[1]CHEN Long,DING Meng,SHI Lei,et al.UAV object tracking based on template feature buffer and adaptive attention[J].CAAI Transactions on Intelligent Systems,2026,21(3):688-700.[doi:10.11992/tis.202507009]
Copy

UAV object tracking based on template feature buffer and adaptive attention

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 21 Number of periods: 2026 3 Page number: 688-700 Column: 学术论文—机器感知与模式识别 Public date: 2026-05-05
Title:
UAV object tracking based on template feature buffer and adaptive attention
Author(s):
CHEN Long1;  DING Meng1; 2;  SHI Lei3;  LI Zhihui4;  XU Xiaoyu5;  PAN Yilun1
1. College of Investigation, People’s Public Security University of China, Beijing 100038, China;
2. Public Security Behavioral Science Lab, People’s Public Security University of China, Beijing 100038, China;
3. State Key Laboratory of Media Convergence and Communication, Communication University of China, Beijing 100024, China;
4. Institute of Forensic Science of China, Beijing 100038, China;
5. Guangdong Provincial Forensic Science of Evidence Materials Engineering Technology Research Center, Shenzhen 518033, China
Keywords:
object tracking; UAV; template feature buffer; adaptive attention; plug-and-play; historical information; computer vision; deep learning
CLC:
TP391.4
DOI:
10.11992/tis.202507009
Abstract:
Existing UAV object tracking methods typically retain only the template information from recent frames, leading to the loss of critical historical appearance information. To address the challenges of information loss and effective utilization of historical data in UAV tracking, this paper proposes a novel tracking method based on template feature buffer and adaptive attention mechanisms. 1)we design a template feature buffer module that maintains a comprehensive repository of historical target appearances through a sliding window mechanism, effectively addressing the information loss problem inherent in traditional methods. 2) we introduce an adaptive attention mechanism that employs channel-level attention to dynamically evaluate the relevance of stored features, enabling intelligent weighting of historical template information. 3) we adopt a plug-and-play architecture that integrates seamlessly with existing mainstream trackers, enhancing the algorithm’s practicality and versatility, and design a symmetric sequence evaluation method to validate the effective retention and utilization of historical target information. Experimental results demonstrate significant performance improvements across five mainstream tracking algorithms, with average AUC improvements of 2.34 percentage points on the UAV123 dataset, 7.24 percentage points on the UAV20L dataset, 4.11 percentage points on UAV123-L, and 9.14 percentage points on UAV20L-L, validating the effectiveness and broad applicability of our method.
References:
[1] WU Xin, LI Wei, HONG Danfeng, et al. Deep learning for unmanned aerial vehicle-based object detection and tracking: a survey[J]. IEEE geoscience and remote sensing magazine, 2022, 10(1): 91-124
[2] SUN Nianyi, ZHAO Jin, SHI Qing, et al. Moving target tracking by unmanned aerial vehicle: a survey and taxonomy[J]. IEEE transactions on industrial informatics, 2024, 20(5): 7056-7068
[3] 黄昱程, 肖子旺, 武丹凤, 等. 时空融合与判别力增强的孪生网络目标跟踪方法[J]. 智能系统学报, 2024, 19(5): 1218-1227 HUANG Yucheng, XIAO Ziwang, WU Danfeng, et al. Spatiotemporal fusion and discriminative augmentation for improved Siamese tracking[J]. CAAI transactions on intelligent systems, 2024, 19(5): 1218-1227
[4] WEI Xing, BAI Yifan, ZHENG Yongchao, et al. Autoregressive visual tracking[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023: 9697-9706.
[5] BAI Yifan, ZHAO Zeyang, GONG Yihong, et al. ARTrackV2: prompting autoregressive tracker where to look and how to describe[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 19048-19057.
[6] 刘芳, 卢晨阳, 路言, 等. 基于自适应模板更新的Transformer无人机目标跟踪算法[J]. 航空学报, 2025, 46(16): 290-301 LIU Fang, LU Chenyang, LU Yan, et al. Adaptive template update-based Transformer algorithm for UAV target tracking[J]. Acta aeronautica et astronautica sinica, 2025, 46(16): 290-301
[7] ZHOU Xinyu, GUO Pinxue, HONG Lingyi, et al. Reading relevant feature from global representation memory for visual object tracking[EB/OL]. (2024-02-02)[2025-07-07]. https://arxiv.org/abs/2402.14392.
[8] CHEN Xiaotang, FENG Xiaokun, HU Shiyu, et al. MemVLT: vision-language tracking with adaptive memory-based prompts[C]//Advances in Neural Information Processing Systems 37. Vancouver: NeurIPS, 2024: 14903-14933.
[9] YUAN Xiaoying, XU Tingfa, LIU Xincong, et al. Multi-step temporal modeling for UAV tracking[J]. IEEE transactions on circuits and systems for video technology, 2024, 34(8): 7216-7230
[10] ZHANG Tianshuo, ZHU Linlin, LIN Feng. A robust tracking method based on dynamic template updating[C]//2024 36th Chinese Control and Decision Conference. Xi’an: IEEE, 2024: 3338-3342.
[11] ZHANG Mingyang, VAN BEECK K, GOEDEM? T. Object tracking withMultiple dynamic templates updating[C]//Image and Vision Computing. Cham: Springer, 2023: 144-158.
[12] ZHENG Yang, XU Yijie, LIANG Jimin. Spatiotemporal memory network for UAV target tracking[C]//Proceedings of 4th 2024 International Conference on Autonomous Unmanned Systems. Singapore: Springer, 2025: 79-88.
[13] ZHANG Huanlong, SONG Peipei, FU Weiqiang, et al. Brain-inspired memory network for visual tracking with recurrent meta-learning updater[J]. Digital signal processing, 2025, 162: 105159
[14] CAI Wenrui, LIU Qingjie, WANG Yunhong. HIPTrack: visual tracking with historical prompts[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 19258-19267.
[15] WANG Yuanhui, YE Ben, CAI Zhanchuan. Dynamic template updating using spatial-temporal information in Siamese trackers[J]. IEEE transactions on multimedia, 2024, 26: 2006-2015
[16] WU You, WANG Xucheng, YANG Xiangyang, et al. Learning occlusion-robust vision transformers for real-time UAV tracking[C]//2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2025: 17103-17113.
[17] XUE Chaocan, ZHONG Bineng, LIANG Qihua, et al. Similarity-guided layer-adaptive vision transformer for UAV tracking[C]//2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2025: 6730-6740.
[18] CAO Ziang, HUANG Ziyuan, PAN Liang, et al. Towards real-world visual tracking with temporal contexts[J]. IEEE transactions on pattern analysis and machine intelligence, 2023, 45(12): 15834-15849
[19] XIE Jinxia, ZHONG Bineng, MO Zhiyi, et al. Autoregressive queries for adaptive tracking with spatio-temporal transformers[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 19300-19309.
[20] MUELLER M, SMITH N, GHANEM B. A benchmark and simulator for UAV tracking[C]//Computer Vision–ECCV 2016. Cham: Springer, 2016: 445-461.
[21] CHEN Xin, PENG Houwen, WANG Dong, et al. SeqTrack: sequence to sequence learning for visual object tracking[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023: 14572-14581.
[22] 林淑彬, 吴贵山, 姚文勇, 等. 基于光照自适应动态一致性的无人机目标跟踪[J]. 智能系统学报, 2022, 17(6): 1093-1103 LIN Shubin, WU Guishan, YAO Wenyong, et al. Unmanned aerial vehicles object tracking based on illumination adaptive dynamic consistency[J]. CAAI transactions on intelligent systems, 2022, 17(6): 1093-1103
[23] DANELLJAN M, BHAT G, KHAN F S, et al. ATOM: accurate tracking by overlap maximization[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2020: 4655-4664.
[24] BHAT G, DANELLJAN M, VAN GOOL L, et al. Learning discriminative model prediction for tracking[C]//2019 IEEE/CVF International Conference on Computer Vision. Seoul: IEEE, 2020: 6181-6190.
[25] DANELLJAN M, VAN GOOL L, TIMOFTE R. Probabilistic regression for visual tracking[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 7181-7190.
[26] MAYER C, DANELLJAN M, BHAT G, et al. Transforming model prediction for tracking[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 8721-8730.
[27] YAN Bin, PENG Houwen, FU Jianlong, et al. Learning spatio-temporal transformer for visual tracking[C]//2021 IEEE/CVF International Conference on Computer Vision. Montreal: IEEE, 2022: 10428-10437.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems