基于多传感器融合的目标追踪算法研究

目标追踪是计算机视觉领域的重要分支，机器通过视觉对视频中的目标以边 界框的形式进行持续定位，广泛应用于自动驾驶、视频监控和机器人导航等领域。 随着工业技术的发展，新型传感器如深度、红外以及事件传感器可以捕获多种类 型的数据，这些数据统一称为多模态数据。通过将其与相机传感器获得的 RGB 数 据融合，在如黑夜、背景杂乱等复杂环境下可以获得更鲁棒和准确的追踪结果，是 目前热点研究方向，具有很好的研究意义和应用价值。

本文以基于多传感器融合的目标追踪为研究方向，其核心问题是如何有效融 合传感器捕获的多模态数据。通过回顾现有研究，本文深入探索了用于目标追踪 的多模态数据融合方法。目前的多模态追踪算法如视觉-深度(RGB-Depth)、视 觉-红外(RGB-Thermal)和视觉-事件(RGB-Event)算法相比单模态追踪算法性 能􏰀升十分有限，并且需要不同的框架设计以应对不同的模态融合，难以实现统 一的多模态追踪。由此，本文􏰀出了基于注意力机制的 RGBD 多模态融合算法和 基于频域调制的统一多模态追踪算法。本文针对基于多传感器融合的目标追踪算 法进行了研究并取得了以下成果:我们􏰀出了基于注意力机制的 RGBD 多模态融 合算法。由于现有的 RGBD 融合方法中模态间信息交互不充分，因此我们引入了 注意力机制加强模态交互的同时建模模态间的共有特征和特有特征，有效􏰀高了 RGBD 目标追踪的性能，显著优于其他算法。除此之外我们􏰀出了基于频域调制 的统一多模态追踪算法。受到多模态数据在频域中互补的共性的启发，本文基于 设计的频域调制融合机制实现了统一的 RGBD、RGBT 以及 RGBE 目标追踪算法 框架，其可以自适应的滤除不同模态间的干扰信息并融合互补的线索。在下游任 务的 DepthTrack、LasHeR 和 VisEvent 等多个数据集上的实验表明，该算法具备通 用性的同时兼有强大的性能，在各种多模态追踪任务中优于其他所有算法。

[1] BOLME D S, BEVERIDGE J R, DRAPER B A, et al. Visual object tracking using adaptive correlation filters[J/OL]. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010: 2544-2550. https://api.semanticscholar.org/CorpusID:2451356.
[2] HENRIQUES J F, CASEIRO R, MARTINS P, et al. High-Speed Tracking with Kernelized Correlation Filters[J/OL]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 37: 583-596. https://api.semanticscholar.org/CorpusID:5378407.
[3] DANELLJAN M, KHAN F S, FELSBERG M, et al. Adaptive Color Attributes for Real-Time Visual Tracking[J/OL]. 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014: 1090-1097. https://api.semanticscholar.org/CorpusID:11907849.
[4] BERTINETTO L, VALMADRE J, HENRIQUES J F, et al. Fully-Convolutional Siamese Net- works for Object Tracking: abs/1606.09549[A/OL]. 2016. https://api.semanticscholar.org/Co rpusID:14309034.
[5] LI B, YAN J, WU W, et al. High Performance Visual Tracking with Siamese Region Proposal Network[J/OL]. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 8971-8980. https://api.semanticscholar.org/CorpusID:52255840.
[6] DANELLJAN M, BHAT G, KHAN F S, et al. ATOM: Accurate Tracking by Overlap Max- imization[J/OL]. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2018: 4655-4664. https://api.semanticscholar.org/CorpusID:53712235.
[7] BHAT G, DANELLJAN M, GOOL L V, et al. Learning Discriminative Model Prediction for Tracking[J/OL]. 2019 IEEE/CVF International Conference on Computer Vision (ICCV), 2019: 6181-6190. https://api.semanticscholar.org/CorpusID:118637813.
[8] YU Y, XIONG Y, HUANG W, et al. Deformable Siamese Attention Networks for Visual Object Tracking[J/OL]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020: 6727-6736. https://api.semanticscholar.org/CorpusID:215754230.
[9] FU Z, LIU Q, FU Z, et al. STMTrack: Template-free Visual Tracking with Space-time Memory Networks[J/OL]. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021: 13769-13778. https://api.semanticscholar.org/CorpusID:232478557.
[10] GUO D, SHAO Y, CUI Y, et al. Graph Attention Tracking[J/OL]. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020: 9538-9547. https://api.semantic scholar.org/CorpusID:227126492.
[11] CHEN X, YAN B, ZHU J, et al. Transformer Tracking[J/OL]. 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021: 8122-8131. https://api.semanticscho lar.org/CorpusID:232404168.
[12] CUI Y, CHENG J, WANG L, et al. MixFormer: End-to-End Tracking with Iterative Mixed Attention[J/OL]. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022: 13598-13608. https://api.semanticscholar.org/CorpusID:247595120.
[13] YE B, CHANG H, MA B, et al. Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework: abs/2203.11991[A/OL]. 2022. https://api.semanticscholar.org/Co rpusID:247618649.
[14] KART U, KÄMÄRÄINEN J, MATAS J, et al. Depth Masked Discriminative Correlation Filter [J/OL]. 2018 24th International Conference on Pattern Recognition (ICPR), 2018: 2112-2117. https://api.semanticscholar.org/CorpusID:3525830.
[15] SONG S, XIAO J. Tracking revisited using RGBD camera: Unified benchmark and baselines [C]//Proceedings of the IEEE international conference on computer vision. 2013: 233-240.
[16] WANG Q, FANG J, YUAN Y. Multi-cue based tracking[J/OL]. Neurocomputing, 2014, 131: 227-236. https://api.semanticscholar.org/CorpusID:4856025.
[17] MESHGI K, ICHI MAEDA S, OBA S, et al. An occlusion-aware particle filter tracker to handle complex and persistent occlusions[J/OL]. Comput. Vis. Image Underst., 2016, 150: 81-94. https://api.semanticscholar.org/CorpusID:46357201.
[18] YAN S, YANG J, KÄPYLÄ J, et al. Depthtrack: Unveiling the power of rgbd tracking[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021: 10725- 10733.
[19] XIAO J, STOLKIN R, GAO Y, et al. Robust Fusion of Color and Depth Data for RGB-D Target Tracking Using Adaptive Range-Invariant Depth Models and Spatio-Temporal Consis- tency Constraints[J/OL]. IEEE Transactions on Cybernetics, 2018, 48: 2485-2499. https: //api.semanticscholar.org/CorpusID:2383049.
[20] SHI H, GAO C, SANG N. Using consistency of depth gradient to improve visual tracking in RGB-D sequences[C]//2015 Chinese Automation Congress (CAC). IEEE, 2015: 518-522.
[21] WANG Y, WEI X, SHEN H, et al. Robust fusion for RGB-D tracking using CNN features[J]. Applied Soft Computing, 2020, 92: 106302.
[22] BIBI A, ZHANG T, GHANEM B. 3d part-based sparse tracker with automatic synchroniza- tion and registration[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016: 1439-1448.
[23] LIU Y, JING X, NIE J, et al. Context-Aware Three-Dimensional Mean-Shift With Occlusion Handling for Robust Object Tracking in RGB-D Videos[J/OL]. IEEE Transactions on Multi- media, 2019, 21: 664-677. https://api.semanticscholar.org/CorpusID:67869284.
[24] KART U, LUKEZIC A, KRISTAN M, et al. Object tracking by reconstruction with view- specific discriminative correlation filters[C]//Proceedings of the IEEE/CVF conference on com- puter vision and pattern recognition. 2019: 1339-1348.
[25] ZHAO H, CHEN J, WANG L, et al. ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D Data[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 5126-5135.
[26] ZHU Y, LI C, LUO B, et al. Dense feature aggregation and pruning for RGBT tracking[C]// Proceedings of the 27th ACM International Conference on Multimedia. 2019: 465-472.
[27] ZHANG L, DANELLJAN M, GONZALEZ-GARCIA A, et al. Multi-modal fusion for end-to-end RGB-T tracking[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. 2019: 0-0.
[28] ZHANG P, ZHAO J, BO C, et al. Jointly modeling motion and appearance cues for robust RGB-T tracking[J]. IEEE Transactions on Image Processing, 2021, 30: 3335-3347.
[29] ZHANG T, LIU X, ZHANG Q, et al. SiamCDA: Complementarity-and distractor-aware RGB- T tracking based on Siamese network[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2021, 32(3): 1403-1417.
[30] LI C, LIU L, LU A, et al. Challenge-aware RGBT tracking[C]//European Conference on Com- puter Vision. Springer, 2020: 222-237.
[31] XIAO Y, YANG M, LI C, et al. Attribute-based progressive fusion network for rgbt tracking [C]//Proceedings of the AAAI Conference on Artificial Intelligence: Vol. 36. 2022: 2831-2838.
[32] HUI T, XUN Z, PENG F, et al. Bridging Search Region Interaction With Template for RGB- T Tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 13630-13639.
[33] GEHRIG D, REBECQ H, GALLEGO G, et al. Asynchronous, photometric feature track- ing using events and frames[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 750-765.
[34] LIU H, MOEYS D P, DAS G, et al. Combined frame-and event-based detection and tracking [C]//2016 IEEE International Symposium on Circuits and systems (ISCAS). IEEE, 2016: 2511- 2514.
[35] HUANG J, WANG S, GUO M, et al. Event-guided structured output tracking of fast-moving objects using a celex sensor[J]. IEEE Transactions on Circuits and Systems for Video Technol- ogy, 2018, 28(9): 2413-2417.
[36] YANG Z, WU Y, WANG G, et al. DashNet: A hybrid artificial and spiking neural network for high-speed object tracking[A]. 2019.
[37] FUKUSHIMA K. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J]. Biological cybernetics, 1980, 36(4): 193-202.
[38] LECUN Y, BOSER B E, DENKER J S, et al. Backpropagation Applied to Handwritten Zip Code Recognition[J/OL]. Neural Computation, 1989, 1: 541-551. https://api.semanticscholar. org/CorpusID:41312633.
[39] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep con- volutional neural networks[J/OL]. Communications of the ACM, 2012, 60: 84 - 90. https: //api.semanticscholar.org/CorpusID:195908774.
[40] HE K, ZHANG X, REN S, et al. Deep Residual Learning for Image Recognition[J/OL]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015: 770-778. https: //api.semanticscholar.org/CorpusID:206594692.
[41] VASWANI A, SHAZEER N M, PARMAR N, et al. Attention is All you Need[C/OL]//Neural Information Processing Systems. 2017. https://api.semanticscholar.org/CorpusID:13756489.
[42] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: abs/2010.11929[A/OL]. 2020. https://api.sema nticscholar.org/CorpusID:225039882.
[43] LIU Z, LIN Y, CAO Y, et al. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows[J/OL]. 2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021: 9992-10002. https://api.semanticscholar.org/CorpusID:232352874.
[44] CAI H, LI J, HU M, et al. EfficientViT: Lightweight Multi-Scale Attention for High-Resolution Dense Prediction[J/OL]. 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023: 17256-17267. https://api.semanticscholar.org/CorpusID:267021988.
[45] RAO Y, ZHAO W, LIU B, et al. DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification: abs/2106.02034[A/OL]. 2021. https://api.semanticscholar.org/Corpus ID:235313562.
[46] MENG L, LI H, CHEN B C, et al. AdaViT: Adaptive Vision Transformers for Efficient Image Recognition[J/OL]. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021: 12299-12308. https://api.semanticscholar.org/CorpusID:244729636.
[47] SHAKER A M, MAAZ M, RASHEED H A, et al. SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications[J/OL]. 2023 IEEE/CVF International Conference on Computer Vision (ICCV), 2023: 17379-17390. https://api.semanticscholar.org/ CorpusID:257766532.
[48] YE B, CHANG H, MA B, et al. Joint feature learning and relation modeling for tracking: A one-stream framework[C]//European Conference on Computer Vision. Springer, 2022: 341- 357.
[49] HOIEM D, DIVVALA S K, HAYS J. Pascal VOC 2008 Challenge[C/OL]//2008. https://api.se manticscholar.org/CorpusID:17020356.
[50] HU J, LU J, TAN Y P. Sharable and Individual Multi-View Metric Learning[J/OL]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40: 2281-2288. https://api. semanticscholar.org/CorpusID:32577220.
[51] KIM J, MA M, PHAM T X, et al. Modality Shifting Attention Network for Multi-Modal Video Question Answering[J/OL]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020: 10103-10112. https://api.semanticscholar.org/CorpusID: 220117666.
[52] PAN B, CAI H, HUANG D A, et al. Spatio-Temporal Graph for Video Captioning With Knowl- edge Distillation[J/OL]. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recog- nition (CVPR), 2020: 10867-10876. https://api.semanticscholar.org/CorpusID:214728152.
[53] ZHOU T, FU H, CHEN G, et al. Specificity-preserving RGB-D saliency detection[C]// Proceedings of the IEEE/CVF international conference on computer vision. 2021: 4681-4691.
[54] CHEN Y W, TSAI Y H, YANG M H. End-to-end multi-modal video temporal grounding[J]. Advances in Neural Information Processing Systems, 2021, 34: 28442-28453.
[55] CHEN X, YAN B, ZHU J, et al. Transformer tracking[C]//Proceedings of the IEEE/CVF con- ference on computer vision and pattern recognition. 2021: 8126-8135.
[56] CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers [C]//European conference on computer vision. Springer, 2020: 213-229.
[57] BHAT G, DANELLJAN M, GOOL L V, et al. Learning discriminative model prediction for tracking[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2019: 6182-6191.
[58] DANELLJAN M, BHAT G, KHAN F S, et al. Atom: Accurate tracking by overlap maximiza- tion[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recogni- tion. 2019: 4660-4669.
[59] XIAO J, STOLKIN R, GAO Y, et al. Robust fusion of color and depth data for RGB-D tar- get tracking using adaptive range-invariant depth models and spatio-temporal consistency con- straints[J]. IEEE Transactions on Cybernetics, 2017, 48(8): 2485-2499.
[60] LUKEZIC A, KART U, KAPYLA J, et al. Cdtb: A color and depth visual object tracking dataset and benchmark[C]//Proceedings of the IEEE/CVF International Conference on Com- puter Vision. 2019: 10013-10022.
[61] SONG S, XIAO J. Tracking revisited using RGBD camera: Unified benchmark and baselines [C]//Proceedings of the IEEE international conference on computer vision. 2013: 233-240.
[62] MESHGI K, ICHI MAEDA S, OBA S, et al. An occlusion-aware particle filter tracker to handle complex and persistent occlusions[J/OL]. Computer Vision and Image Understanding, 2016, 150: 81-94. https://www.sciencedirect.com/science/article/pii/S1077314216300649. DOI: https://doi.org/10.1016/j.cviu.2016.05.011.
[63] CAMPLANI M, HANNUNA S L, MIRMEHDI M, et al. Real-time RGB-D Tracking with Depth Scaling Kernelised Correlation Filters and Occlusion Handling.[C]//BMVC: Vol. 4. 2015: 5.
[64] HANNUNA S, CAMPLANI M, HALL J, et al. DS-KCF: a real-time tracker for RGB-D data [J]. Journal of Real-Time Image Processing, 2016, 16(5): 1-20.
[65] LIU Y, JING X Y, NIE J, et al. Context-aware three-dimensional mean-shift with occlusion handling for robust object tracking in RGB-D videos[J]. IEEE Transactions on Multimedia, 2018, 21(3): 664-677.
[66] KART U, KäMäRäINEN J K, MATAS J. How to Make an RGBD Tracker?[C]//ECCVW. 2018.
[67] KART U, LUKEžIč A, KRISTAN M, et al. Object Tracking by Reconstruction with View- Specific Discriminative Correlation Filters[C]//IEEE Conference on Computer Vision and Pat-tern Recognition. 2019.
[68] QIAN Y, YAN S, LUKEžIč A, et al. DAL : A Deep Depth-aware Long-term Tracker[C]//International Conference on Pattern Recognition. 2020.
[69] ZHAO P, LIU Q, WANG W, et al. TSDM: Tracking by SiamRPN++ with a Depth-refiner and aMask-generator[C]//2020 25th International Conference on Pattern Recognition (ICPR). IEEE,2021: 670-676.
[70] DANELLJAN M, GOOL L V, TIMOFTE R. Probabilistic regression for visual tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020:7183-7192.
[71] MAYER C, DANELLJAN M, PAUDEL D P, et al. Learning target candidate association tokeep track of what not to track[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2021: 13444-13454.
[72] CHEN X, YAN B, ZHU J, et al. Transformer tracking[C]//Proceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition. 2021: 8126-8135.
[73] JINGCHAO P, HAITAO Z, ZHENGWEI H, et al. Siamese infrared and visible light fusion network for RGB-T tracking[A]. 2021.
[74] ZHU X F, XU T, TANG Z, et al. RGBD1K: A large-scale dataset and benchmark for RGB-D object tracking[C]//Proceedings of the AAAI Conference on Artificial Intelligence: Vol. 37. 2023: 3870-3878.
[75] LIN S, ZHANG Z, HUANG Z, et al. Deep frequency filtering for domain generalization[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 11797-11807.
[76] XU Q, ZHANG R, ZHANG Y, et al. A fourier-based framework for domain generalization[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021: 14383-14392.
[77] CONG R, SUN M, ZHANG S, et al. Frequency Perception Network for Camouflaged Object Detection[A]. 2023.
[78] ZHONG Y, LI B, TANG L, et al. Detecting camouflaged object in frequency domain[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 4504-4513.
[79] LIU W, SHEN X, PUN C M, et al. Explicit visual prompting for low-level structure segmenta- tions[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recogni- tion. 2023: 19434-19445.
[80] LIU W, SHEN X, PUN C M, et al. Explicit Visual Prompting for Universal Foreground Seg- mentations[A]. 2023.
[81] YANG Y, SOATTO S. Fda: Fourier domain adaptation for semantic segmentation[C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 4085-4095.
[82] PATRO B N, NAMBOODIRI V P, AGNEESWARAN V S. SpectFormer: Frequency and At- tention is what you need in a Vision Transformer[A]. 2023.
[83] QIN Z, ZHANG P, WU F, et al. Fcanet: Frequency channel attention networks[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021: 783-792.
[84] CHITSAZ K, HAJABDOLLAHI M, KARIMI N, et al. Acceleration of convolutional neural network using FFT-based split convolutions[A]. 2020.
[85] LI S, XUE K, ZHU B, et al. Falcon: A fourier transform based approach for fast and se- cure convolutional neural network predictions[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 8705-8714.
[86] MATHIEU M, HENAFF M, LECUN Y. Fast training of convolutional networks through ffts [A]. 2013.
[87] VAHID K A, PRABHU A, FARHADI A, et al. Butterfly transform: An efficient fft based neural architecture design[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2020: 12021-12030.
[88] PRATT H, WILLIAMS B, COENEN F, et al. Fcnn: Fourier convolutional neural networks [C]//Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2017, Skopje, Macedonia, September 18–22, 2017, Proceedings, Part I 17. Springer, 2017: 786-798.
[89] CHI L, JIANG B, MU Y. Fast fourier convolution[J]. Advances in Neural Information Pro- cessing Systems, 2020, 33: 4479-4488.
[90] BAXES G A. Digital image processing: principles and applications[M]. John Wiley & Sons, Inc., 1994.
[91] GONZALES R C, WINTZ P. Digital image processing[M]. Addison-Wesley Longman Pub- lishing Co., Inc., 1987.
[92] HU X, ZHONG B, LIANG Q, et al. Transformer Tracking via Frequency Fusion[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2023.
[93] WANG X, CHAI L, CHEN J, et al. WCCNet: Wavelet-integrated CNN with Crossmodal Re- arranging Fusion for Fast Multispectral Pedestrian Detection[A]. 2023.
[94] YANG J, LI Z, ZHENG F, et al. Prompting for multi-modal tracking[C]//Proceedings of the 30th ACM International Conference on Multimedia. 2022: 3492-3500.
[95] ZHU J, LAI S, CHEN X, et al. Visual prompt multi-modal tracking[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2023: 9516-9526.
[96] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: Transformers for image recognition at scale[A]. 2020.
[97] KRISTAN M, LEONARDIS A, MATAS J, et al. The tenth visual object tracking vot2022 challenge results[C]//European Conference on Computer Vision. Springer, 2022: 431-460.
[98] LI C, XUE W, JIA Y, et al. LasHeR: A large-scale high-diversity benchmark for RGBT tracking [J]. IEEE Transactions on Image Processing, 2021, 31: 392-404.
[99] LI C, LIANG X, LU Y, et al. RGB-T object tracking: Benchmark and baseline[J]. Pattern Recognition, 2019, 96: 106977.
[100] WANG X, LI J, ZHU L, et al. Visevent: Reliable object tracking via collaboration of frame and event flows[A]. 2021.
[101] KRISTAN M, LEONARDIS A, MATAS J, et al. The eighth visual object tracking VOT2020 challenge results[C]//Computer Vision–ECCV 2020 Workshops: Glasgow, UK, August 23–28, 2020, Proceedings, Part V 16. Springer, 2020: 547-601.
[102] KRISTAN M, MATAS J, LEONARDIS A, et al. The seventh visual object tracking vot2019 challenge results[C]//ICCVW. 2019: 0-0.
[103] QIAN Y, YAN S, LUKEŽIČ A, et al. DAL: A deep depth-aware long-term tracker[C]//2020 25th International Conference on Pattern Recognition (ICPR). IEEE, 2021: 7825-7832.
[104] KRISTANM,MATASJ,LEONARDISA,etal.Theninthvisualobjecttrackingvot2021chal- lenge results[C]//Proceedings of the IEEE/CVF international conference on computer vision. 2021: 2711-2738.
[105]DANELLJAN M, BHAT G, KHAN F S, et al. Atom: Accurate tracking by overlap maximiza- tion[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2019: 4660-4669.
[106]LIC,ZHAON,LUY,etal.WeightedsparserepresentationregularizedgraphlearningforRGB- T object tracking[C]//Proceedings of the 25th ACM international conference on Multimedia. 2017: 1856-1864.
[107] ZHU Y, LI C, LUO B, et al. Dense feature aggregation and pruning for RGBT tracking[C]// Proceedings of the 27th ACM International Conference on Multimedia. 2019: 465-472.
[108] ZHU Y, LI C, TANG J, et al. Quality-aware feature aggregation network for robust RGBT tracking[J]. IEEE Transactions on Intelligent Vehicles, 2020, 6(1): 121-130.
[109] ZHANG H, ZHANG L, ZHUO L, et al. Object tracking in RGB-T videos using modal-aware attention network and competitive learning[J]. Sensors, 2020, 20(2): 393.
[110]WANG C, XU C, CUI Z, et al. Cross-modal pattern-propagation for RGB-T tracking[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 7064-7073.
[111] ZHANG P, ZHAO J, BO C, et al. Jointly modeling motion and appearance cues for robust RGB-T tracking[J]. IEEE Transactions on Image Processing, 2021, 30: 3335-3347.
[112]YAN B, PENG H, FU J, et al. Learning spatio-temporal transformer for visual tracking[C]// Proceedings of the IEEE/CVF international conference on computer vision. 2021: 10448- 10457.
[113]ZHANG P, ZHAO J, WANG D, et al. Visible-thermal UAV tracking: A large-scale bench- mark and new baseline[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 8886-8895.
[114]PARKE,BERGAC.Meta-tracker:Fastandrobustonlineadaptationforvisualobjecttrackers [C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018: 569-585.
[115]NAM H, HAN B. Learning multi-domain convolutional neural networks for visual tracking [C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 4293-4302.
[116] SONG Y, MA C, WU X, et al. Vital: Visual tracking via adversarial learning[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 8990-8999.
[117]WANG Q, ZHANG L, BERTINETTO L, et al. Fast online object tracking and segmentation: A unifying approach[C]//Proceedings of the IEEE/CVF conference on Computer Vision and Pattern Recognition. 2019: 1328-1338.
[118]CHEN Z, ZHONG B, LI G, et al. Siamese box adaptive network for visual tracking[C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 6668-6677.
[119]GUO D, WANG J, CUI Y, et al. SiamCAR: Siamese fully convolutional classification and regression for visual tracking[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 6269-6277.
[120]DANELLJAN M, GOOL L V, TIMOFTE R. Probabilistic regression for visual tracking[C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 7183-7192.
[121]DAI K, ZHANG Y, WANG D, et al. High-performance long-term tracking with meta-updater [C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 6298-6307.
[122]VOIGTLAENDERP,LUITENJ,TORRPH,etal.Siamr-cnn:Visualtrackingbyre-detection [C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020: 6578-6588.
[123]WANG Y, CHEN X, CAO L, et al. Multimodal token fusion for vision transformers[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022: 12186-12195.