2.765

2022影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

全天实时跟踪无人机目标的多正则化相关滤波算法

王法胜 李富 尹双双 王星 孙福明 朱兵

王法胜, 李富, 尹双双, 王星, 孙福明, 朱兵. 全天实时跟踪无人机目标的多正则化相关滤波算法. 自动化学报, 2023, 49(11): 2409−2425 doi: 10.16383/j.aas.c220424
引用本文: 王法胜, 李富, 尹双双, 王星, 孙福明, 朱兵. 全天实时跟踪无人机目标的多正则化相关滤波算法. 自动化学报, 2023, 49(11): 2409−2425 doi: 10.16383/j.aas.c220424
Wang Fa-Sheng, Li Fu, Yin Shuang-Shuang, Wang Xing, Sun Fu-Ming, Zhu Bing. All-day and real-time multi-regularized correlation filter for UAV object tracking. Acta Automatica Sinica, 2023, 49(11): 2409−2425 doi: 10.16383/j.aas.c220424
Citation: Wang Fa-Sheng, Li Fu, Yin Shuang-Shuang, Wang Xing, Sun Fu-Ming, Zhu Bing. All-day and real-time multi-regularized correlation filter for UAV object tracking. Acta Automatica Sinica, 2023, 49(11): 2409−2425 doi: 10.16383/j.aas.c220424

全天实时跟踪无人机目标的多正则化相关滤波算法

doi: 10.16383/j.aas.c220424
基金项目: 国家自然科学基金(61972068, 61976042), 国家重点研发计划(2021YFC3320300), 兴辽英才计划(XLYC2007023), 辽宁省高等学校创新人才支持计划(LR2019020)资助
详细信息
    作者简介:

    王法胜:大连民族大学信息与通信工程学院教授. 主要研究方向为计算机视觉, 模式识别. E-mail: wangfasheng@dlnu.edu.cn

    李富:大连民族大学信息与通信工程学院硕士研究生. 主要研究方向为计算机视觉. E-mail: fuliytu@163.com

    尹双双:大连民族大学信息与通信工程学院硕士研究生. 主要研究方向为计算机视觉. E-mail: yss460229828@163.com

    王星:大连民族大学信息与通信工程学院硕士研究生. 主要研究方向为计算机视觉. E-mail: dlnuwangxing@gmail.com

    孙福明:大连民族大学信息与通信工程学院教授. 主要研究方向为计算机视觉, 多媒体技术. 本文通信作者. E-mail: sunfuming@dlnu.edu.cn

    朱兵:哈尔滨工业大学电子与信息工程学院副研究员. 主要研究方向为图像处理, 模式识别. E-mail: zhubing@hit.edu.cn

All-day and Real-time Multi-regularized Correlation Filter for UAV Object Tracking

Funds: Supported by National Natural Science Foundation of China (61972068, 61976042), National Key Research and Development Program of China (2021YFC3320300), Liaoning Revitalization Talents Program (XLYC2007023), and Innovative Talents Program for Liaoning Universities (LR2019020)
More Information
    Author Bio:

    WANG Fa-Sheng Professor at the School of Information and Communication Engineering, Dalian Minzu University. His research interest covers computer vision and pattern recognition

    LI Fu Master student at the School of Information and Communication Engineering, Dalian Minzu University. His main research interest is computer vision

    YIN Shuang-Shuang Master student at the School of Information and Communication Engineering, Dalian Minzu University. Her main research interest is computer vision

    WANG Xing Master student at the School of Information and Communication Engineering, Dalian Minzu University. His main research interest is computer vision

    SUN Fu-Ming Professor at the School of Information and Communication Engineering, Dalian Minzu University. His research interest covers computer vision and multimedia technology. Corresponding author of this paper

    ZHU Bing Associate research fellow at the School of Electronics and Information Engineering, Harbin Institute of Technology. His research interest covers image processing and pattern recognition

  • 摘要: 相关滤波算法(Correlation filter, CF)已广泛应用于无人机目标跟踪. 然而, 受无人机 (Unmanned aerial vehicle, UAV) 平台本身计算性能的制约, 现有的无人机相关滤波跟踪算法大都仅采用手工特征来描述目标的外观, 难以获得目标的全面语义信息. 并且这些跟踪算法仅能较好地进行光照条件良好场景下的跟踪, 而在跟踪夜间场景下的目标时性能严重下降. 此外, 相关滤波跟踪器采用余弦窗口来抑制循环移位产生的边界效应, 缩小了样本提取区域, 产生了训练样本污染的问题, 这不可避免地降低了跟踪器的性能. 针对以上问题, 提出全天实时多正则化相关滤波算法(All-day and real-time multi-regularized correlation filter, AMRCF)跟踪无人机目标. 首先, 引入一个自适应图像增强模块, 在不影响图像各通道颜色比例的前提下, 对获得的图像进行增强, 以提高夜间目标跟踪性能. 其次, 引入一个轻量型的深度网络来提取目标的深度特征, 并与手工特征一起来表示目标的语义信息. 此外, 在算法框架中嵌入高斯形状掩膜, 在抑制边界效应的同时, 有效避免训练样本污染. 最后, 在5个公开的无人机基准数据集上进行充分的实验. 实验结果表明, 所提出的算法与多个先进的相关滤波跟踪器相比, 取得了有竞争力的结果, 且算法的实时速度约为25 fps, 能够胜任无人机的目标跟踪任务.
  • 图  1  AMRCF与其他算法在DTB70上的总体性能比较

    Fig.  1  Overall performance of AMRCF compared with other algorithms on DTB70

    图  2  AMRCF跟踪算法框架图

    Fig.  2  Framework of the proposed AMRCF algorithm

    图  3  原始图像与增强图像的对比(每组图像的第一行是原始图像, 第二行是相应的增强图像)

    Fig.  3  Comparison of original image and enhanced image (The first row of each image set is the original image, and the second row is the corresponding enhanced image)

    图  4  教师网络和学生网络的架构

    Fig.  4  Architectures of the teacher network and the student network

    图  5  边界效应抑制可视化图((a)空间域循环移位产生的带有边界效应的训练样本; (b)加入余弦窗口后, 带有污染的训练样本; (c)高斯形状掩膜可视化图, 样本的中心距离图像中心越近, 其权重越大, 重要性越高, 反之则越低)

    Fig.  5  Visualization of boundary effect suppression ((a) Training samples with boundary effect generated by cyclic shifts in the spatial domain; (b) Training samples with contamination after adding cosine window; (c) Gaussian-shaped mask visualization, the closer the center of the sample is to the center of the image, the higher the weight and importance, and vice versa)

    图  6  AMRCF与其他算法在5个无人机目标跟踪基准上的实验结果

    Fig.  6  Experimental results of AMRCF and other algorithms on five UAV target tracking benchmarks

    图  7  6个无人机目标跟踪算法的跟踪结果在部分序列上的可视化对比

    Fig.  7  Visual comparison of tracking results of six UAV tracking algorithms on selected sequences

    图  8  失败案例的可视化对比

    Fig.  8  Visual comparison of failure cases

    表  1  消融实验结果对比

    Table  1  Comparison of ablation experiment results

    基准数据集评价指标BaselineBaseline+AdaBaseline+CF-VGGBaseline+MBaseline+Ada+CF-VGGBaseline+Ada+CF-VGG+M
    DTB70精确度0.6660.6660.6890.6560.689$\underline{\underline {\boldsymbol{0.726}}} $
    成功率0.4660.4660.4790.4570.479$\underline{\underline {\boldsymbol{0.488}}} $
    UAVDark135精确度0.5930.6020.5980.5900.608$\underline{\underline {\boldsymbol{0.610}}} $
    成功率0.4550.4630.4620.4580.461$\underline{\underline {\boldsymbol{0.464}}} $
    UAVTrack112精确度0.6810.6720.6920.6780.713$\underline{\underline {{0.712} } }$
    成功率0.4670.4630.4690.4660.481$\underline{\underline {\boldsymbol{0.484}}} $
    UAV123精确度0.6930.6930.6890.6740.708$\underline{\underline {{0.694}}} $
    成功率0.4850.4850.4710.4750.4870.478
    VisDrone-SOT2018精确度0.8120.8110.8020.7950.811$ \underline{\underline{{\boldsymbol{0.816}}}} $
    成功率0.6000.6000.5910.5840.5960.598
    下载: 导出CSV

    表  2  消融实验帧率对比

    Table  2  Frame rate comparison of ablation experiment

    基准数据集BaselineBaseline+AdaBaseline+CF-VGGBaseline+MBaseline+Ada+CF-VGG+M
    DTB7034.266234.532927.284132.751626.56060
    UAVDark13525.965321.362222.557223.438314.59290
    UAVTrack11236.596331.961530.620034.664228.57300
    UAV12335.062834.391528.082434.634827.30980
    VisDrone-SOT201833.364132.979027.148631.843425.77150
    平均33.050931.045427.138531.466524.56156
    下载: 导出CSV

    表  3  CF-VGG与教师网络VGG性能对比

    Table  3  Comparison of performance between CF-VGG and teacher network VGG

    基准数据集评价指标BaselineBaseline+Ada+
    M+VGG
    Baseline+Ada+
    M+CF-VGG
    精确度0.66600.70800.7260
    DTB70成功率0.46600.46700.4880
    帧率34.266213.523926.5606
    精确度0.59300.60400.6100
    UAVDark135成功率0.45500.46300.4640
    帧率25.96539.292814.5929
    精确度0.68100.71100.7120
    UAVTrack112成功率0.46700.48200.4840
    帧率36.596314.790628.5730
    下载: 导出CSV

    表  4  各跟踪算法在无人机目标跟踪基准上的帧率比较

    Table  4  Comparison of frame rates of various tracking algorithms on UAV target tracking benchmarks

    DTB70UAVDark135UAVTrack112VisDrone-SOT2018UAV123平均
    MRCF34.266225.965336.596333.364135.062833.0509
    MSCF24.448720.021823.144624.818923.393723.1655
    BACF34.623223.790542.485637.088939.502735.4982
    DSST59.529925.267295.038861.745784.639165.2441
    ECO_HC50.267646.261960.835658.207959.693655.0533
    fDSST$\underline{\underline {137.9438}} $$\underline{\underline {165.0210}} $$\underline{\underline {178.2769}} $$\underline{\underline {146.0930}} $$\underline{\underline {164.2684}} $$\underline{\underline {158.3206}} $
    KCF546.8368291.7405970.2931619.1967894.7070664.5548
    SAMF8.05805.53817.63827.55339.95597.7487
    SRDCF8.02735.512510.48288.074510.29238.4779
    STRCF20.470815.330921.903320.912921.209519.9655
    AutoTrack38.968433.109141.030941.812440.865239.1572
    ARCF21.828817.403622.777521.146322.440021.1192
    DRCF29.937222.018031.831530.208031.977429.1944
    Staple76.825759.085277.722890.285079.147076.6131
    AMRCF26.560614.592928.573025.771527.309824.5616
    下载: 导出CSV

    表  5  AMRCF与无人机目标跟踪算法的性能比较

    Table  5  Performance comparison of AMRCF and UAV target tracking algorithms

    基准数据集评价指标MRCFMSCFAutoTrackDRCFARCFAMRCF
    DTB70精确度0.6660.649$\underline{\underline {0.716}} $0.6360.6940.726
    成功率0.4660.450$\underline{\underline {0.478}} $0.4400.4720.488
    UAVDark135精确度0.593$\underline{\underline {0.600}} $0.5990.4810.5840.610
    成功率0.455$\underline{\underline {0.459}} $0.4540.3880.4480.464
    UAVTrack112精确度0.6810.688$\underline{\underline {0.695}} $0.6750.6720.712
    成功率0.467$\underline{\underline {0.468}} $0.4640.4580.4570.484
    UAV123精确度0.6930.6900.6890.7000.671$\underline{\underline {0.694}} $
    成功率0.485$\underline{\underline {0.483}} $0.4720.4820.4680.478
    VisDrone-SOT2018精确度$\underline{\underline {0.812}} $0.7760.7880.7820.7970.816
    成功率0.6000.5700.5730.5730.584$\underline{\underline {0.598}} $
    下载: 导出CSV

    表  6  各算法在DTB70基准不同属性上的性能比较

    Table  6  Performance comparison of each algorithm on different attributes of the DTB70 benchmark

    属性评价指标SRDCFSTRCFStapleSAMFECO_HCDSSTfDSST
    SV精确度0.4620.5680.4890.4560.5380.4730.543
    成功率0.3590.4170.3490.3390.4310.3610.378
    ARV精确度0.3430.4920.4300.3750.4870.3660.405
    成功率0.2680.3470.3140.2890.3610.2900.275
    OCC精确度0.4780.6170.5280.5000.6390.4230.467
    成功率0.3100.4000.3490.321$\underline{\underline {0.430}} $0.2750.310
    DEF精确度0.2890.5540.4190.3870.5610.3390.390
    成功率0.2080.3900.2830.2930.3910.2610.243
    FCM精确度0.5540.7130.4940.4990.6780.4850.587
    成功率0.3980.4670.3310.3330.4610.3220.388
    IR精确度0.4190.5860.4570.4090.5480.4000.489
    成功率0.3120.3930.3180.3010.3930.2820.326
    OR精确度0.2200.3850.3710.2250.3900.2370.226
    成功率0.2040.2570.2830.2180.2710.2550.153
    OV精确度0.5520.6520.4200.5370.5150.4740.564
    成功率0.3780.4240.2780.3240.3800.3090.381
    BC精确度0.3930.6110.3930.3520.5530.3120.356
    成功率0.2560.3690.2310.2210.3350.1980.225
    SOA精确度0.5690.6770.5290.4990.6540.5280.562
    成功率0.3790.4470.3460.3190.4450.3340.351
    属性评价指标BACFARCFAutoTrackDRCFMSCFMRCFAMRCF
    SV精确度0.545$\underline{\underline {0.707}} $0.6880.5740.6100.6130.735
    成功率0.3980.487$\underline{\underline {0.493}} $0.4460.4500.4510.522
    ARV精确度0.370$\underline{\underline {0.608}} $0.6050.5260.5420.5560.661
    成功率0.2740.393$\underline{\underline {0.405}} $0.3770.3770.3840.442
    OCC精确度0.556$\underline{\underline {0.638}} $0.6310.5850.5850.5870.624
    成功率0.3680.4460.4150.4140.4120.4180.406
    DEF精确度0.4100.654$\underline{\underline {0.670}} $0.5590.6100.6280.748
    成功率0.2820.426$\underline{\underline {0.452}} $0.3920.4190.4160.492
    FCM精确度0.640$\underline{\underline {0.742}} $0.7440.6990.6940.719 0.738
    成功率0.4340.4960.4960.4720.4710.4960.494
    IR精确度0.5370.636$\underline{\underline {0.684}} $0.5940.6030.6150.696
    成功率0.3740.429$\underline{\underline {0.454}} $0.4130.4160.4290.466
    OR精确度0.270$\underline{\underline {0.451}} $0.4390.3460.3850.4120.524
    成功率0.2230.321$\underline{\underline {0.343}} $0.2630.2970.3230.369
    OV精确度0.5750.6420.6900.6110.6290.675$\underline{\underline {0.680}} $
    成功率0.3830.4270.4070.4300.4140.448$\underline{\underline {0.435}} $
    BC精确度0.4910.585$\underline{\underline {0.635}} $0.5940.6100.6160.640
    成功率0.3110.3770.3940.3650.376$\underline{\underline {0.399}} $0.400
    SOA精确度0.641$\underline{\underline {0.730}} $0.7310.7000.6780.6950.694
    成功率0.4210.484$\underline{\underline {0.473}} $0.4530.4520.4710.447
    下载: 导出CSV
  • [1] Zhang F, Ma S P, Yu L X, Zhang Y L, Qiu Z L, Li Z Y. Learning future-aware correlation filters for efficient UAV tracking. Remote Sensing, 2021, 13(20): Article No. 4111 doi: 10.3390/rs13204111
    [2] 孟琭, 杨旭. 目标跟踪算法综述. 自动化学报, 2019, 45(7): 1244-1260

    Meng Lu, Yang Xu. A survey of object tracking algorithms. Acta Automatica Sinica, 2019, 45(7): 1244-1260
    [3] Xu L B, Li Q L, Jiang J, Zou G F, Liu Z, Gao M L. Adaptive spatio-temporal regularized correlation filters for UAV-based tracking. In: Proceedings of the 15th Asian Conference on Computer Vision (ACCV). Kyoto, Japan: Springer, 2020. 391−404
    [4] Henriques J F, Caseiro R, Martins P, Batista J. High-speed tracking with kernelized correlation filters. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 583-596 doi: 10.1109/TPAMI.2014.2345390
    [5] Danelljan M, Hager G, Khan F S, Felsberg M. Learning spatially regularized correlation filters for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV). Santiago, Chile: IEEE, 2015. 4310−4318
    [6] 熊丹, 卢惠民, 肖军浩, 郑志强. 具有尺度和旋转适应性的长时间目标跟踪. 自动化学报, 2019, 45(2): 289-304

    Xiong Dan, Lu Hui-Min, Xiao Jun-Hao, Zheng Zhi-Qiang. Robust long-term object tracking with adaptive scale and rotation estimation. Acta Automatica Sinica, 2019, 45(2): 289-304
    [7] 张伟俊, 钟胜, 徐文辉, Wu Ying. 融合显著性与运动信息的相关滤波跟踪算法. 自动化学报, 2021, 47(7): 1572-1588

    Zhang Wei-Jun, Zhong Sheng, Xu Wen-Hui, Wu Ying. Correlation filter based visual tracking integrating saliency and motion cues. Acta Automatica Sinica, 2021, 47(7): 1572-1588
    [8] Galoogahi H K, Fagg A, Lucey S. Learning background-aware correlation filters for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV). Venice, Italy: IEEE, 2017. 1144−1152
    [9] Wu X D, Xu J, Zhu Z Y, Wang Y N, Zhang Q, Tang S M, et al. Correlation filter tracking algorithm based on spatial-temporal regularization and context awareness. Applied Intelligence, 2022, 52: 17772-17783 doi: 10.1007/s10489-022-03458-8
    [10] 蒲磊, 冯新喜, 侯志强, 查宇飞, 余旺盛. 基于深度空间正则化的相关滤波跟踪算法. 电子学报, 2020, 48(10): 2025-2032

    Pu Lei, Feng Xin-Xi, Hou Zhi-Qiang, Cha Yu-Fei, Yu Wang-Sheng. Correlation filter tracking based on deep spatial regularization. Acta Electronica Sinica, 2020, 48(10): 2025-2032
    [11] Wang F S, Yin S S, Mbelwa J T, Sun F M. Context and saliency aware correlation filter for visual target tracking. Multimedia Tools and Applications, 2022, 81: 27879-27893 doi: 10.1007/s11042-022-12760-z
    [12] Yuan D, Chang X J, Li Z H, He Z Y. Learning adaptive spatial-temporal context-aware correlation filters for UAV tracking. ACM Transactions on Multimedia Computing, Communications, and Applications, 2022, 18(3): Article NO. 70
    [13] Wang L, Li J, Huang B, Chen J, Li X, Wang J, et al. Auto-perceiving correlation filter for uav tracking. IEEE Transactions on Circuits and Systems for Video Technology, 2022, 32(9): 5748-5761 doi: 10.1109/TCSVT.2022.3155731
    [14] 丁新尧, 张鑫. 基于显著性特征的选择性目标跟踪算法. 电子学报, 2020, 48(1): 118-123

    Ding Xin-Yao, Zhang Xin. Visual tracking with salient features and selective mechanism. Acta Electronica Sinica, 2020, 48(1): 118-123
    [15] Bolme D S, Beveridge J R, Draper B A, Lui Y M. Visual object tracking using adaptive correlation filters. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, USA: IEEE, 2010. 2544−2550
    [16] Wang Y B, Wang F S, Wang C, He J J, Sun F M. Learning saliency-aware correlation filters for visual tracking. The Computer Journal, 2022, 65(7): 1846-1859 doi: 10.1093/comjnl/bxab026
    [17] 蒲磊, 冯新喜, 侯志强, 余旺盛. 基于二阶池化网络的鲁棒视觉跟踪算法. 电子学报, 2020, 48(8): 1472-1478

    Pu Lei, Feng Xin-Xi, Hou Zhi-Qiang, Yu Wang-Sheng. Robust visual tracking based on second order pooling network. Acta Electronica Sinica, 2020, 48(8): 1472-1478
    [18] Ma C, Huang J B, Yang X K, Yang M H. Hierarchical convolutional features for visual tracking. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV). Santiago, Chile: IEEE, 2015. 3074−3082
    [19] Javed S, Danelljan M, Khan F S, Khan M H, Felsberg M, Matas J. Visual object tracking with discriminative filters and Siamese networks: A survey and outlook. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(5): 6552-6574
    [20] Zheng G Z, Fu C H, Ye J J, Lin F L, Ding F Q. Mutation sensitive correlation filter for real-time UAV tracking with adaptive hybrid label. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA). Xi'an, China: IEEE, 2021. 503−509
    [21] Ye J J, Fu C H, Lin F L, Ding F Q, An S, Lu G. Multi-regularized correlation filter for UAV tracking and self-localization. IEEE Transactions on Industrial Electronics, 2022, 69(6): 6004-6014 doi: 10.1109/TIE.2021.3088366
    [22] Li Y M, Fu C H, Ding F Q, Huang Z Y, Lu G. AutoTrack: Towards high-performance visual tracking for UAV with automatic spatio-temporal regularization. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, USA: IEEE, 2020. 11920−11929
    [23] Li S Y, Yeung D Y. Visual object tracking for unmanned aerial vehicles: A benchmark and new motion models. In: Proceedings of the Thirty-first AAAI Conference on Artificial Intelligence. San Francisco, California, USA: AAAI, 2017. 4140−4146
    [24] Wang N, Zhou W G, Song Y B, Ma C, Li H Q. Real-time correlation tracking via joint model compression and transfer. IEEE Transactions on Image Processing, 2020, 29: 6123-6135 doi: 10.1109/TIP.2020.2989544
    [25] Fu C H, Cao Z A, Li Y M, Ye J J, Feng C. Onboard real-time aerial tracking with efficient Siamese anchor proposal network. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: Article No. 5606913
    [26] Li B W, Fu C H, Ding F Q, Ye J J, Lin F L. All-day object tracking for unmanned aerial vehicle. IEEE Transactions on Mobile Computing, 2023, 22(8): 4515-4529 doi: 10.1109/TMC.2022.3162892
    [27] Wen L Y, Zhu P F, Du D W, Bian X, Ling H B, Hu Q H, et al. VisDrone-SOT2018: The vision meets drone single-object tracking challenge results. In: Proceedings of the European Conference on Computer Vision Workshops. Munich, Germany: Springer, 2018. 469−495
    [28] Mueller M, Smith N, Ghanem B. A benchmark and simulator for UAV tracking. In: Proceedings of the European Conference on Computer Vision. Amsterdam, The Netherlands: Springer, 2016. 445−461
    [29] Henriques J F, Caseiro R, Martins P, Batista J. Exploiting the circulant structure of tracking-by-detection with kernels. In: Proceedings of the European Conference on Computer Vision. Florence, Italy: Springer, 2012. 702−715
    [30] Danelljan M, Hager G, Khan F S, Felsberg M. Discriminative scale space tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(8): 1561-1575 doi: 10.1109/TPAMI.2016.2609928
    [31] Wang C, Zhang L, Xie L H, Yuan J S. Kernel cross-correlator. In: Proceedings of the Thirty-second AAAI Conference on Artificial Intelligence. New Orleans, USA: AAAI, 2018. 4179−4186
    [32] Zhang Y, Liu G X, Zhang H Y, Huang H L. Robust visual tracker combining temporal consistent constraint and adaptive spatial regularization. Neural Computing and Applications, 2021, 33(14): 8355-8374 doi: 10.1007/s00521-020-05589-w
    [33] Deng C W, He S C, Han Y Q, Zhao B Y. Learning dynamic spatial-temporal regularization for UAV object tracking. IEEE Signal Processing Letters, 2021, 28: 1230-1234 doi: 10.1109/LSP.2021.3086675
    [34] Li F, Tian C, Zuo W M, Zhang L, Yang M H. Learning spatial-temporal regularized correlation filters for visual tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, USA: IEEE, 2018. 4904−4913
    [35] Xu T Y, Feng Z H, Wu X J, Kittler J. Joint group feature selection and discriminative filter learning for robust visual object tracking. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, South Korea: IEEE, 2019. 7950−7960
    [36] Feng S, Hu K L, Fan E, Zhao L P, Wu C D. Kalman filter for spatial-temporal regularized correlation filters. IEEE Transactions on Image Processing, 2021, 30: 3263-3278 doi: 10.1109/TIP.2021.3060164
    [37] Danelljan M, Bhat G, Khan F S, Felsberg M. ECO: Efficient convolution operators for tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Hawaii, USA: IEEE, 2017. 6931−6939
    [38] Zhao J W, Wei F Y, Chen N N, Zhou Z H. Spatial and long-short temporal attention correlation filters for visual tracking. IET Image Processing, 2022, 16(11): 3011-3024 doi: 10.1049/ipr2.12535
    [39] Hua X, Wang X Q, Rui T, Shao F M, Wang D. Light-weight UAV object tracking network based on strategy gradient and attention mechanism. Knowledge-Based Systems, 2021, 224: Article No. 107071 doi: 10.1016/j.knosys.2021.107071
    [40] Zhang Z P, Liu Y F, Li B, Hu W M, Peng H W. Toward accurate pixelwise object tracking via attention retrieval. IEEE Transactions on Image Processing, 2021, 30: 8553-8566 doi: 10.1109/TIP.2021.3117077
    [41] Xu T Y, Feng Z H, Wu X J, Kittler J. Adaptive channel selection for robust visual object tracking with discriminative correlation filters. International Journal of Computer Vision, 2021, 129: 1359-1375 doi: 10.1007/s11263-021-01435-1
    [42] Zhu X F, Wu X J, Xu T Y, Feng Z H, Kittler J. Robust visual object tracking via adaptive attribute-aware discriminative correlation filters. IEEE Transactions on Multimedia, 2022, 24: 301-312 doi: 10.1109/TMM.2021.3050073
    [43] 王科平, 朱朋飞, 杨艺, 费树岷. 多时空感知相关滤波融合的目标跟踪算法. 计算机辅助设计与图形学学报, 2020, 32(11): 1840-1852

    Wang Ke-Ping, Zhu Peng-Fei, Yang Yi, Fei Shu-Min. Target tracking algorithm based on multi-time-space perception correlation filters fusion. Journal of Computer-Aided Design & Computer Graphics, 2020, 32(11): 1840-1852
    [44] Li F, Wu X H, Zuo W M, Zhang D, Zhang L. Remove cosine window from correlation filter-based visual trackers: When and how. IEEE Transactions on Image Processing, 2020, 29: 7045-7060 doi: 10.1109/TIP.2020.2997521
    [45] Tang M, Zheng L Y, Yu B, Wang J Q. Fast kernelized correlation filter without boundary effect. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV). Waikoloa, HI, USA: IEEE, 2021. 2998−3007
    [46] Fu C H, Xu J T, Lin F L, Guo F Y, Liu T C, Zhang Z J. Object saliency-aware dual regularized correlation filter for real-time aerial tracking. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(12): 8940-8951 doi: 10.1109/TGRS.2020.2992301
    [47] Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network. arXiv preprint arXiv: 1503.02531, 2015.
    [48] Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, et al. ImageNet large scale visual recognition challenge. International Journal of Computer Vision, 2015, 115: 211-252 doi: 10.1007/s11263-015-0816-y
    [49] Boyd S, Parikh N, Chu E, Peleato B, Eckstein J. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends in Machine Learning, 2011, 3(1): 1-122
    [50] Huang Z Y, Fu C H, Li Y M, Lin F L, Lu P. Learning aberrance repressed correlation filters for real-time UAV tracking. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, South Korea: IEEE, 2019. 2891−2900
    [51] Bertinetto L, Valmadre J, Golodetz S, Miksik O, Torr P H S. Staple: Complementary learners for real-time tracking. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA: IEEE, 2016. 1401−1409
    [52] Li Y, Zhu J K. A scale adaptive kernel correlation filter tracker with feature integration. In: Proceedings of the European Conference on Computer Vision. Zurich, Switzerlan: Springer, 2014. 254−265
    [53] Wu Y, Lim J, Yang M H. Online object tracking: A benchmark. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Portland, USA: IEEE, 2013. 2411−2418
  • 加载中
图(8) / 表(6)
计量
  • 文章访问数:  366
  • HTML全文浏览量:  97
  • PDF下载量:  134
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-05-23
  • 录用日期:  2023-02-10
  • 网络出版日期:  2023-09-28
  • 刊出日期:  2023-11-22

目录

    /

    返回文章
    返回