基于深度学习的多无人机多目标跟踪

doi:10.19678/j.issn.1000-3428.0069100

摘要/Abstract

摘要：

无人机(UAV)多目标跟踪技术在交通运营、安全监测、水域巡检等领域受到广泛关注。然而, 目前已有的多目标跟踪算法多用于单无人机多目标跟踪, 而单无人机的视角通常具有一定的局限性, 当目标被遮挡时目标发生ID切换会导致跟踪失败。为了解决该问题, 提出一种多无人机多目标跟踪(MUMTTrack)算法。采用基于检测的跟踪(TBD)范式, 利用多架无人机同时跟踪目标, 弥补单无人机视角的局限性。为了有效融合多架无人机的跟踪结果, 为MUMTTrack设计一种基于加速鲁棒特征(SURF)算法的图像匹配策略和ID分配策略。将MUMTTrack算法的性能与当前主流的单无人机多目标跟踪算法在MDMT数据集上进行实验比较。实验结果表明, MUMTTrack算法在识别F1(IDF1)值和多目标跟踪精度(MOTA)这两个多目标跟踪性能指标上均表现出明显的优势。

关键词: 无人机, 遮挡目标, 多无人机跟踪, 多目标跟踪, 目标关联

Abstract:

Unmanned Aerial Vehicle (UAV) Multi-Object Tracking (MOT) technology is widely used in various fields such as traffic operation, safety monitoring, and water area inspection. However, existing MOT algorithms are primarily designed for single-UAV MOT scenarios. The perspective of a single-UAV typically has certain limitations, which can lead to tracking failures when objects are occluded, thereby causing ID switching. To address this issue, this paper proposes a Multi-UAV Multi-Object Tracking (MUMTTrack) algorithm. The MUMTTrack network adopts an MOT paradigm based on Tracking By Detection (TBD), utilizing multiple UAVs to track objects simultaneously and compensating for the perspective limitations of a single-UAV. Additionally, to effectively integrate the tracking results from multiple UAVs, an ID assignment strategy and an image matching strategy are designed based on the Speeded Up Robust Feature (SURF) algorithm for MUMTTrack. Finally, the performance of MUMTTrack is compared with that of existing widely used single-UAV MOT algorithms on the MDMT dataset. According to the comparative analysis, MUMTTrack demonstrates significant advantages in terms of MOT performance metrics, such as the Identity F1 (IDF1) value and Multi-Object Tracking Accuracy (MOTA).

Key words: Unmanned Aerial Vehicle (UAV), occluded object, multi-UAV tracking, Multi-Object Tracking (MOT), object association

周翰祺, 方东旭, 张宁波, 孙文生. 基于深度学习的多无人机多目标跟踪[J]. 计算机工程, 2025, 51(4): 57-65.

ZHOU Hanqi, FANG Dongxu, ZHANG Ningbo, SUN Wensheng. Multi-UAV Multi-Object Tracking Based on Deep Learning[J]. Computer Engineering, 2025, 51(4): 57-65.

https://www.ecice06.com/CN/Y2025/V51/I4/57

图/表 10

图1 YOLOX网络结构

Fig.1 Structure of the YOLOX network

图2 MUMTTrack网络结构

Fig.2 Structure of the MUMTTrack network

图3 基于匹配点提取的透视变换矩阵计算

Fig.3 Perspective transformation matrix calculating based on matching point extraction

图4 MDMT部分数据集

Fig.4 Partial MDMT dataset

图5 目标被遮挡情况下单无人机多目标跟踪算法与多无人机多目标跟踪算法的跟踪结果对比

Fig.5 Comparison of tracking results between single-UAV MOT algorithm and multi-UAV MOT algorithm in the presence of occluded objects

参考文献 26

1	杨洋, 宋品德, 钟春来, 等. 无人机视角下基于深度学习的多目标跟踪研究进展. 计算机工程与应用, 2023, 59(23): 48- 62.
	YANG Y, SONG P D, ZHONG C L, et al. Research progress of multi-target tracking based on deep learning from perspective of UAV. Computer Engineering and Applications, 2023, 59(23): 48- 62.
2	周海赟, 项学智, 王馨遥, 等. 多特征融合的端到端链式行人多目标跟踪网络. 计算机工程, 2022, 48(9): 305- 313. doi: 10.19678/j.issn.1000-3428.0062296
	ZHOU H Y, XIANG X Z, WANG X Y, et al. Chained end-to-end pedestrian multi-object tracking network with multi-feature fusion. Computer Engineering, 2022, 48(9): 305- 313. doi: 10.19678/j.issn.1000-3428.0062296
3	贺愉婷, 车进, 吴金蔓. 基于YOLOv5和重识别的行人多目标跟踪方法. 液晶与显示, 2022, 37(7): 880- 890.
	HE Y T, CHE J, WU J M. Pedestrian multi-target tracking method based on YOLOv5 and person re-identification. Chinese Journal of Liquid Crystals and Displays, 2022, 37(7): 880- 890.
4	谭芳, 穆平安, 马忠雪. 基于YOLOv3检测和特征点匹配的多目标跟踪算法. 计量学报, 2021, 42(2): 157- 162.
	TAN F, MU P A, MA Z X. Multi-target tracking algorithm based on YOLOv3 detection and feature point matching. Acta Metrologica Sinica, 2021, 42(2): 157- 162.
5	金立生, 华强, 郭柏苍, 等. 基于优化DeepSort的前方车辆多目标跟踪. 浙江大学学报(工学版), 2021, 55(6): 1056- 1064.
	JIN L S, HUA Q, GUO B C, et al. Multi-target tracking of vehicles based on optimized DeepSort. Journal of ZheJiang University (Engineering Science), 2021, 55(6): 1056- 1064.
6	安志强, 李智军, 刘硕, 等. 融合YOLOv7和BYTE多目标跟踪的多类别海珍品计数方法. 农业工程学报, 2023, 39(9): 183- 189.
	AN Z Q, LI Z J, LIU S, et al. Multi-category sea foods counting method integrating YOLOv7 and BYTE multi-target tracking. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(9): 183- 189.
7	CHONG C Y. An overview of machine learning methods for multiple target tracking[C]//Proceedings of the 2021 IEEE 24th International Conference on Information Fusion. Washington D.C., USA: IEEE Press, 2021: 1-9.
8	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D.C., USA: IEEE Press, 2016: 779-788.
9	REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137- 1149.
10	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector. Berlin, Germany: Springer, 2016.
11	LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of the IEEE International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2017: 2980-2988.
12	GE Z, LIU S T, WANG F, et al. YOLOX: exceeding YOLO series in 2021[EB/OL]. [2023-11-10]. http://arxiv.org/abs/2107.08430v2.
13	BEWLEY A, GE Z Y, OTT L, et al. Simple online and realtime tracking[C]//Proceedings of the IEEE International Conference on Image Processing (ICIP). Washington D.C., USA: IEEE Press, 2016: 3464-3468.
14	WOJKE N, BEWLEY A, PAULUS D. Simple online and realtime tracking with a deep association metric[C]//Proceedings of the IEEE International Conference on Image Processing (ICIP). Washington D.C., USA: IEEE Press, 2017: 3645-3649.
15	ZHANG Y F, SUN P Z, JIANG Y, et al. ByteTrack: multi-object tracking by associating every detection box. Berlin, Germany: Springer, 2022.
16	MILAN A, LEAL-TAIXE L, REID I, et al. MOT16: a benchmark for multi-object tracking[EB/OL]. [2023-11-10]. http://arxiv.org/abs/1603.00831v2.
17	LIU Z H, SHANG Y Y, LI T M, et al. Robust multi-drone multi-target tracking to resolve target occlusion: a benchmark. IEEE Transactions on Multimedia, 2023, 25, 1462- 1476.
18	BAY H, ESS A, TUYTELAARS T, et al. Speeded-Up Robust Features (SURF). Computer Vision and Image Understanding, 2008, 110(3): 346- 359.
19	PETERSON L. k-nearest neighbor. Scholarpedia, 2009, 4(2): 1883.
20	FISCHLER M, BOLLES R. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 1981, 24(6): 381- 395.
21	LOWE D G. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91- 110.
22	BERNARDIN K, STIEFELHAGEN R. Evaluating multiple object tracking performance: the CLEAR MOT metrics. EURASIP Journal on Image and Video Processing, 2008(1): 246309.
23	BOTTOU L. Stochastic gradient descent tricks. Berlin, Germany: Springer, 2012.
24	FENG C J, ZHONG Y J, GAO Y, et al. Tood: task-aligned one-stage object detection[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). Washington D.C., USA: IEEE Press, 2021: 1-7.
25	ZHU B J, WANG J F, JIANG Z K, et al. AutoAssign: differentiable label assignment for dense object detection[EB/OL]. [2023-11-10]. http://arxiv.org/abs/2007.03496v3.
26	WANG J, CHEN K, XU R, et al. Carafe: content-aware reassembly of features[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. Washington D.C., USA: IEEE Press, 2019: 3007-3016.

[1]	林绍福, 陈盈盈, 李硕朋. 基于深度强化学习的多无人机能量传输与边缘计算联合优化方法[J]. 计算机工程, 2025, 51(3): 144-154.
[2]	崔金荣, 叶伟浩, 郑鸿, 刘同来, 齐龙, 徐勇. 基于域自适应NWD-YOLOv5的复杂环境下水稻幼苗计数[J]. 计算机工程, 2025, 51(3): 320-333.
[3]	徐渊博, 任静, 王亮, 符宁, 於志文. 面向无人机辅助边缘计算的卸载任务准入控制机制[J]. 计算机工程, 2025, 51(2): 54-64.
[4]	秦媛, 张杭, 朱宏鹏, 李炯, 胡航. 卫星MIMO通信系统抗移动无人机集群干扰的在线BSS算法[J]. 计算机工程, 2024, 50(6): 65-76.
[5]	赵继达, 甄国涌, 储成群. 基于YOLOv8的无人机图像目标检测算法[J]. 计算机工程, 2024, 50(4): 113-120.
[6]	吴嘉鑫, 孙一飞, 吴亚兰, 武继刚. 面向安全传输的低能耗无人机轨迹优化算法[J]. 计算机工程, 2024, 50(2): 59-67.
[7]	王林, 赵莉, 王无为. 高动态场景下无人机空对空目标检测[J]. 计算机工程, 2024, 50(12): 265-275.
[8]	张文政, 吴长悦, 满卫东, 刘明月, 赵文. 双通道对抗网络在建筑物分割中的应用[J]. 计算机工程, 2024, 50(11): 297-307.
[9]	谌海云, 余鹏, 王海川. 时域孪生网络融合Transformer的长时无人机视觉跟踪[J]. 计算机工程, 2024, 50(11): 107-118.
[10]	万昊楠, 吴飞, 尹玲. 基于自适应无人机数量的节时部署优化算法[J]. 计算机工程, 2024, 50(10): 302-312.
[11]	李松江, 耿兰兰, 王鹏. 基于改进Yolov4的车辆目标检测[J]. 计算机工程, 2023, 49(4): 272-280.
[12]	白俊卿, 韩柏迅, 张丰侠. 基于深度学习的无人机图像语义分割算法研究[J]. 计算机工程, 2023, 49(4): 233-239.
[13]	周海赟, 项学智, 王馨遥, 任文凯. 多特征融合的端到端链式行人多目标跟踪网络[J]. 计算机工程, 2022, 48(9): 305-313.
[14]	马华伟, 马凯, 郭君. 考虑多投递的带无人机车辆路径规划问题研究[J]. 计算机工程, 2022, 48(8): 299-305.
[15]	赵蓓英, 姬伟峰, 翁江, 吴玄, 李映岐. 基于启发式Q学习的FANET可信路由算法[J]. 计算机工程, 2022, 48(5): 162-169.

选择文件类型/文献管理软件名称

选择包含的内容