Robust visual tracking for UAVs with dynamic feature weight selection | Applied Intelligence Skip to main content
Springer Nature Link
Log in

Robust visual tracking for UAVs with dynamic feature weight selection

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

The low reliability of feature and tracking box detection remains a problem in visual object tracking. Currently, most discriminative correlation filter (DCF) trackers integrate multiple types of features with fixed weights. However, these approaches cannot be adapted to complex scenes when fixed weights are used for features. In addition, the tracking box of traditional DCF trackers lacks scale and aspect ratio adaptability, which can inevitably lead to excessive background noise. To address these problems, we propose a robust tracking method for unmanned aerial vehicles (UAVs) using dynamic feature weight selection. Specifically, we define a feature weight pool that contains multiple weights for different features. In each frame, we select a weight combination with high reliability from the weight pool. This approach is a form of dynamic feature weight selection since the feature weight may be different for each frame. Furthermore, EdgeBoxes is combined with the DSST and can adapt well to the scale and aspect ratio of the tracking box. Extensive experiments based on UAV123@10fps, VisDrone2018-test-dev, and UAVDT show that our tracker is superior to other state-of-the-art trackers. It is noteworthy that the proposed dynamic feature weight selection method can be embedded into any tracking model using multiple features.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Bonatti R, Ho C, Wang W, Choudhury S, Scherer S (2019) Towards a robust aerial cinematography platform: Localizing and tracking moving targets in unstructured environments. In: 2019 IEEE/RSJ International conference on intelligent robots and systems (IROS), pp 229–236. https://doi.org/10.1109/IROS40897.2019.8968163https://doi.org/10.1109/IROS40897.2019.8968163

  2. collab=K M., H. C E. (2019) Uav traffic patrolling via road detection and tracking in anonymous aerial video frames. In: Journal of intelligent robotic systems, vol 95, pp 675–690. https://doi.org/10.1007/s10846-018-0954-x

  3. Xue X, Li Y, Shen Q (2018) Unmanned aerial vehicle object tracking by correlation filter with adaptive appearance model. Sensors 18(9). https://doi.org/10.3390/s18092751

  4. Jiang B, Zhang Y, Tang J, Luo B, Li C (2019) Robust visual tracking via laplacian regularized random walk ranking. Neurocomputing 339:139–148. https://doi.org/10.1016/j.neucom.2019.01.102

    Article  Google Scholar 

  5. Chi Y, Zhixiang L, Youmin Z (2017) Aerial images-based forest fire detection for firefighting using optical remote sensing techniques and unmanned aerial vehicles. Journal of Intelligent & Robotic Systems 88:635–654. https://doi.org/10.1007/s10846-016-0464-7

    Article  Google Scholar 

  6. Huang Z, Fu C, Li Y, Lin F, Lu P (2019) Learning aberrance repressed correlation filters for real-time uav tracking. In: 2019 IEEE/CVF International conference on computer vision (ICCV), pp 2891–2900. https://doi.org/10.1109/ICCV.2019.00298

  7. Li Y, Fu C, Ding F, Huang Z, Lu G (2020) Autotrack: Towards high-performance visual tracking for uav with automatic spatio-temporal regularization. In: 2020 IEEE/CVF conference on computer vision and pattern recognition (CVPR), pp 11920–11929. https://doi.org/10.1109/CVPR42600.2020.01194

  8. Wang M, Liu Y, Huang Z (2017) Large margin object tracking with circulant feature maps. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), pp 4800–4808

  9. Yan Y, Guo X, Tang J, Li C, Wang X (2021) Learning spatio-temporal correlation filter for visual tracking. Neurocomputing 436:273–282. https://doi.org/10.1016/j.neucom.2021.01.057

    Article  Google Scholar 

  10. Yun S, Choi J, Yoo Y, Yun K, Choi JY (2017) Action-decision networks for visual tracking with deep reinforcement learning. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), pp 1349–1358. https://doi.org/10.1109/CVPR.2017.148

  11. Cen M, Jung C (2018) Fully convolutional siamese fusion networks for object tracking. In: 2018 25Th IEEE international conference on image processing (ICIP), pp 3718–3722. https://doi.org/10.1109/ICIP.2018.8451102

  12. Voigtlaender P, Luiten J, Torr PHS, Leibe B (2020) Siam R-CNN: visual tracking by re-detection. In: 2020 IEEE/CVF conference on computer vision and pattern recognition, CVPR 2020, Seattle, WA, USA, Computer Vision Foundation IEEE, pp 6577–6587. https://doi.org/10.1109/CVPR42600.2020.00661

  13. Sun X, Han G, Guo L, Yang H, Wu X, Li Q (2022) Two-stage aware attentional siamese network for visual tracking. Pattern Recogn 124:108502. https://doi.org/10.1016/j.patcog.2021.108502https://doi.org/10.1016/j.patcog.2021.108502

    Article  Google Scholar 

  14. Danelljan M, Bhat G, Khan FS, Felsberg M (2017) Eco: Efficient convolution operators for tracking. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), pp 6931–6939. https://doi.org/10.1109/CVPR.2017.733

  15. Zhang J, Feng W, Yuan T, Wang J, Sangaiah AK (2022) Scstcf: Spatial-channel selection and temporal regularized correlation filters for visual tracking. Appl Soft Comput 118:108485. https://doi.org/10.1016/j.asoc.2022.108485

    Article  Google Scholar 

  16. Zhang T, Xu C, Yang M-H (2017) Multi-task correlation particle filter for robust object tracking. In: 2017 IEEE Conference on computer vision and pattern recognition (CVPR), pp 4819–4827. https://doi.org/10.1109/CVPR.2017.512

  17. Moorthy S, Choi JY, Joo YH (2020) Gaussian-response correlation filter for robust visual object tracking. Neurocomputing 411:78–90. https://doi.org/10.1016/j.neucom.2020.06.016

    Article  Google Scholar 

  18. Gang X, Xingchen Z, Ping Y, Xingzhong X, Shengyun P (2020) Anti-occlusion object tracking based on correlation filter. SIViP 14:753–761. https://doi.org/10.1007/s11760-019-01601-6

    Article  Google Scholar 

  19. Junrong Y, Luchao Z, Yingbiao Y, Xin X, Chenjie D (2021) Dual-template adaptive correlation filter for real-time object tracking. Multimed Tools Appl 80:2355–2376. https://doi.org/10.1007/s11042-020-09644-5

    Article  Google Scholar 

  20. Danelljan M, Häger G, Khan FS, Felsberg M (2017) Discriminative scale space tracking. IEEE Trans Pattern Anal Mach Intell 39(8):1561–1575. https://doi.org/10.1109/TPAMI.2016.2609928

    Article  Google Scholar 

  21. Wang C, Zhang L, Xie L, Yuan J (2018) Kernel cross-correlator. In: AAAI Conference on artificial intelligence, vol 32. https://ojs.aaai.org/index.php/AAAI/article/view/11710

  22. Huang D, Luo L, Wen M, Chen Z, Zhang C (2015) Enable scale and aspect ratio adaptability in visual tracking with detection proposals. In: Proceedings of the british machine vision conference (BMVC), BMVA Press, pp 1–12. https://doi.org/10.5244/C.29.185

  23. Ma C, Huang J-B, Yang X, Yang M-H (2019) Robust visual tracking via hierarchical convolutional features. IEEE Trans Pattern Anal Mach Intell 41(11):2709–2723. https://doi.org/10.1109/TPAMI.2018.2865311

    Article  Google Scholar 

  24. Zitnick CL, Dollár P (2014) Edge boxes: Locating object proposals from edges. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer Vision – ECCV 2014, Springer, pp 391–405. https://doi.org/10.1007/978-3-319-10602-1_26

  25. Lina G, Bing L, Ping F, Mingzhu X, Junbao L (2021) Visual tracking via dynamic saliency discriminative correlation filter. Applied Intelligence. https://doi.org/10.1007/s10489-021-02260-2

  26. Elayaperumal D, Joo YH (2021) Aberrance suppressed spatio-temporal correlation filters for visual object tracking. Pattern Recogn 115:107922. https://doi.org/10.1016/j.patcog.2021.107922

    Article  Google Scholar 

  27. Li F, Tian C, Zuo W, Zhang L, Yang M-H (2018) Learning spatial-temporal regularized correlation filters for visual tracking. In: 2018 IEEE/CVF Conference on computer vision and pattern recognition, pp 4904–4913. https://doi.org/10.1109/CVPR.2018.00515https://doi.org/10.1109/CVPR.2018.00515

  28. Galoogahi HK, Fagg A, Lucey S (2017) Learning background-aware correlation filters for visual tracking. In: 2017 IEEE International conference on computer vision (ICCV), pp 1144–1152. https://doi.org/10.1109/ICCV.2017.129

  29. Li B, Yan J, Wu W, Zhu Z, Hu X (2018) High performance visual tracking with siamese region proposal network. In: 2018 IEEE conference on computer vision and pattern recognition, CVPR 2018, Salt Lake City, UT, USA, Computer Vision Foundation / IEEE Computer Society, pp 8971–8980. https://doi.org/10.1109/CVPR.2018.00935

  30. Li B, Wu W, Wang Q, Zhang F, Xing J, Yan J (2019) Siamrpn++: Evolution of siamese visual tracking with very deep networks. In: IEEE conference on computer vision and pattern recognition, CVPR 2019, Long Beach, CA, USA, Computer Vision Foundation / IEEE, pp 4282–4291. https://doi.org/10.1109/CVPR.2019.00441

  31. Yu Y, Xiong Y, Huang W, Scott MR (2020) Deformable siamese attention networks for visual object tracking. In: 2020 IEEE/CVF conference on computer vision and pattern recognition, CVPR 2020, Seattle, WA, USA, Computer Vision Foundation / IEEE, pp 6727–6736. https://doi.org/10.1109/CVPR42600.2020.00676

  32. Guo D, Wang J, Cui Y, Wang Z, Chen S (2020) Siamcar: Siamese fully convolutional classification and regression for visual tracking. In: 2020 IEEE/cvf conference on computer vision and pattern recognition, CVPR 2020, Seattle, WA, USA, Computer Vision Foundation / IEEE, pp 6268–6276. https://doi.org/10.1109/CVPR42600.2020.00630

  33. Guo D, Shao Y, Cui Y, Wang Z, Zhang L, Shen C (2021) Graph attention tracking. In: 2021 IEEE/CVF Conference on computer vision and pattern recognition (CVPR), pp 9538–9547. https://doi.org/10.1109/CVPR46437.2021.00942

  34. Yang K, He Z, Pei W, Zhou Z, Li X, Yuan D, Zhang H (2021) Siamcorners: Siamese corner networks for visual tracking. IEEE Trans Multimed, pp 1–1. https://doi.org/10.1109/TMM.2021.3074239https://doi.org/10.1109/TMM.2021.3074239

  35. Wang Y, Luo X, Ding L, Fu S, Wei X (2019) Robust visual tracking based on response stability. Eng Appl Artif Intell 85:137–149. https://doi.org/10.1016/j.engappai.2019.05.002

    Article  Google Scholar 

  36. Liu Y, Li S, Cheng M-M (2020) Refinedbox: Refining for fewer and high-quality object proposals. Neurocomputing 406:106–116. https://doi.org/10.1016/j.neucom.2020.04.017

    Article  Google Scholar 

  37. Ke W, Chen J, Ye Q (2019) Deep contour and symmetry scored object proposal. Pattern Recogn Lett 119:172–179. https://doi.org/10.1016/j.patrec.2018.01.004

    Article  Google Scholar 

  38. Liang Y, Liu Y, Yan Y, Zhang L, Wang H (2021) Robust visual tracking via spatio-temporal adaptive and channel selective correlation filters. Pattern Recogn 112:107738. https://doi.org/10.1016/j.patcog.2020.107738

    Article  Google Scholar 

  39. Mueller M, Smith N, Ghanem B (2016) A benchmark and simulator for uav tracking. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer Vision – ECCV 2016, Springer, pp 445–461. https://doi.org/10.1007/978-3-319-46448-0_27

  40. Wen L, Zhu P, Du D, Bian X, Ling H, Hu Q, Liu C, Cheng H, Liu X, Ma W (2018) Visdrone-sot2018: The vision meets drone single-object tracking challenge results. In: Computer Vision - ECCV 2018 Workshops - Munich, Germany, Proceedings, Part V, vol 11133, Springer, pp 469–495. https://doi.org/10.1007/978-3-030-11021-5_28

  41. Du D, Qi Y, Yu H, Yang Y, Duan K, Li G, Zhang W, Huang Q, Tian Q (2018) The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking. Springer. https://doi.org/10.1007/978-3-030-01249-6_23

  42. Li Y, Fu C, Ding F, Huang Z, Pan J (2020) Augmented memory for correlation filters in real-time uav tracking. In: 2020 IEEE/RSJ international conference on intelligent robots and systems (IROS), pp. 1559–1566. https://doi.org/10.1109/IROS45743.2020.9341595

  43. Li B, Fu C, Ding F, Ye J, Lin F (2021) Adtrack: Target-aware dual filter learning for real-time anti-dark UAV tracking. In: IEEE International conference on robotics and automation, ICRA 2021, Xi’an, China, IEEE, pp 496–502. https://doi.org/10.1109/ICRA48506.2021.9561564

Download references

Funding

This research was funded by Natural Science Foundation of Shandong Province, grant number ZR2021MF068, ZR2021MF107, ZR2021MF015, ZR2020MA030 and Key R&D Program (Soft Science) Project of Shandong Province, grant number 2020RKB01017 and School-level Teaching Reform Project of Shandong Technology and Business University, grant number 11688202023.

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Shandong Technology and Business University, Yantai, 264005, Shandong, China

    Zhiyong An, Xiumin Wang, Bo Li, Zhongliang Xiang & Bin Zhang

Authors
  1. Zhiyong An
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Xiumin Wang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Bo Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Zhongliang Xiang
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Bin Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Bo Li.

Ethics declarations

Competing interests

The authors declare no conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

An, Z., Wang, X., Li, B. et al. Robust visual tracking for UAVs with dynamic feature weight selection. Appl Intell 53, 3836–3849 (2023). https://doi.org/10.1007/s10489-022-03719-6

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-022-03719-6

Keywords