融合低通滤波器的孪生网络跟踪算法

doi:10.3778/j.issn.1002-8331.2208-0208

摘要/Abstract

摘要： 针对深层次网络中的填充操作会破坏网络严格的平移不变性，提出了一种改进的孪生神经网络目标跟踪算法（BsSiamCAR）。在SiamCAR基础上，用ResNet-50网络对模板图像和搜索区域进行特征提取时，采用低通滤波器和最大池化相融合的策略，改善平移不变性对深层次网络的影响，提高深层次网络的稳定性。为了解决目标跟踪中背景干扰、尺度变化等复杂场景中的问题，引入通道注意力，注意力机制能够有选择性地突出对跟踪有利的特征通道，增强算法在复杂环境中的鲁棒性。实验结果表明，BsSiamCAR在OTB100、VOT2018、UAV123数据集上较SiamRPN和SiamCAR等多种算法在成功率和精度上均有提升，跟踪速度达到43 FPS。

关键词: 目标跟踪, 孪生网络, 低通滤波器, 通道注意力, 最大池化

Abstract: An improved Siamese network target tracking algorithm（BsSiamCAR） is proposed for deep-level networks in which the padding operation can destroy the strict translational invariance of the network. Based on SiamCAR, when using ResNet-50 for target extraction of template images and search images, a low-pass filter and max-pooling are fused to improve the effect of translation invariance on the deep network and improve the deep network. For the problems in complex scenes such as background interference and scale change in target tracking, channel attention is introduced, which can selectively highlight the feature channels favorable to tracking and enhance the robustness of the algorithm in complex environments. The experimental results show that BsSiamCAR has improved in success rate and accuracy over various algorithms such as SiamRPN and SiamCAR on OTB100, VOT2018, and UAV123 datasets, and the tracking speed reaches 43 FPS.

Key words: target tracking, Siamese network, low-pass filters, channel attention, max-pooling

杨晓强, 刘文昊. 融合低通滤波器的孪生网络跟踪算法[J]. 计算机工程与应用, 2023, 59(23): 237-245.

YANG Xiaoqiang, LIU Wenhao. Siamese Network Tracking Algorithm of Fused Low Pass Filter[J]. Computer Engineering and Applications, 2023, 59(23): 237-245.

参考文献

[1] 束平，许克应，鲍华.多层特征融合和并行自注意力的孪生网络目标跟踪算法[J].计算机应用研究，2022，39（4）：1237-1241.
SHU P，XU K Y，BAO H.Multi?layer feature fusion and parallel self-attention siamese networks for visual tracking[J].Application Research of Computers，2022，39（4）：1237-1241.
[2] 程旭，王莹莹，张年杰，等.基于空间感知的多级损失目标跟踪对抗攻击方法[J].通信学报，2021，42（11）：242-254.
CHENG X，WANG Y Y，ZHANG N J，et al.Multi-level loss object tracking adversarial attack method based on spatial perception[J].Journal on Communications，2021，42（11）：242-254.
[3] BERTINETTO L，VALMADRE J，HENRIQUES J，et al.Fully-convolutional siamese networks for object tracking[C]//European Conference on Computer Vision，2016：850-865.
[4] KRIZHEVSKY A，SUTSKEVER I，HINTON G E.Imagenet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems，2012：1097-1105.
[5] VALMADRE J，BERTINETTO L，HENRIQUES J，et al.End-to-end representation learning for correlation filter based tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition，2017：2805-2813.
[6] LI B，YAN J，WU W，et al.High performancevisual tracking with siamese region proposalnetwork[C]//IEEE Conference on Computer Vision and Pattern Recognition，2018：8971-8980.
[7] ZHU Z，WANG Q，LI B，et al.Distractor-aware siamese networks for visual object tracking[C]//European Conference on Computer Vision，2018：101-117.
[8] ZHANG Z P，PENG H W.Deeper and wider siamese networks for real-time visual tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition，2019：4586-4595.
[9] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[10] LI B，WU W，WANG Q，et al.SiamRPN++：evolution of siamese visual tracking with very deep networks[C]//IEEE Conferenceon Computer Vision and Pattern Recognition，2019：4277-4286.
[11] CHEN Z，ZHONG B，LI G，et al.Siamese box adaptive network for visual tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition，2020：6668-6677.
[12] GUO D，WANG J，CUI Y，et al.SiamCAR：siamese fully convolutional classification and regression for visual tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition，2020：6269-6277.
[13] WU Y，LIM J，YANG M H.Object tracking benchmark[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2015，37（9）：1834-1848.
[14] KRISTAN M，LEONARDIS A，MATAS J，et al.The sixth visual object tracking vot2018 challenge results[C]//European Conference on Computer Vision，2018.
[15] MUELLER M，SMITH N，GHANEM B.A benchmark and simulator for UAV tracking[C]//European Conference on Computer Vision，2016：445-461.
[16] ZHANG R.Making convolutional networks shift-invariant again[C]//International Conference on Machine Learning，2019：7324-7334.
[17] HU J，SHEN L，SUN G.Squeeze-and-excitation networks[C]//IEEE Conference on Computer Vision and Pattern Recognition，2018：7132-7141.
[18] DENG J，DONG W，SOCHER R，et al.Imagenet：a large-scale hierarchical image database[C]//IEEE Conference on Computer Vision and Pattern Recognition，2009：248-255.
[19] HUANG L，ZHAO X，HUANG K.Got-10k：a large high-diversity benchmark for generic object tracking in the wild[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2019，43（5）：1562-1577.
[20] ZHANG Z，PENG H，FU J，et al.Ocean：objectaware anchor-free tracking[C]//European Conference on Computer Vision，2020：771-787.
[21] DANELLJAN M，HAGER G，S F KHAN，et al.Learning spatially regularized correlation filters for visual tracking[C]//IEEE International Conference on Computer Vision，2015：4310-4318.
[22] 王玲，周磊，王鹏，等.基于注意力机制和孪生网络的跟踪算法研究[J].计算机工程与应用，2022，58（23）：161-168.
WANG L，ZHOU L，WANG P，et al.Research on tracking algorithm based on attention mechanism and siamese network[J].Computer Engineering and Applications，2022，58（23）：161-168.
[23] DANELLJAN M，BHAT G，KHAN F S，et al.ECO：efficient convolution operators for tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition，2017：6638-6646.
[24] DANELLJAN M，BHAT G，KHAN F S，et al.Atom：accurate tracking by overlap maximization[C]//IEEE Conference on Computer Vision and Pattern Recognition，2019：4660-4669.
[25] BERTINETTO L，VALMADRE J，GOLODETZ S.Complementary learners for real-time tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition，2016：1401-1409.
[26] CAO Z，FU C，YE J，et al.HiFT：hierarchical feature transformer for aerial tracking[C]//International Conference on Computer Vision，2021：15457-15466.
[27] DU F，LIU P，ZHAO W，et al.Correlation-guided attention for corner detection based visual tracking[C]//IEEE Conference on Computer Vision and Pattern Recognition，2020：6836-6845.
[28] WOO S，PARK J，LEE J Y，et al.CBAM：convol-utional block attention module[C]//European Conference on Computer Vision，2018：3-19.
[29] LIU Y，SHAO Z，HOFFMANN N.Global attention mechanism：retain information to enhance channel-spatial interactions[J].arXiv：2112.05561，2021.
[30] LIU H，LIU F，FAN X，et al.Polarized self-attention：towards high-quality pixel-wise regression[J].arXiv：2107.00782，2021.