Survey[J]. Pattern Recognition and Artificial Intelligence, 2018, 31(1): 61-76.(in Chinese)
    [3] 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.
    [4] Lin Z, Yuan C. Robust Visual Tracking in Low-Resolution Sequence[J], IEEE International Conference on Image Processing (ICIP), Athens, 2018: 4103-4107.
    [5] Zhao H, Yang G, Wang D, et al. Lightweight Deep Neural Network for Real-Time Visual Tracking with Mutual Learning[J], IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, 2019: 3063-3067.
    [6] 张能波, 苏振斌, 谢维信．Lasso约束下融合光流信息的DCF目标跟踪算法[J]. 信号处理, 2019, 35(5): 911-918.
    [7] Zhang Nengbo, Su Zhenbin, Xie Weixin. DCF Visual Object Tracking Algorithm with Lasso Constraints and Fusion Optical Flow[J]. Journal of Signal Processing, 2019, 35(5): 911-918.(in Chinese)
    [8] Danelljan M, Hger G, Khan F S, et al. Learning spatially regularized correlation filters for visual tracking[J]. IEEE International Conference on Computer Vision, Santiago, 2015: 4310-4318.
    [9] Li Feng, Tian Cheng, Zuo Wangmeng. Learning spatial-temporal regularized correlation filters for visual tracking[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2018: 4904-4913.
    [10] Galoogahi H K, Fagg A, Lucey S. Learning background-aware correlation filters for visual tracking[J]. IEEE International Conference on Computer Vision, 2017: 1135-1143.
    [11] Wang Mengmeng, Liu Yong, Huang Zeyi. Large Margin Object Tracking with Circulant Feature Maps[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2017: 4800-4808.
    [12] Choi J, Chang H J, Yun S, et al. Attentional Correlation Filter Network for Adaptive Visual Tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition., 2017: 4828-4837.
    [13] Huang Ziyuan, Fu Changhong, Li Yiming. Learning. Aberrance Repressed Correlation Filters for Real-Time UAV Tracking[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2019: 2891-2900.
    [14] 胡正平, 尹艳华, 顾剑新. 位置-尺度异空间协调的多特征选择相关滤波目标跟踪算法[J]. 信号处理, 2019, 35(12): 1979-1989.
    [15] Hu Zhengping, Yin Yanhua, Gu Jianxin. Multi-feature Selection Correlated Filtering TArget Tracking Algorithms Based on Location-Scale Different Space Coordination[J]. Journal of Signal Processing, 2019, 35(12): 1979-1989.(in Chinese)
    [16] Xu Cheng, Yi feng, et al. Object Tracking via Temporal Consistency Dictionary Learning[J]. IEEE Transactions on Systems Man and Cybernetics Systems, 2017, 47(4): 628-638.
    [17] Crammer K, Dekel O, Keshet J, et al. Online Passive-Aggressive Algorithms[J]. Journal of Machine Learning Research, 2006, 7(3): 551-585.
    [18] Han Chao, Tan YunKun, Zhu JinHui. Online Feature Selection of Class Imbalance via PA Algorithm[J]. Journal of Computer Science and Technology, 2016, 31(4): 673-682.
    [19] Danelljan M, Bhat G, Khan F S, et al. ECO: Efficient Convolution Operators for Tracking[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2017: 6931-6939.
    [20] Danelljan M, Robinson A, Khan F S, et al. Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking[J]. European Conference on Computer Vision, 2016: 472-488.
    [21] Danelljan M, H?ger G, Khan F S, et al. Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2016: 1430-1438.
    [22] Mueller M, Smith N, Ghanem B. Context-aware correlation filter tracking[J]. IEEE Conference on Computer Vision and Pattern Recognition, 2017, 1387-1395.
    [23] Bibi A, Mueller M, Ghanem B. Target Response Adaptation for Correlation Filter Tracking[M]. Springer International Publishing, 2016.
    [24] Li Yang, Zhu Jianke. A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration[C]//European Conference on Computer Vision. Springer, Cham, 2014: 254-265.
    [25] Zhang Jianming, Ma Shugao, Sclaroff S. MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization[C]// European Conference on Computer Vision. Springer, Cham, 2014: 188-203.
    [26] Dai?Kenan, Wang?Dong, Lu Huchuan, et al. Visual Tracking via Adaptive Spatially-Regularized Correlation Filters[C]// 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA, IEEE, 2019:?4665-4674.
    [27] Wu Yi,?Lim Jongwoo, Yang Ming-Hsuan. Online Object Tracking: A Benchmark[C]//IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, 2013: 2411-2418.
    [28] Wu Yi,?Lim Jongwoo, Yang Ming-Hsuan. Object Tracking Benchmark[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1834-1848.
    [29] Liang Pengpeng, Blasch Erik, Ling Haibin. Encoding color information for visual tracking: Algorithms and benchmark.[J]. IEEE Transactions on Image Processing, 2015, 24(12): 5630-5644.
    • 相关文章
    • 施引文献(1)

  • 期刊类型引用(0)

    其他类型引用(1)

    • 资源附件(0)
计量
  • 文章访问数:  174
  • HTML全文浏览量:  13
  • PDF下载量:  180
  • 被引次数: 1
出版历程
  • 收稿日期:  2020-06-23
  • 修回日期:  2020-09-02
  • 发布日期:  2021-01-24

目录

摘要
HTML全文
    参考文献(29)
    相关文章
    施引文献(1)
    资源附件(0)

    /

    返回文章
    返回

    版权所有 © 2009 《信号处理》 编辑部  京ICP备12041980号-1

    地址：北京市西城区鼓楼西大街41号  电话：010-64010656  Email：xhcl@signal.org.cn

    本系统由 北京仁和汇智信息技术有限公司 开发  百度统计