复杂背景下反无人机红外目标鲁棒跟踪算法

doi:10.7527/S1000-6893.2025.32264

Abstract

Abstract:

In the anti-UAV task under complex backgrounds， infrared target tracking faces numerous challenges，such as multi-scale targets， occlusion， moving out of view， and background interference. To address these problems，a robust infrared UAV tracking algorithm is proposed. First， a global tracking model is designed， which adopts an effi⁃cient one-stage anchor-free framework to perform global search for handling target disappearance caused by occlusionor moving out of view， while employing a multi-level structure to track targets of varying sizes. Second， a spatiotemporalfeature fusion module based on the memory network is proposed， which leverages spatio-temporal featuresfrom video sequences to enhance target discriminability. Third， a target enhancement and interference suppressionmodule is introduced， which records and matches target and interference features between frames to generate weight⁃ing maps. These maps are applied to the score maps to improve the algorithm’s anti-interference capability. Finally， adynamic hierarchical acceleration method is proposed to improve the running efficiency by removing redundant hierar⁃chical computations. Experimental results demonstrate that the proposed algorithm achieves 92. 4% and 78. 7% preci⁃sion and 69. 4% and 56. 5% success rates on the 2nd and 3rd Anti-UAV datasets， respectively， with a running speedof 26. 9 framen per second， which significantly outperforms existing methods and achieves real-time and robust UAVtracking in complex scenarios

Key words: infrared target tracking, nti-UAV, complex background, anti-interference, real-time tracking, deep learning

CLC Number:

V279

Zicheng FENG, Wenlong ZHANG, Donghui LIU, Qifeng YU. Robust infrared target tracking algorithm for anti-UAV in complexbackgrounds[J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(4): 332264.

Figures/Tables 27

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Table 1

Dynamic hierarchical acceleration method

前一帧最大得分 $s ˜ m a x t - 1$	前一帧输出层级	动态层级加速策略				FPN	FLOPs/G	Time/ms
前一帧最大得分 $s ˜ m a x t - 1$	前一帧输出层级	0	1	2	3	FPN	FLOPs/G	Time/ms
［0，0.3）	0，1，2，3	√	√	√	√	0，1，2，3	352.84	41.28
［0.3，0.7］	0	√	√	×	×	0，1，2，3	335.54	36.35
	1	√	√	√	×	0，1，2，3	349.37	39.16
	2	×	√	√	√	1，2，3	128.92	24.26
	3	×	×	√	√	2，3	72.27	18.91
（0.7，1］	0	√	×	×	×	0，1，2，3	280.23	31.54
	1	×	√	×	×	1，2，3	111.63	19.77
	2	×	×	√	×	2，3	68.80	16.83
	3	×	×	×	√	3	57.76	15.87

Table 1

Fig.8

Fig.9

Table 2

Fig.10

Table 3

Comparison results of the proposed algorithms and 3 algorithms for tracking targets with different sizes

算法	尺寸范围
算法	$[0,10)$	$[10,20)$	$[20,40)$	$[40, + ∞)$
GlobalTrack	58.1/36.3	49.1/31.4	94.4/71.3	94.3/77.0
LTMU	50.4/37.2	55.1/39.6	95.8/74.8	95.0/78.1
SiamDT	55.8/33.1	52.8/37.7	95.2/72.7	95.6/78.3
STGT	62.4/40.0	55.7/39.7	96.3/73.7	94.8/77.5
STGT++	65.1/41.7	57.2/40.4	96.8/74.1	95.3/77.7

Table 3

Table 4

Fig.11

Fig.12

Table 5

Table 6

Fig.13

Table 7

Fig.14

Table 8

Fig.15

Table 9

Fig.16

Table 10

Parameter analysis of DHA

$s 1$	$s 2$
$s 1$	0.6	0.7	0.8
0.2	78.4/56.3/28.9	78.6/56.4/27.4	78.6/56.4/25.7
0.3	78.5/56.3/28.6	78.7/56.5/26.9	78.7/56.5/25.5
0.4	78.5/56.4/27.9	78.7/56.5/26.3	78.7/56.5/25.0
0.5	78.6/56.4/26.9	78.7/56.5/25.5	78.8/56.5/23.8

Table 10

Fig.A1

References 32

[1]	王传云，苏阳，王琳霖，等. 面向反制无人机集群的多目标连续鲁棒跟踪算法［J］. 航空学报， 2024， 45（7）： 329017.
	WANG C Y， SU Y， WANG L L， et al. Multi-object continuous robust tracking algorithm for anti-UAV swarm［J］. Acta Aeronautica et Astronautica Sinica， 2024， 45（7）： 329017 （in Chinese）.
[2]	王红涛，邓淼磊，赵文君，等. 基于深度学习的单目标跟踪算法综述［J］. 计算机系统应用， 2022， 31（5）： 40-51.
	WANG H T， DENG M L， ZHAO W J， et al. Survey on single object tracking algorithms based on deep learning［J］. Computer Systems and Applications， 2022， 31（5）： 40-51 （in Chinese）.
[3]	YAN B， PENG H W， FU J L， et al. Learning spatio-temporal transformer for visual tracking［C］∥2021 IEEE/CVF International Conference on Computer Vision （ICCV）. Piscataway： IEEE Press， 2021： 10428-10437.
[4]	YE B T， CHANG H， MA B P， et al. Joint feature learning and relation modeling for tracking： A one-stream framework［C］∥Computer Vision-ECCV 2022. Cham： Springer， 2022： 341-357.
[5]	CHEN X， PENG H W， WANG D， et al. SeqTrack： Sequence to sequence learning for visual object tracking［C］∥2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2023： 14572-14581.
[6]	DAI K N， ZHANG Y H， WANG D， et al. High-performance long-term tracking with meta-updater［C］∥2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2020： 6297-6306.
[7]	YU Q J， MA Y C， HE J F， et al. A unified transformer-based tracker for anti-UAV tracking［C］∥2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops （CVPRW）. Piscataway： IEEE Press， 2023： 3036-3046.
[8]	HUANG L H， ZHAO X， HUANG K Q. GlobalTrack： A simple and strong baseline for long-term tracking［J］. Proceedings of the AAAI Conference on Artificial Intelligence， 2020， 34（7）： 11037-11044.
[9]	HUANG B， LI J N， CHEN J J， et al. Anti-UAV410： A thermal infrared benchmark and customized scheme for tracking drones in the wild［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2024， 46（5）： 2852-2865.
[10]	REN S Q， HE K M， GIRSHICK R， et al. Faster R-CNN：Towards real-time object detection with region proposal networks［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2017， 39（6）： 1137-1149.
[11]	FANG H Z， WANG X L， LIAO Z K， et al. A real-time anti-distractor infrared UAV tracker with channel feature refinement module［C］∥2021 IEEE/CVF International Conference on Computer Vision Workshops （ICCVW）. Piscataway： IEEE Press， 2021： 1240.
[12]	JIANG N， WANG K R， PENG X K， et al. Anti-UAV： A large-scale benchmark for vision-based UAV tracking［J］. IEEE Transactions on Multimedia， 2021， 25： 486-500.
[13]	LI S J， ZHAO S， CHENG B， et al. Robust visual tracking via hierarchical particle filter and ensemble deep features［J］. IEEE Transactions on Circuits and Systems for Video Technology， 2020， 30（1）： 179-191.
[14]	HARE S， GOLODETZ S， SAFFARI A， et al. Struck： Structured output tracking with kernels［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence， 2016， 38（10）： 2096-2109.
[15]	HENRIQUES J F， CASEIRO R， MARTINS P， et al. Exploiting the circulant structure of tracking-by-detection with kernels［C］∥Computer Vision-ECCV 2012. Cham： Springer， 2012： 702-715.
[16]	LI B， WU W， WANG Q， et al. SiamRPN++： Evolution of Siamese visual tracking with very deep networks［C］∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2019： 4277-4286.
[17]	丁奇帅，雷帮军，吴正平. 基于孪生网络的轻量型无人机单目标跟踪算法［J］. 航空学报， 2025， 46（4）： 330925.
	DING Q S， LEI B J， WU Z P. A lightweight single object tracking algorithm for UAVs based on Siamese network ［J］. Acta Aeronautica et Astronautica Sinica， 2025， 46（4）： 330925 （in Chinese）.
[18]	MAYER C， DANELLJAN M， BHAT G， et al. Transforming model prediction for tracking［C］∥2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2022： 8721-8730.
[19]	ZHU Z， WANG Q， LI B， et al. Distractor-aware Siamese networks for visual object tracking［C］∥Computer Vision-ECCV 2018. Cham： Springer， 2018： 103-119.
[20]	HUANG B， CHEN J J， XU T F， et al. SiamSTA： Spatio-temporal attention based Siamese tracker for tracking UAVs［C］∥2021 IEEE/CVF International Conference on Computer Vision Workshops （ICCVW）. Piscataway： IEEE Press， 2021： 1204-1212.
[21]	CHEN X， YAN B， ZHU J W， et al. Transformer tracking ［C］∥2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2021： 8122-8131.
[22]	WEI X， BAI Y F， ZHENG Y C， et al. Autoregressive visual tracking［C］∥2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2023： 9697-9706.
[23]	XIE J X， ZHONG B N， MO Z Y， et al. Autoregressive queries for adaptive tracking with spatio-temporal transformers［C］∥2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2024： 19300-19309.
[24]	WU H， LI W Q， LI W Q， et al. A real-time robust approach for tracking UAVs in infrared videos［C］∥2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops （CVPRW）. Piscataway： IEEE Press， 2020： 4448-4455.
[25]	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 （CVPR）. Piscataway： IEEE Press， 2019： 4655-4664.
[26]	ZHAO J J， ZHANG X H， ZHANG P Y. A unified approach for tracking UAVs in infrared［C］∥2021 IEEE/CVF International Conference on Computer Vision Workshops （ICCVW）. Piscataway： IEEE Press， 2021： 1213-1222.
[27]	DANELLJAN M， VAN GOOL L， TIMOFTE R. Probabilistic regression for visual tracking［C］∥2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2020： 7181-7190.
[28]	SHI X J， CHEN Z R， WANG H， et al. Convolutional LSTM network： A machine learning approach for precipitation nowcasting［C］∥Proceedings of the 29th International Conference on Neural Information Processing Systems. New York： ACM， 2015： 802-810..
[29]	TIAN Z， SHEN C H， CHEN H， et al. FCOS： Fully convolutional one-stage object detection［C］∥2019 IEEE/CVF International Conference on Computer Vision （ICCV）. Piscataway： IEEE Press， 2019： 9626-9635.
[30]	BHAT G， DANELLJAN M， VAN GOOL L， et al. Learning discriminative model prediction for tracking［C］∥2019 IEEE/CVF International Conference on Computer Vision （ICCV）. Piscataway： IEEE Press， 2019： 6181-6190.
[31]	BHAT G， DANELLJAN M， VAN GOOL L， et al. Know your surroundings： Exploiting scene information for object tracking［C］∥Computer Vision-ECCV 2020. Cham： Springer， 2020： 205-221.
[32]	LIU Z， NING J， CAO Y， et al. Video swin transformer ［C］∥2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Piscataway： IEEE Press， 2022： 3192-3201.

算法	来源	1st Anti-UAV test-dev		2nd Anti-UAV test-dev		3rd Anti-UAV val
算法	来源	P/%	AUC/%	P/%	AUC/%	P/%	AUC/%
ATOM^［25］	CVPR 2019	79.3	61.6	72.5	54.1	58.5	43.1
DiMP^［30］	ICCV 2019	85.2	66.8	77.7	59.1	64.4	47.4
PrDiMP^［27］	CVPR 2020	89.1	69.2	82.2	61.3	66.4	49.0
KYS^［31］	ECCV 2020	85.8	67.3	78.4	59.6	67.1	49.0
STARK^［3］	ICCV 2021	89.4	69.5	82.2	62.0	69.0	48.8
TOMP^［18］	CVPR 2022	83.0	65.8	74.3	57.8	60.8	43.8
OSTrack^［4］	ECCV 2022	93.6	72.4	83.4	62.7	68.7	51.9
SeqTrack^［5］	CVPR 2023	73.2	55.3	66.9	50.1	62.0	43.5
AQATrack^［23］	CVPR 2024	90.9	70.3	80.7	60.9	66.2	47.5
DaSiamRPN^［19］	ECCV 2018	90.7	68.7	77.2	57.7	59.6	42.0
GlobalTrack^［8］	AAAI 2020	97.5	75.6	89.3	65.5	74.7	53.0
LTMU^［6］	CVPR 2020	96.7	75.8	88.3	68.6	73.3	55.4
SiamSTA^［20］ #	ICCVW 2021	96.9	72.6	88.8	65.5
SiamDT^［9］	PAMI 2024	97.7	76.4	89.4	68.5	75.0	53.3
STGT++（本文）		98.0	76.5	92.4	69.4	78.7	56.5

性能指标	DaSiamRPN	GlobalTrack	LTMU	SiamDT	STGT++ w/o DHA	STGT++
参数量/M	60.1	59.0	112.1	62.4	59.3	59.3
计算量/G	103.7 （541.1）	287.7	148.5 （346.9）	372.6	352.8	57.8~352.8
速度/（帧·s^-1）	22.7	22.3	1.5	9.1	18.7	26.9

性能指标	特征提取网络
性能指标	ResNet18	ResNet34	ResNet50	ResNet101
P/%	75.9	76.5	77.4	77.0
AUC/%	55.0	55.1	55.8	55.7
速度/ （帧·s^-1）	23.6	22.2	20.8	17.8

性能指标	时空特征融合方法
性能指标	无	ConvLSTM	Video SwinTransformer
P/%	76.8	77.4	75.0
AUC/%	55.3	55.8	54.2
速度/（帧·s^-1）	30.5	20.8	16.2

性能指标	CGR数量
性能指标	1	2	3	4
P/%	76.8	77.4	77.2	77.4
AUC/%	55.1	55.8	55.9	55.7
速度/（帧·s^-1）	23.3	20.8	18.6	16.3

Robust infrared target tracking algorithm for anti-UAV in complexbackgrounds

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 27

References 32

Related Articles 15

Recommended Articles

Metrics

Comments

STFF			TEIS	DHA	P/%	AUC/%	速度/ （帧·s^-1）
FF	Conv LTSM	B	TEIS	DHA	P/%	AUC/%	速度/ （帧·s^-1）
√					76.6	55.2	30.9
√	√				77.2	55.6	21.1
√	√	√			77.4	55.8	20.8
√	√	√	√		78.8	56.6	18.7
√	√	√	√	√	78.7	56.5	26.9

[1]	Leyan LI, Rennong YANG, Anxin GUO, Qi SONG, Jialiang ZUO. Beyond-visual-range air combat threat prediction and dynamic evasion method based on all-domain fire field theory [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(4): 332205-332205.
[2]	Ye TAO, Jinhui TANG, Zhen YAN, Chen ZHOU, Chong WANG. A trajectory imputation method integrating representation transformation and pattern regression [J]. Acta Aeronautica et Astronautica Sinica, 2026, 47(1): 332106-332106.
[3]	Jianyu XU, Li ZHOU, Zhanxue WANG, Jie SHI, Hao SHI. Calculation method for hypersonic plume infrared radiation based on a fast line-by-line calculation model [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(8): 630778-630778.
[4]	Lingjie MENG, Hongguang LI, Xinjun LI. SAR image simulation method guided by geomorphic category information [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(7): 331003-331003.
[5]	Zhihao ZHAO, Zhaohua YANG, Yun WU, Yuanjin YU. Single-photon counting imaging denoising method based on deep learning in low-light environment [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(3): 630531-630531.
[6]	Yiquan WU, Kang TONG. Research advances on deep learning-based small object detection in UAV aerial images [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(3): 30848-030848.
[7]	Zijian XIANG, Zhenyu MA, Xixiang YANG. Inversion of structural performance parameters of composite materials based on deep learning [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(24): 231877-231877.
[8]	Tianqi FAN, Zhengxia ZOU, Zhenwei SHI. Typical remote sensing target detection with data synthesis based on reinforcement learning [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(23): 631955-631955.
[9]	Kui LIU, Hao SUN, Han WU, Kefeng JI, Gangyao KUANG. Dynamic brightness reconstruction for UAV visible-infrared fusion object detection [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(23): 631968-631968.
[10]	Bo PENG, Jikang BAI, Weiwen CHEN, Xiangtao ZHENG, Jianjun LEI, Xiaoqiang LU. Research progress for UAV search and rescue methods based on deep learning [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(23): 632761-632761.
[11]	Qiushi CHEN, Jinglong GAO, Meng WANG, Wenkun BIAN, Haojun HAN. Overview of anti-interference technology of unmanned aerial vehicle satellite navigation system [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(17): 331797-331797.
[12]	Xiaowei JIANG, Yiquan WU. Research progress of UAV aerial image mosaic methods [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(17): 331799-331799.
[13]	Lin CHEN, Xiwen GU, Zhiying CHEN, Zhuo ZHANG, Xiaoliang SUN. High-precision monocular vision pose measurement for large distance span in carrier landing guidance [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(15): 331568-331568.
[14]	Bin SUN, Hang YOU, Wenbo LI, Xiangrui LIU, Jiayi MA. Dual-band payload image fusion and its applications in low-altitude remote sensing [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(11): 531343-531343.
[15]	Fanteng MENG, Yong QIN, Jing CUI, Yunpeng WU, Zicheng ZHANG, Shaowei WEI. Unknown risk detection in external environment of railroad using UAV images [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(11): 531262-531262.