基于动态语义聚类关系建模的目标跟踪方法

doi:10.16451/j.cnki.issn1003-6059.202504001

摘要
图/表
参考文献(44)
相关文章 (15)

全文: PDF (4296 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要

Transformer跟踪器采用全局注意力机制时,常因目标形变导致特征判别性下降,引发目标和背景混淆.针对此问题,文中提出基于动态语义聚类关系建模的目标跟踪方法.首先,构建语义关系建模模块,通过特征空间中局部注意力聚焦语义相近的特征向量,有效抑制目标与干扰背景的错误交互.然后,利用图神经网络捕捉局部关联性,设计动态语义聚类模块,自适应生成语义类别划分,实现动态注意力突出目标和背景的鉴别信息.最后,设计语义背景消除模块,在关系建模过程中有效抑制背景特征干扰,提升跟踪效率.在6个基准数据集上的大量实验表明,文中方法性能较优.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	聂国豪
	王兴梅
	徐悦竹
	杨文涛

关键词 ：目标跟踪, 自注意力, 特征学习, 图神经网络

Abstract：

When the Transformer based object tracking method employs the global attention mechanism to model the spatial relations between the search area and the template, the target deformation can lead to the degradation of feature discriminability, causing confusion between the target and the background. To solve this problem, a dynamic semantic clustering relation modeling method for object tracking is proposed. First, a semantic relation modeling module is constructed. Local attention mechanisms in the feature space are employed to concentrate on semantically similar feature vectors, thereby effectively suppressing erroneous interactions between the target and the distracting background. Second, graph neural networks are utilized to capture local correlations and design a dynamic semantic clustering module. The module adaptively generates semantic category partitions, enabling dynamic attention mechanisms to enhance the discriminative information between the target and the background. Finally, a semantic background elimination strategy is designed to effectively suppress the interference from background features during relationship modeling, thereby improving tracking efficiency. Experimental results on six benchmark datasets demonstrate the superiority of the proposed method.

Key words： Object Tracking Self-Attention Feature Learning Graph Neural Network

收稿日期: 2025-03-04

ZTFLH:

TP391

基金资助:

黑龙江省重点研发计划项目(No.GA23A903)、中央高校基本科研业务费专项资金项目(No.3072024XX0602)、航空科学基金项目(No.202400550P6001)资助

通讯作者: 徐悦竹,博士,讲师,主要研究方向为图像识别、多模态数据处理、人工智能.E-mail:xuyuezhu@hrbeu.edu.cn.

作者简介: 聂国豪,博士研究生,主要研究方向为目标跟踪、目标检测.E-mail:nieguohao@hrbeu.edu.cn.
王兴梅,博士,教授,主要研究方向为人工智能、水下信号处理、计算机视觉、模式识别.E-mail:wangxingmei@hrbeu.edu.cn.
杨文涛,硕士研究生,主要研究方向为目标跟踪,智能感知.E-mail:1940928852@qq.com.

引用本文:

聂国豪, 王兴梅, 徐悦竹, 杨文涛. 基于动态语义聚类关系建模的目标跟踪方法[J]. 模式识别与人工智能, 2025, 38(4): 293-309. NIE Guohao, WANG Xingmei, XU Yuezhu, YANG Wentao. Dynamic Semantic Clustering Relation Modeling Method for Object Tracking. Pattern Recognition and Artificial Intelligence, 2025, 38(4): 293-309.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202504001 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2025/V38/I4/293

[1] 卢湖川,李佩霞,王栋.目标跟踪算法综述.模式识别与人工智能, 2018, 31(1): 61-76.
(LU H C, LI P X, WANG D.Visual Object Tracking: A Survey. Pattern Recognition and Artificial Intelligence, 2018, 31(1): 61-76.)
[2] 杜晨杰,杨宇翔,伍瀚,等.旋转自适应的多特征融合多模板学习视觉跟踪算法.模式识别与人工智能, 2021, 34(9): 787-797.
(DU C J, YANG Y X, WU H, et al. Visual Tracking Algorithm Based on Rotation Adaptation, Multi-feature Fusion and Multi-template Learning. Pattern Recognition and Artificial Intelligence, 2021, 34(9): 787-797.)
[3] 姜文涛,刘晓璇,涂潮,等.空间异常适应性的目标跟踪.模式识别与人工智能, 2021, 34(5): 473-484.
(JIANG W Y, LIU X X, TU C, et al. Spatially Abnormal Adaptive Target Tracking. Pattern Recognition and Artificial Intelligence, 2021, 34(5): 473-484.)
[4] BERTINETTO L, VALMADRE J, HENRIQUES J F, et al. Fully-Convolutional Siamese Networks for Object Tracking // Proc of the European Conference on Computer Vision. Berlin, Germany: Sprin-ger, 2016: 850-865.
[5] LI B, WU W, WANG Q, et al. SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 4277-4286.
[6] MAYER C, DANELLJAN M, PAUDEL D P, et al. Learning Target Candidate Association to Keep Track of What not to Track // Proc of the IEEE/CVF International Conference on Computer Vision. Wa-shington, USA: IEEE, 2021: 13424-13434.
[7] CHEN X, YAN B, ZHU J W, et al. Transformer Tracking // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Re-cognition. Washington, USA: IEEE, 2021: 8122-8131.
[8] YAN B, PENG H W, FU J L, et al. Learning Spatio-Temporal Transformer for Visual Tracking // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2021: 10428-10437.
[9] XIE F, WANG C Y, WANG G T, et al. Learning Tracking Representations via Dual-Branch Fully Transformer Networks // Proc of the IEEE/CVF International Conference on Computer Vision Workshops. Washington, USA: IEEE, 2021: 2688-2697.
[10] LIN L T, FAN H, ZHANG Z P, et al. SwinTrack: A Simple and Strong Baseline for Transformer Tracking // Proc of the 36th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2022: 16743-16754.
[11] ZHANG H L, LIU M D, SONG X H, et al. Spatial Attention Inference Model for Cascaded Siamese Tracking with Dynamic Resi-dual Update Strategy. Computer Vision and Image Understanding, 2024, 248. DOI: 10.1016/j.cviu.2024.104125.
[12] GAO L, CHEN L K, LIU P, et al. Transformer-Based Visual Object Tracking via Fine-Coarse Concatenated Attention and Cross Concatenated MLP. Pattern Recognition, 2024, 146. DOI: 10.1016/j.patcog.2023.109964.
[13] NIE G H, WANG X M, YAN Z N, et al. Temporal Relation Transformer for Robust Visual Tracking with Dual-Memory Lear-ning. Applied Soft Computing, 2024, 167(A). DOI: 10.1016/j.asoc.2024.112229.
[14] MARVASTI-ZADEH S M, CHENG L, GHANEI-YAKHDAN H, et al. Deep Learning for Visual Tracking: A Comprehensive Survey. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(5): 3943-3968.
[15] YE B T, CHANG H, MA B P, et al. Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2022: 341-357.
[16] LAN J P, CHENG Z Q, HE J Y, et al. ProContEXT: Exploring Progressive Context Transformer for Tracking // Proc of the IEEE International Conference on Acoustics, Speech and Signal Proce-ssing. Washington, USA: IEEE, 2023. DOI: 10.1109/ICASSP49357.2023.10094971.
[17] SHI L T, ZHONG B N, LIANG Q H, et al. Explicit Visual Prompts for Visual Object Tracking. Proceedings of the AAAI Conference on Artificial Intelligence, 2024, 38(5): 4838-4846.
[18] XIE J X, ZHONG B N, MO Z Y, et al. Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2024: 19300-19309.
[19] ZHU J W, CHEN X, DIAO H W, et al. Exploring Dynamic Transformer for Efficient Object Tracking. IEEE Transactions on Neural Networks and Learning Systems, 2025. DOI: 10.1109/TNNLS.2025.3545752.
[20] WANG Q W, ZHOU L Y, JIN P C, et al. TrackingMamba: Visual State Space Model for Object Tracking. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 16744-16754.
[21] ZENG W, JIN S, LIU W T, et al. Not All Tokens Are Equal: Human-Centric Visual Analysis via Token Clustering Transformer // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2022: 11091-11101.
[22] FU Z H, FU Z H, LIU Q J, et al. SparseTT: Visual Tracking with Sparse Transformers // Proc of the 31st International Joint Confe-rence on Artificial Intelligence. San Francisco, USA: IJCAI, 2022: 905-912.
[23] CUI Y T, JIANG C, WU G S, et al. MixFormer: End-to-End Tracking with Iterative Mixed Attention. IEEE Transactions on Pa-ttern Analysis and Machine Intelligence, 2024, 46(6): 4129-4146.
[24] GAO S Y, ZHOU C L, MA C, et al. AiATrack: Attention in Atten-tion for Transformer Visual Tracking // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2022: 146-164.
[25] GAO S Y, ZHOU C L, ZHANG J.Generalized Relation Modeling for Transformer Tracking // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2023: 18686-18695.
[26] WANG J, YANG S, WANG Y Y.Dynamic Region-Aware Transformer Backbone Network for Visual Tracking. Engineering Applications of Artificial Intelligence, 2024, 133. DOI: 10.1016/j.engappai.2024.108329.
[27] ZHANG S, ZHANG D, ZOU Q.ATPTrack: Visual Tracking with Alternating Token Pruning of Dynamic Templates and Search Region. Neurocomputing, 2025. DOI: 10.1016/j.neucom.2025.129534.
[28] RAO Y M, ZHAO W L, LIU B L, et al. DynamicVIT: Efficient Vision Transformers with Dynamic Token Sparsification // Proc of the 35th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2021: 13937-13949.
[29] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An Image Is Worth 16×16 Words: Transformers for Image Recognition at Scale[C/OL].[2025-02-10]. https://arxiv.org/pdf/2010.11929.
[30] DU M J, DING S, JIA H J.Study on Density Peaks Clustering Based on k-Nearest Neighbors and Principal Component Analysis. Knowledge-Based Systems, 2016, 99: 135-145.
[31] MELAS-KYRIAZI L, RUPPRECHT C, LAINA I, et al. Deep Spec-tral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2022: 8354-8365.
[32] FAN H, LIN L T, YANG F, et al. LaSOT: A High-Quality Ben-chmark for Large-Scale Single Object Tracking // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 5369-5378.
[33] HUANG L H, ZHAO X, HUANG K Q.GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(5): 1562-1577.
[34] MÜLLER M, BIBI A, GIANCOLA S, et al. TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 300-317.
[35] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: Common Objects in Context // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2014: 740-755.
[36] WU Y, LIM J, YANG M H.Online Object Tracking: A Benchmark // Proc of the IEEE Conference on Computer Vision and Pa-ttern Recognition. Washington, USA: IEEE, 2013: 2411-2418.
[37] MUELLER M, SMITH N, GHANEM B.A Benchmark and Simulator for UAV Tracking // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 445-461.
[38] BHAT G, DANELLJAN M, VAN GOOL L, et al. Learning Discriminative Model Prediction for Tracking // Proc of the IEEE/CVF International Conference on Computer Vision. Washington, USA: IEEE, 2019: 6181-6190.
[39] WANG N, ZHOU W G, WANG J, et al. Transformer Meets Tra-cker: Exploiting Temporal Context for Robust Visual Tracking // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 1571-1580.
[40] SONG Z K, YU J Q, CHEN Y P, et al. Transformer Tracking with Cyclic Shifting Window Attention // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2022: 8781-8790.
[41] ZHANG M H, ZHANG Q Y, SONG W, et al. PromptVT: Promp-ting for Efficient and Accurate Visual Tracking. IEEE Transactions on Circuits and Systems for Video Technology, 2024, 34(8): 7373-7385.
[42] YAO J Z, WANG Z X, ZHANG J L, et al. Tracking in Tracking: An Efficient Method to Solve the Tracking Distortion. Engineering Applications of Artificial Intelligence, 2024, 135. DOI: 10.1016/j.engappai.2024.108698.
[43] WANG X M, NIE G H, MENG J X, et al. MIMTrack: In-Context Tracking via Masked Image Modeling. Proceedings of the AAAI Conference on Artificial Intelligence, 2025, 39(8): 7979-7987.
[44] WEI X, BAI Y F, ZHENG Y C, et al. Autoregressive Visual Tra-cking // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2023: 9697-9706.