
浏览全部资源
扫码关注微信
1.中国人民解放军海军装备部驻沈阳地区军事代表局, 辽宁 沈阳 110000
2.中国科学院 长春光学精密机械与物理研究所, 吉林 长春 130033
赵萌,男,学士,工程师,2014年于哈尔滨工程大学获得学士学位,主要从事机器视觉方面的研究。E-mail:635766103@qq.com
郑滨汐,男,硕士,助理研究员,2023年于哈尔滨工程大学获得硕士学位,主要从事深度学习目标跟踪算法的研究。E-mail:zhengbinxi@hrbeu.edu.cn
收稿:2026-04-30,
修回:2026-05-17,
纸质出版:2026-06-06
移动端阅览
赵萌, 郑滨汐, 孙翯, 等. 结合注意力与抗遮挡策略的无人机航拍目标跟踪[J]. 液晶与显示, 2026,41(6):908-923.
ZHAO Meng, ZHENG Binxi, SUN He, et al. UAV aerial target tracking with attention mechanism and anti-occlusion strategies[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(6): 908-923.
赵萌, 郑滨汐, 孙翯, 等. 结合注意力与抗遮挡策略的无人机航拍目标跟踪[J]. 液晶与显示, 2026,41(6):908-923. DOI: 10.37188/CJLCD.2026-0076. CSTR: 32172.14.CJLCD.2026-0076.
ZHAO Meng, ZHENG Binxi, SUN He, et al. UAV aerial target tracking with attention mechanism and anti-occlusion strategies[J]. Chinese Journal of Liquid Crystals and Displays, 2026, 41(6): 908-923. DOI: 10.37188/CJLCD.2026-0076. CSTR: 32172.14.CJLCD.2026-0076.
为了解决无人机在目标跟踪任务中存在的复杂干扰、目标遮挡等问题,提出了一种引入注意力机制和目标遮挡判别机制的孪生神经网络目标跟踪算法SiamAL,以及其融合目标检测算法的变体SiamAL-Det。基于SiamDMU算法,首先在主干网络引入注意力机制,同时采用新的激活函数h-swish,提升了复杂干扰条件下的特征表征能力;其次,引入基于卡尔曼滤波的运动先验对目标轨迹进行估计,利用跟踪器置信度联合预测‑观测残差对跟踪状态进行分级判别:在严重遮挡时,自适应提高运动先验权重,从而在遮挡期间保持轨迹连续性;最后设计一种融合检测与跟踪的算法框架来提升实际跟踪效果,在判定跟踪失败或严重漂移时,触发轻量检测分支进行重检测与纠正。在数据集UAV123上,SiamAL以及SiamAL-Det算法的成功率和精确率分别达到了65.3%、86.6%和68.6%、88.8%,相比基准算法SiamDMU分别提升了2.5%、3.7%和5.8%、5.9%。与多种主流基于孪生网络的跟踪算法对比,成功率和精确率表现更优,表明提出的方法在无人机航拍场景中具有良好的应用前景。
To address the challenges of complex interference and target occlusion in UAV target tracking, a Siamese network-based tracker named SiamAL is proposed, which incorporates an attention mechanism and an occlusion-discrimination module, along with its variant SiamAL-Det that additionally integrates an object detection module. Based on the SiamDMU algorithm, an attention mechanism is first introduced into the backbone network, and the h-swish activation function is adopted to enhance feature representation under complex interference conditions. A Kalman-filter-based motion prior is then introduced to estimate the target trajectory, and the tracking state is evaluated based on tracker confidence and prediction-observation residuals. In cases of severe occlusion, the motion prior weight is adaptively increased to maintain trajectory continuity. Finally, an integrated detection-and-tracking framework is designed to enhance tracking performance. A lightweight detection branch is triggered for re-detection and correction upon tracking failure or severe drift. Experimental results on the UAV123 dataset show that SiamAL achieves a success rate of 65.3% and a precision rate of 86.6%, while SiamAL-Det achieves 68.6% and 88.8%, respectively. In comparison with several mainstream Siamese network-based trackers, SiamAL outperforms in both success rate and precision, demonstrating the promising application prospects of the proposed method in UAV aerial tracking scenarios.
苗宗成 , 高世严 , 贺泽民 , 等 . 基于孪生网络的目标跟踪算法 [J]. 液晶与显示 , 2023 , 38 ( 2 ): 256 - 266 . doi: 10.37188/CJLCD.2022-0186 http://dx.doi.org/10.37188/CJLCD.2022-0186
MIAO Z C , GAO S Y , HE Z M , et al . Single-objective tracking algorithm based on Siamese networks [J]. Chinese Journal of Liquid Crystals and Displays , 2023 , 38 ( 2 ): 256 - 266 . (in Chinese) . doi: 10.37188/CJLCD.2022-0186 http://dx.doi.org/10.37188/CJLCD.2022-0186
BERTINETTO L , VALMADRE J , HENRIQUES J F , et al . Fully-convolutional Siamese networks for object tracking [C]// Computer Vision-ECCV 2016 Workshops . Amsterdam : ECCV , 2016 : 850 - 865 . doi: 10.1007/978-3-319-48881-3_56 http://dx.doi.org/10.1007/978-3-319-48881-3_56
LI B , WU W , WANG Q , et al . SiamRPN++: evolution of Siamese visual tracking with very deep networks [C]// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Long Beach : IEEE , 2019 : 4277 - 4286 . doi: 10.1109/cvpr.2019.00441 http://dx.doi.org/10.1109/cvpr.2019.00441
LI B , YAN J J , WU W , et al . High performance visual tracking with Siamese region proposal network [C]// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City : IEEE , 2018 : 8971 - 8980 . doi: 10.1109/cvpr.2018.00935 http://dx.doi.org/10.1109/cvpr.2018.00935
HUANG B , XU T F , SHEN Z Y , et al . SiamATL: online update of Siamese tracking network via attentional transfer learning [J]. IEEE Transactions on Cybernetics , 2022 , 52 ( 8 ): 7527 - 7540 . doi: 10.1109/tcyb.2020.3043520 http://dx.doi.org/10.1109/tcyb.2020.3043520
CHEN Z D , ZHONG B N , LI G R , et al . Siamese box adaptive network for visual tracking [C]// Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Seattle : IEEE , 2020 : 6667 - 6676 . doi: 10.1109/cvpr42600.2020.00670 http://dx.doi.org/10.1109/cvpr42600.2020.00670
MUELLER M , SMITH N , GHANEM B . A benchmark and simulator for UAV tracking [C]. 14th European Conference on Computer Vision . Amsterdam : ECCV , 2016 : 445 - 461 . doi: 10.1007/978-3-319-46448-0_27 http://dx.doi.org/10.1007/978-3-319-46448-0_27
LIU J , WANG H , MA C , et al . SiamDMU: Siamese dual mask update network for visual object tracking [J]. IEEE Transactions on Emerging Topics in Computational Intelligence , 2024 , 8 ( 2 ): 1656 - 1669 . doi: 10.1109/tetci.2024.3353674 http://dx.doi.org/10.1109/tetci.2024.3353674
MA J Y , REN J L , ZHANG J H , et al . Quantum imaging using spatially entangled photon pairs from a nonlinear metasurface [J]. eLight , 2025 , 5 ( 1 ): 2 . doi: 10.1186/s43593-024-00080-8 http://dx.doi.org/10.1186/s43593-024-00080-8
HAN G R , ERYILMAZ M , GONCHAROV A , et al . Deep learning-enhanced dual-mode multiplexed optical sensor for point-of-care diagnostics of cardiovascular diseases [J]. Light: Science Applications , 2026 , 15 ( 1 ): 190 . doi: 10.1038/s41377-026-02275-9 http://dx.doi.org/10.1038/s41377-026-02275-9
徐逸 , 甄佳宁 , 蒋侠朋 , 等 . 无人机遥感与XGBoost的红树林物种分类 [J]. 遥感学报 , 2021 , 25 ( 3 ): 737 - 752 .
XU Y , ZHEN J N , JIANG X P , et al . Mangrove species classification with UAV-based remote sensing data and XGBoost [J]. National Remote Sensing Bulletin , 2021 , 25 ( 3 ): 737 - 752 . (in Chinese)
郭庆华 , 胡天宇 , 刘瑾 , 等 . 轻小型无人机遥感及其行业应用进展 [J]. 地理科学进展 , 2021 , 40 ( 9 ): 1550 - 1569 . doi: 10.18306/dlkxjz.2021.09.010 http://dx.doi.org/10.18306/dlkxjz.2021.09.010
GUO Q H , HU T Y , LIU J , et al . Advances in light weight unmanned aerial vehicle remote sensing and major industrial applications [J]. Progress in Geography , 2021 , 40 ( 9 ): 1550 - 1569 . (in Chinese) . doi: 10.18306/dlkxjz.2021.09.010 http://dx.doi.org/10.18306/dlkxjz.2021.09.010
吴志成 , 林秀贵 , 许家浩 , 等 . 一种采用航拍图像识别高压输电线路防震锤缺失的检测算法 [J]. 应用科技 , 2021 , 48 ( 5 ): 35 - 41,53 .
WU Z C , LIN X G , XU J H , et al . An algorithm for missing detection of anti-vibration hammer on high voltage transmission line based on aerial image [J]. Computing magazine of the CCF , 2021 , 48 ( 5 ): 35 - 41, 53 . (in Chinese)
张志豪 , 厉小润 , 陈淑涵 . 基于改进YOLO11的无人机航拍图像小目标检测算法 [J]. 液晶与显示 , 2025 , 40 ( 6 ): 915 - 930 . doi: 10.37188/cjlcd.2025-0010 http://dx.doi.org/10.37188/cjlcd.2025-0010
ZHANG Z H , LI X R , CHEN S H . Small object detection algorithm in UAV aerial images based on improved YOLO11 [J]. Chinese Journal of Liquid Crystals and Displays , 2025 , 40 ( 6 ): 915 - 930 . (in Chinese) . doi: 10.37188/cjlcd.2025-0010 http://dx.doi.org/10.37188/cjlcd.2025-0010
SOLEIMANITALEB Z , KEYVANRAD M A , JAFARI A . Object tracking methods: a review [C]. 2019 9th International Conference on Computer and Knowledge Engineering (ICCKE). Mashhad : IEEE , 2019 : 282 - 288 . doi: 10.1109/iccke48569.2019.8964761 http://dx.doi.org/10.1109/iccke48569.2019.8964761
CHENG F , LIANG Z B , PENG G L , et al . An anti-UAV long-term tracking method with hybrid attention mechanism and hierarchical discriminator [J]. Sensors , 2022 , 22 ( 10 ): 3701 . doi: 10.3390/s22103701 http://dx.doi.org/10.3390/s22103701
HUANG B , CHEN J J , XU T F , et al . SiamSTA: spatio-temporal attention based Siamese tracker for tracking UAVs [C]// Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision Workshops . Montreal : IEEE , 2021 : 1204 - 1212 . doi: 10.1109/iccvw54120.2021.00140 http://dx.doi.org/10.1109/iccvw54120.2021.00140
李大湘 , 辛嘉妮 , 刘颖 . 位置敏感Transformer航拍图像目标检测模型 [J]. 光学 精密工程 , 2024 , 32 ( 5 ): 727 - 739 . doi: 10.37188/ope.20243205.0727 http://dx.doi.org/10.37188/ope.20243205.0727
LI D X , XIN J N , LIU Y . Position-sensitive Transformer aerial image object detection model [J]. Optics and Precision Engineering , 2024 , 32 ( 5 ): 727 - 739 . doi: 10.37188/ope.20243205.0727 http://dx.doi.org/10.37188/ope.20243205.0727
YUAN X Y , XU T F , LIU X C , et al . Multi-step temporal modeling for UAV tracking [J]. IEEE Transactions on Circuits and Systems for Video Technology , 2024 , 34 ( 8 ): 7216 - 7230 . doi: 10.1109/tcsvt.2024.3375366 http://dx.doi.org/10.1109/tcsvt.2024.3375366
LIU X C , XU T F , WANG Y , et al . BACTrack: building appearance collection for aerial tracking [J]. IEEE Transactions on Circuits and Systems for Video Technology , 2024 , 34 ( 6 ): 5002 - 5017 . doi: 10.1109/tcsvt.2023.3340372 http://dx.doi.org/10.1109/tcsvt.2023.3340372
PANG H B , SU J , MA R Q , et al . Multiple templates transformer for visual object tracking [J]. Knowledge-Based Systems , 2023 , 280 : 111025 . doi: 10.1016/j.knosys.2023.111025 http://dx.doi.org/10.1016/j.knosys.2023.111025
HOWARD A , SANDLER M , CHU G , et al . Searching for MobileNetV3 [C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision . Seoul : IEEE , 2019 : 1314 - 1324 . doi: 10.1109/iccv.2019.00140 http://dx.doi.org/10.1109/iccv.2019.00140
ZHOU L J , ZHANG J L . Combined Kalman filter and multifeature fusion Siamese network for real-time visual tracking [J]. Sensors , 2019 , 19 ( 9 ): 2201 . doi: 10.3390/s19092201 http://dx.doi.org/10.3390/s19092201
FU C H , LU K H , ZHENG G Z , et al . Siamese object tracking for unmanned aerial vehicle: a review and comprehensive analysis [J/OL]. arXiv , 2022 : 2205 . 04281 . doi: 10.1007/s10462-023-10558-5 http://dx.doi.org/10.1007/s10462-023-10558-5
黄鹤 , 张科 , 陈永安 , 等 . 一种无人机航拍目标的长期跟踪算法 [J]. 哈尔滨工业大学学报 , 2022 , 54 ( 5 ): 104 - 116 .
HUANG H , ZHANG K , CHEN Y A , et al . A long-term tracking algorithm for UAV aerial photography [J]. Journal of Harbin Institute of Technology , 2022 , 54 ( 5 ): 104 - 116 . (in Chinese)
HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C]// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas : IEEE , 2016 : 770 - 778 . doi: 10.1109/cvpr.2016.90 http://dx.doi.org/10.1109/cvpr.2016.90
WOO S , PARK J , LEE J Y , et al . CBAM: convolutional block attention module [C]// Proceedings of the 15th European Conference on Computer Vision (ECCV) . Munich : ECCV , 2018 : 3 - 19 . doi: 10.1007/978-3-030-01234-2_1 http://dx.doi.org/10.1007/978-3-030-01234-2_1
闫纲琦 , 梁宗林 , 宋延嵩 , 等 . 基于注意力残差网络的快照式多光谱相机图像重构 [J]. 中国光学(中英文) , 2024 , 17 ( 6 ): 1316 - 1328 . doi: 10.37188/co.2023-0196 http://dx.doi.org/10.37188/co.2023-0196
YAN G Q , LIANG Z L , SONG Y S , et al . Image reconstruction of snapshot multispectral camera based on an attention residual network [J]. Chinese Optics , 2024 , 17 ( 6 ): 1316 - 1328 . (in Chinese) . doi: 10.37188/co.2023-0196 http://dx.doi.org/10.37188/co.2023-0196
王伯霄 , 宋延嵩 , 董小娜 . 难点注意力感知红外小目标检测网络 [J]. 中国光学(中英文) , 2024 , 17 ( 3 ): 538 - 547 . doi: 10.37188/co.2023-0178 http://dx.doi.org/10.37188/co.2023-0178
WANG B X , SONG Y S , DONG X N . Indistinguishable points attention-aware network for infrared small object detection [J]. Chinese Optics , 2024 , 17 ( 3 ): 538 - 547 . (in Chinese) . doi: 10.37188/co.2023-0178 http://dx.doi.org/10.37188/co.2023-0178
SUN L F , YANG Z , ZHANG J J , et al . Visual object tracking for unmanned aerial vehicles based on the template-driven Siamese network [J]. Remote Sensing , 2022 , 14 ( 7 ): 1584 . doi: 10.3390/rs14071584 http://dx.doi.org/10.3390/rs14071584
ZHU Z , WANG Q , LI B , et al . Distractor-aware Siamese networks for visual object tracking [C]// Proceedings of the 15th European Conference on Computer Vision (ECCV) . Munich : ECCV , 2018 : 103 - 119 . doi: 10.1007/978-3-030-01240-3_7 http://dx.doi.org/10.1007/978-3-030-01240-3_7
BHAT G , DANELLJAN M , VAN GOOL L , et al . Learning discriminative model prediction for tracking [C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision . Seoul : IEEE , 2019 : 6181 - 6190 . doi: 10.1109/iccv.2019.00628 http://dx.doi.org/10.1109/iccv.2019.00628
0
浏览量
164
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621