基于多特征融合与记忆重检测的无人机目标跟踪

朱凯峰; 武丹凤; 朱纪洪; 周芬芬; 靳爽; 匡敏驰

doi:10.12382/bgxb.2026.0036

您当前的位置：

首页 >

文章列表页 >

基于多特征融合与记忆重检测的无人机目标跟踪

更新时间：2026-08-12

- 基于多特征融合与记忆重检测的无人机目标跟踪
- UAV Target Tracking Based on Multi-Feature Fusion and Memory Re-Detection
- 兵工学报 2026年
- 作者机构：
  
  1.北京联合大学北京市信息服务工程重点实验室, 北京 100101
  2.北京联合大学机器人学院 , 北京 100101
  3.清华大学精密仪器系 , 北京 100084
- 作者简介：
  
  邮箱：jqrdanfeng@buu.edu.cn
- 基金信息：
  
  时空信息精密感知技术全国重点实验室开放基金项目( STL2023-B-06-01 ( K) );北京联合大学科研资助项目(ZK20202201)
- DOI：10.12382/bgxb.2026.0036
  中图分类号： TJ301
- 收稿：2026-01-11，
  
  修回：2026-03-15，
  
  录用：2026-05-14，
- 稿件说明：
移动端阅览
朱凯峰, 武丹凤, 朱纪洪, 等. 基于多特征融合与记忆重检测的无人机目标跟踪[J/OL]. 兵工学报, 2026.

ZHU Kaifeng, WU Danfeng, ZHU Jihong, et al. UAV Target Tracking Based on Multi-Feature Fusion and Memory Re-Detection[J/OL]. Acta Armamentarii, 2026.
朱凯峰, 武丹凤, 朱纪洪, 等. 基于多特征融合与记忆重检测的无人机目标跟踪[J/OL]. 兵工学报, 2026. DOI： 10.12382/bgxb.2026.0036.

ZHU Kaifeng, WU Danfeng, ZHU Jihong, et al. UAV Target Tracking Based on Multi-Feature Fusion and Memory Re-Detection[J/OL]. Acta Armamentarii, 2026. DOI： 10.12382/bgxb.2026.0036.

摘要

针对无人机目标跟踪中目标尺度与视角变化、遮挡以及目标丢失后再出现等复杂情形，提出一种增强型核相关滤波跟踪框架。通过构建尺度金字塔并引入旋转不变描述子，实现对目标尺度与视角变化的协同感知；结合基于空间正则化的抗遮挡模块，提高遮挡条件下的跟踪鲁棒性；融合基于卡尔曼滤波的记忆引导重检测与局部搜索策略，增强目标丢失后的恢复能力。在UAV123与OTB100数据集上的实验结果表明：所提方法在资源受限平台上分别可实现33.21 帧/s、35.39 帧/s的实时处理性能，并分别获得54.6%/66.0%的定位精度和37.6%/55.8%的成功率；该方法在目标外观变化与短时遮挡场景下具有良好的稳定性，并能够在目标丢失后实现快速恢复，具备工程应用价值。

Abstract

To address the challenges of target scale and viewpoint variations

occlusion

and target reappearance after loss in unmanned aerial vehicle target tracking

an enhanced kernelized correlation filter tracking framework is proposed. The framework constructs a scale pyramid and incorporates rotation-invariant descriptors to achieve collaborative perception of target scale and viewpoint variations; a spatial regularization-based anti-occlusion module is integrated to improve tracking robustness under occlusion; and a memory-guided re-detection strategy combined with Kalman filtering and local search is employed to enhance recovery capability after target loss. Experimental results on the UAV123 and OTB100 datasets demonstrate that the proposed method achieves real-time performance of 33.21/35.39 FPS on resource-constrained platforms

with localization accuracies of 54.6%/66.0% and success rates of 37.6%/55.8%

respectively. The results indicate that the proposed approach maintains stable tracking performance under target appearance variations and short-term occlusion

and is capable of rapid recovery after target loss

showing strong potential for practical engineering applications.

关键词

Keywords

references

张栋 , 李林 , 王孟阳 , 等 . 不确定环境下多无人机察打一体任务规划方法 [J ] . 北京理工大学学报 , 2025 , 45 ( 2 ): 111 - 125 .

Zhang D , Li L , Wang M Y , et al . Mission planning method for multi-UAV reconnaissance-attack integrated operations under uncertain environments [J ] . Transactions of Beijing Institute of Technology , 2025 , 45 ( 2 ): 111 - 125 . (in Chinese)

相晓嘉 , 谭沁 , 王菖 , 等 . 无人机先进地面站关键技术综述 [J ] . 国防科技大学学报 , 2023 , 45 ( 2 ): 1 - 14 .

Xiang X J , Tan Q , Wang C , et al . Review on key technologies of advanced UAV ground control stations [J ] . Journal of National University of Defense Technology , 2023 , 45 ( 2 ): 1 - 14 . (in Chinese)

赵军民 , 何浩哲 , 王少奇 , 等 . 复杂环境下多无人机目标跟踪与避障联合航迹规划 [J ] . 兵工学报 , 2023 , 44 ( 9 ): 2685 - 2696 .

Zhao J M , He H Z , Wang S Q , et al . Coordinated trajectory planning for multi-UAV target tracking and obstacle avoidance in complex environments [J ] . Acta Armamentarii , 2023 , 44 ( 9 ): 2685 - 2696 . (in Chinese)

樊小冬 , 谭天一 , 吴江 . 轻量化低慢小无人机多目标检测及跟踪方法 [J ] . 北京航空航天大学学报 , 2026 , 52 ( 2 ): 610 - 619 .

Fan X D , Tan T Y , Wu J . Lightweight multi-object detection and tracking method for low-altitude slow and small UAVs [J ] . Journal of Beijing University of Aeronautics and Astronautics , 2026 , 52 ( 2 ): 610 - 619 . (in Chinese)

党昭洋 , 孙晓永 , 郭润泽 , 等 . 融合多视角投影与时空拓扑的多无人机多目标跟踪方法 [J ] . 仪器仪表学报 , 2025 , 46 ( 11 ): 215 - 228 .

Dang Z Y , Sun X Y , Guo R Z , et al . Multi-UAV multi-object tracking method integrating multi-view projection and spatio-temporal topology [J ] . Chinese Journal of Scientific Instrument , 2025 , 46 ( 11 ): 215 - 228 . (in Chinese)

Cao Z A , Huang Z Y , Pan L , et al . Towards real-world visual tracking with temporal contexts [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2023 , 45 ( 12 ): 15834 - 15849 .

Zhu Y B , Li C L , Wang X , et al . RGBT tracking via progressive fusion transformer with dynamically guided learning [J ] . IEEE Transactions on Circuits and Systems for Video Technology , 2024 , 34 ( 9 ): 8722 - 8735 .

Fan H J , Yu Z C , Wang Q , et al . QueryTrack: joint-modality query fusion network for RGBT tracking [J ] . IEEE Transactions on Image Processing , 2024 , 33 : 3187 - 3199 .

Cai Y J , Sui X B , Gu G H , et al . Multi-modal interaction with token division strategy for RGB-T tracking [J ] . Pattern Recognition , 2024 , 155 : 110626 .

Sun M , Liu X T , Wang H Y , et al . MixRGBX: universal multi-modal tracking with symmetric mixed attention [J ] . Neurocomputing , 2024 , 603 : 128274 .

Lu A D , Li C L , Zhao J C , et al . Modality-missing RGBT tracking: invertible prompt learning and high-quality benchmarks [J ] . International Journal of Computer Vision , 2025 , 133 ( 5 ): 2599 - 2619 .

Li B , Peng F G , Hui T R , et al . RGB-T tracking with template-bridged search interaction and target-preserved template updating [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2025 , 47 ( 1 ): 634 - 649 .

Lai S M , Liu C , Zhu J W , et al . MambaVT: spatio-temporal contextual modeling for robust RGB-T tracking [J ] . IEEE Transactions on Circuits and Systems for Video Technology , 2025 , 35 ( 9 ): 9312 - 9323 .

Henriques J F , Caseiro R , Martins P , et al . Exploiting the circulant structure of tracking-by-detection with kernels [C ] // Computer Vision - ECCV 2012: 12th European Conference on Computer Vision , 2012 : 702 - 715 .

Henriques J F , Caseiro R , Martins P , et al . High-speed tracking with kernelized correlation filters [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2015 , 37 ( 3 ): 583 - 596 .

Danelljan M , Häger G , Khan F S , et al . Discriminative scale space tracking [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 , 39 ( 8 ): 1561 - 1575 .

Kiani Galoogahi H , Fagg A , Lucey S . Learning background-aware correlation filters for visual tracking [C ] // 2017 IEEE International Conference on Computer Vision , 2017 : 1144 - 1152 .

Pi Z X , Shao Y , Gao C , et al . Instance-based feature pyramid for visual object tracking [J ] . IEEE Transactions on Circuits and Systems for Video Technology , 2022 , 32 ( 6 ): 3774 - 3787 .

Cai Z M , Wang Z Z , Huang J C , et al . A target tracking method based on adaptive occlusion judgment and model updating strategy [J ] . PeerJ Computer Science , 2023 , 9 : e1562 .

Ma C , Yang X K , Zhang C Y , et al . Long-term correlation tracking [C ] // 2015 IEEE Conference on Computer Vision and Pattern Recognition , 2015 : 5388 - 5396 .

Yan B , Zhang X Y , Wang D , et al . Alpha-Refine: boosting tracking performance by precise bounding box estimation [C ] // 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2021 : 5289 - 5298 .

Mueller M , Smith N , Ghanem B . A benchmark and simulator for UAV tracking [C ] // Computer Vision - ECCV 2016 , 2016 : 445 - 461 .

Wu Y , Lim J , Yang M H . Object tracking benchmark [J ] . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2015 , 37 ( 9 ): 1834 - 1848 .

Bertinetto L , Valmadre J , Henriques J F , et al . Fully-convolutional siamese networks for object tracking [C ] // Computer Vision - ECCV 2016 Workshops , 2016 : 850 - 865 .

Danelljan M , Häger G , Khan F S , et al . Learning spatially regularized correlation filters for visual tracking [C ] // 2015 IEEE International Conference on Computer Vision , 2015 : 4310 - 4318 .

Jia X , Lu H C , Yang M H . Visual tracking via adaptive structural local sparse appearance model [C ] // 2012 IEEE Conference on Computer Vision and Pattern Recognition , 2012 : 1822 - 1829 .

Li F , Tian C , Zuo W M , et al . Learning spatial-temporal regularized correlation filters for visual tracking [C ] // 2018 IEEE Conference on Computer Vision and Pattern Recognition , 2018 : 4904 - 4913 .

Li Y M , Fu C H , Ding F Q , et al . AutoTrack: towards high-performance visual tracking for UAV with automatic spatio-temporal regularization [C ] // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition , 2020 : 11923 - 11932 .

Danelljan M , Bhat G , Khan F S , et al . ECO: efficient convolution operators for tracking [C ] // 2017 IEEE Conference on Computer Vision and Pattern Recognition , 2017 : 6931 - 6939 .

浏览量

下载量

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

复杂环境下多无人机目标跟踪与避障联合航迹规划

氢能炮射无人机精确内弹道模型研究与试验验证

视场约束下无人机动态降落图像视觉伺服控制

基于改进海洋捕食者算法的无人机三维航迹规划

无人机数据链带外电磁干扰3阶互调效应预测