无锚框关键点与注意力机制结合的自适应孪生网络目标追踪方法  

Anchor-Free RepPoints and Attention Mechanism Based Adaptive Siamese Network for Object Tracking

作　　者：袁帅[1,2,3] 窦慧泽 耿金玉 栾方军[1,2,3] YUAN Shuai;DOU Huize;GENG Jinyu;LUAN Fangjun(School of Computer Science and Engineering,Shenyang Jian zhu University,Shenyang 110168;Liaoning Province Big Data Management and Analysis Laboratory of Urban Construction,Shenyang Jianzhu University,Shenyang 110168;Shenyang Branch of National Special Computer Engineering Technology Research Center,Shenyang Jianzhu University,Shenyang 110168;School of Electrical and Control Engineering,Shenyang Jian zhu University,Shenyang 110168)

机构地区：[1]沈阳建筑大学计算机科学与工程学院,沈阳110168 [2]沈阳建筑大学辽宁省城市建设大数据管理与分析重点实验室,沈阳110168 [3]沈阳建筑大学国家特种计算机工程技术研究中心沈阳分中心,沈阳110168 [4]沈阳建筑大学电气与控制工程学院,沈阳110168

出　　处：《模式识别与人工智能》2024年第11期974-985,共12页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金面上项目(No.62073227);辽宁省科技厅基金项目(No.2023JH2/101300212)资助。

摘　　要：目前孪生网络目标追踪算法在目标候选框的生成阶段计算复杂度较高,导致算法存在实时性较差以及在复杂场景中目标追踪精准度较低等缺陷.针对这些问题,文中提出无锚框关键点与注意力机制结合的自适应孪生网络目标追踪方法.首先,在孪生子网络的主干网络中设计大核卷积注意力模块,提取目标全局特征,提升方法的精准度和泛化能力.然后,设计无锚框多关键点模块,学习目标的多关键点,采用自适应学习权重系数模块,筛选准确的目标关键点,进一步提升方法的精准度和鲁棒性.最后,将关键点转换成预测框,无需生成预定义的目标候选框,可减少计算复杂度,提升目标追踪的实时性.在4个数据集上的实验表明,文中方法在精准度和成功率上都有所提升.The high computational complexity of current Siamese network based target tracking algorithm during the candidate box generation stage results in poor real-time performance and reduced accuracy in complex scenarios.To address these issues,an anchor-free RepPoints and attention mechanism based adaptive Siamese network for object tracking is proposed.First,a large-kernel convolutional attention module is introduced in the backbone network of the Siamese subnetwork to extract global features of the target,enhancing the precision and generalization ability of the model.Second,a module for anchor-free multi-RepPoints is utilized to learn multiple RepPoints of the target,and then an adaptive learning weight coefficient module is employed to filter out more accurate target RepPoints,further improving model precision and robustness.Finally,RepPoints are transformed into predicted boxes,thereby eliminating the need for predefined candidate boxes,reducing computational complexity and enhancing real-time tracking performance.Experiments indicate that the proposed method achieves significant improvements in precision and success rate on four datasets.

关 键 词：孪生网络 无锚框关键点 注意力机制 全局特征 权重系数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]