Unmanned Aerial Vehicle Target Tracking Algorithm Based on Lightweight Siamese Networks

ZHONG Xiaowei; WANG Zhisheng; CONG Yuhua

doi:10.15892/j.cnki.djzdxb.2023.05.004

Journal of Projectiles, Rockets, Missiles and Guidance >

2023 , Vol. 43 >Issue 5: 25 - 33

DOI: https://doi.org/10.15892/j.cnki.djzdxb.2023.05.004

Unmanned Aerial Vehicle Target Tracking Algorithm Based on Lightweight Siamese Networks

ZHONG Xiaowei ,
WANG Zhisheng ,
CONG Yuhua

Expand

School of Automation, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, Jiangsu, China

Received date: 2023-06-01

Online published: 2024-12-30

Fold

Abstract

Aiming to address the difficulties in balancing tracking performance and real-time capability in visual object tracking, a lightweight twin-network object tracking algorithm called SiamLD is proposed. The main network is designed to be lightweight to reduce the number of parameters and computation, thus improving the real-time performance of the algorithm. In addition, a high-low-level feature fusion module is used to enhance the utilization of low-level semantic information, and the tracking performance is improved by using multi-branch cross-correlation and fully intersect-and-union method. Experimental results on the UAV123 and DTB70 tracking benchmarks show that the SiamLD algorithm outperforms other mainstream algorithms, and it runs at a speed of 41FPS on unmanned aerial vehicle platforms, effectively balancing tracking performance and real-time capability.

Key words： UAV; target tracking; siamese network; lightweight; feature fusion

Cite this article

ZHONG Xiaowei , WANG Zhisheng , CONG Yuhua . Unmanned Aerial Vehicle Target Tracking Algorithm Based on Lightweight Siamese Networks[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2023 , 43(5) : 25 -33 . DOI: 10.15892/j.cnki.djzdxb.2023.05.004

[an error occurred while processing this directive]

References

Publishing order | Descend order by publishing year | Descend order by cited within

[1]	闫超, 涂良辉, 王聿豪. 无人机在我国民用领域应用综述[J]. 飞行力学, 2022, 40(03): 1-6. YAN C, TU L H, WANG Y H, et al. Application of unmanned aerial vehicle in civil field in China[J]. Flight Dynamics, 2022, 40(03): 1-6.

[2]	王梦亭, 杨文忠, 武雍智. 基于孪生网络的单目标跟踪算法综述[J]. 计算机应用, 2023, 43(3): 661-673. DOI WANG M T, YANG W Z, WU Y Z. Survey of single target tracking algorithms based on Siamese network[J]. Journal of Computer Applications, 2023, 43(3): 661-673. DOI

[3]	陈琳, 刘允刚. 面向无人机的视觉目标跟踪算法: 综述与展望[J]. 信息与控制, 2022, 51(1): 23-40. DOI CHEN L, LIU Y G. UAV visual target tracking algorithms: review and future prospect[J]. Information and Control, 2022, 51(1): 23-40. DOI

[4]	BOLME D S, BEVERIDGE J R, DRAPER B A, et al. Visual object tracking using adaptive correlation filters[C]// IEEE. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2010: 2544-2550.

[5]	HENRIQUES J F, RUI C, MARTINS P, et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]// ECCV. Proceedings of the 12th European conference on Computer Vision. Berlin:Springer, 2012: 702-715.

[6]	HENRIQUES J F, RUI C, MARTINS P, et al. High-speed tracking with kernelized correlation filters[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 37(3): 583-596.

[7]	BERTINETTO L, VALMADRE J, HENRIQUES J F, et al. Fully-convolutional siamese networks for object tracking[C]// ECCV. Proceedings of European Conference on Computer Vision. Berlin:Springer, 2016: 850-865.

[8]	BO L, YAN J, WEI W, et al. High performance visual tracking with siamese region proposal network[C]// IEEE. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2018: 8971-8980.

[9]	LI B, WU W, WANG Q, et al. SiamRPN++: evolution of Siamese visual tracking with very deep networks[C]// IEEE. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2019: 4282-4291.

[10]	CAO Z, HUANG Z, PAN L, et al. TCTrack: temporal contexts for aerial tracking[C]// IEEE. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern recognition. New York: IEEE, 2022: 14798-14808.

[11]	YAN B, PENG H, FU J, et al. Learning spatio-temporal transformer for visual tracking[C] // IEEE. Proceedings of IEEE/CVF International Conference on Computer Vision. New York: IEEE, 2021: 10428-10437.

[12]	WANG Q, WU B, ZHU P, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks[C]// IEEE. Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2020: 11531-11540.

[13]	ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[C]// Proceedings of AAAI Conference on Artificial Intelligence. New York: AAAI, 2020: 12993-13000.

[14]	HUANG L, ZHAO X, HUANG K. GOT-10k: a large high-diversity benchmark for generic object tracking in the wild[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 43(5): 1562-1577.

[15]	FAN H, BAI H, LIN L, et al. LaSOT: a high-quality large-scale single object tracking benchmark[J]. International Journal of Computer Vision, 2020, 129(2): 439-461.

[16]	RUSSAKOVSKY O, DENG J, SU H, et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015, 115(3): 211-252.

[17]	TSUNG Y L, MAIRE M, SERGE J, et al. Microsoft COCO: Common objects in context[C]// ECCV. Proceedings of European Conference on Computer Vision. Berlin:Springer, 2014: 740-755.

[18]	MUELLER M, SMITH N, GHANEM B. A benchmark and simulator for UAV tracking[C]// ECCV. Proceedings of European Conference on Computer Vision. Berlin:Springer, 2016: 445-461.

[19]	LI S Y, YEUNG D Y. Visual object tracking for unmanned aerial vehicles: a benchmark and new motion models[C]// AAAI. Proceedings of AAAI Conference on Artificial Intelligence. San Francisco: AAAI, 2017: 1-7.

[20]	DANELLJAN M, HAGER G, KHAN F, et al. Accurate scale estimation for robust visual tracking[C]// BMVC. Proceedings of the 2014 British Machine Vision Conference. Guildford: BMVC, 2014: 1-5.

[21]	DANELLJAN M, HAGER G, SHAHBAZ KHAN F, et al. Learning spatially regularized correlation filters for visual tracking[C]// IEEE. Proceedings of the IEEE International Conference on Computer Vision. New York: IEEE Computer Society, 2015: 4310-4318.

[22]	WANG N, SONG Y, MA C, et al. Unsupervised deep tracking[C]// IEEE. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2019: 1308-1317.

[23]	DANELLJAN M, BHAT G, SHAHBAZ KHAN F, et al. ECO: efficient convolution operators for tracking[C]// IEEE. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017: 6638-6646.

[24]	LI X, MA C, WU B, et al. Target-aware deeptracking[C]// IEEE. Proceedings of the IEEE Conferenceon Computer Vision and Pattern Recognition. New York: IEEE, 2019: 1369-1378.

[25]	ZHANG Z, PENG H. Deeper and wider siamese networks for real-time visual tracking[C]// IEEE. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE Computer Society, 2019: 4591-4600.

[26]	CHEN Z, ZHONG B, LI G, et al. Siamese box adaptive network for visual tracking[C]// IEEE. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2020: 6667-6676.

[27]	FU C, CAO Z, LI Y, et al. Siamese anchor proposal network for high-speed aerial tracking[C]// IEEE. Proceedings of IEEE International Conference on Robotics and Automation. New York: IEEE, 2021: 510-516.

[28]	CAO Z, FU C H, YE J J, et al. SiamAPN++: siamese attentional aggregation network for real-time UAV tracking[C]// IEEE. Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. New York: IEEE, 2021: 3086-3092.

Options

Outlines