UAV Visual Tracking with Enhanced Feature Information

Shuduo Zhao; Yunsheng Chen; Shuaidong Yang

doi:doi:10.11648/j.acis.20241202.12

Research Article |

| Peer-Reviewed

UAV Visual Tracking with Enhanced Feature Information

Shuduo Zhao^*

, Yunsheng Chen, Shuaidong Yang

Published in Automation, Control and Intelligent Systems (Volume 12, Issue 2)

Received: 5 July 2024 Accepted: 26 July 2024 Published: 15 August 2024

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Unmanned aerial vehicles (UAVs) visual tracking is an important research direction. The tracking object is lost due to the problems of target occlusion, illumination variation, flight vibration and so on. Therefore, based on a Siamese network, this study proposes a UAVs visual tracker named SiamDFT++ to enhance the correlation of depth features. First, the network width of the three-layer convolution after the full convolution neural network is doubled, and the appearance information of the target is fully utilized to complete the feature extraction of the template frame and the detection frame. Then, the attention information fusion module and feature deep convolution module are proposed in the template branch and the detection branch, respectively. The feature correlation calculation methods of the two depths can effectively suppress the background information, enhance the correlation between pixel pairs, and efficiently complete the tasks of classification and regression. Furthermore, this study makes full use of shallow features to enhance the extraction of object features. Finally, this study uses the methods of deep cross-correlation operation and complete intersection over union to complete the matching and location tasks. The experimental results show that the tracker has strong robustness in UAVs short-term tracking scenes and long-term tracking scenes.

Published in	Automation, Control and Intelligent Systems (Volume 12, Issue 2)
DOI	10.11648/j.acis.20241202.12
Page(s)	35-47
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

Visual Tracking, Unmanned Aerial Vehicles, Convolutional Feature, Real-time Remote Sensing

References

[1]	Yang. S, Xu. J, Chen. H, et al, High-performance UAVs visual tracking using deep convolutional feature, Neural Computing and Applications, 2022, pp. 13539-13558. https://doi.org/10.1007/s00521-022-07181-w
[2]	Henriques. J. F, Caseiro. R, Martins. P, et al, High-speed tracking with kernelized correlation filters, IEEE Trans. Pattern. Anal. vol. 37, no.3, pp. 583-596, Mar. 2015. https://doi.org/10.1109/TPAMI.2014.2345390
[3]	Bertinetto. L, Valmadre. J, Golodetz. S, et al, Staple: Complementary learners for real-time tracking, presented at the Proceedings of the IEEE conference on computer vision and pattern recognition, Jun.2021, pp. 1401-1409. https://doi.org/10.48550/arXiv.1512.01355
[4]	Bertinetto. L, Valmadre. J, Henriques. J. F, et al, Fully-convolutional siamese networks for object tracking, European conference on computer vision, Nov. 2016, pp. 850-865. https://doi.org/10.48550/arXiv.1606.09549
[5]	Danelljan. M, Hager. G, Khan. F, et al, Accurate scale estimation for robust visual tracking, presented at British Machine Vision Conference, Sep. 2014, pp. 1-5. https://doi.org/10.5244/c.28.65
[6]	Kiani. Galoogahi. H, Fagg. A, Lucey. S, Learning background aware correlation filters for visual tracking, presented at Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Oct.2017, pp. 1135-1143. https://doi.org/10.1109/ICCV.2017.129
[7]	Li. F, Tian. C, Zuo. W, et al, Learning spatial-temporal regularized correlation filters for visual tracking, presented at Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jun.2018, pp. 4904-4913. https://doi.org/10.1109/CVPR.2018.00515
[8]	Li. B, Yan. J, Wu. W, et al, High performance visual tracking with siamese region proposal network, presented at Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2018, pp. 8971-8980. https://doi.org/10.1109/CVPR.2018.00935
[9]	Wang. N, Song. Y, Ma. C, et al, Unsupervised Deep Representation Learning for Real-Time Tracking, International Journal of Computer Vision, Jun. 2021, pp. 400-418. https://doi.org/10.1007/s11263-020-01357-4
[10]	Li. X, Ma. C, Wu. B, et al, Target-Aware Deep Tracking, presented at Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2019, pp. 1369-1378. https://doi.org/10.48550/arXiv.1904.01772
[11]	Li. B, Wu. W, Wang. Q, et al, Siamrpn++: Evolution of siamese visual tracking with very deep networks, presented at Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jun.2019, pp. 4282-4291. https://doi.org/10.48550/arXiv.1812.11703
[12]	Hou. Q, Zhang. L, Cheng. M. M, et al, Strip pooling: Rethinking spatial pooling for scene parsing, presented at Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2020, pp. 4003–4012. https://doi.org/10.48550/arXiv.2003.13328
[13]	Wang. Q, Wu. B, Zhu. P, et al, ECA-Net: Efficient channel attention for deep convolutional neural networks, presented at 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2020. https://doi.org/10.48550/arXiv.1910.03151
[14]	Li. Y, Zhu. J, A scale adaptive kernel correlation filter tracker with feature integration, presented at European conference on computer vision, Mar. 2015, pp. 254-265. https://doi.org/10.1007/978-3-319-16181-5_18
[15]	Danelljan. M, Robinson. A, Khan. F. S, et al, Beyond correlation filters: Learning continuous convolution operators for visual tracking, presented at European conference on computer vision, Sep. 2016, pp.472-488. https://doi.org/10.1007/978-3-319-46454-1_29
[16]	Danelljan. M, Bhat. G, Shahbaz. KhanF, et al, Eco: Efficient convolution operators for tracking, presented at Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jul. 2017, pp. 6638-6646. https://doi.org/10.48550/arXiv.1611.09224
[17]	Cao. Z, Fu. C, Ye. J, et al, HiFT: Hierarchical Feature Transformer for Aerial Tracking, presented at Proceedings of the IEEE/CVF International Conference on Computer Vision, Oct. 2021, pp. 15457-15466. https://doi.org/10.1109/ICCV48922.2021.01517
[18]	Chen. S, Xie. E, Ge. C, et al, CycleMLP: A MLP-like Architecture for Dense Visual Predictions, IEEE Transactions on Pattern Analysis and Machine Intelligence, Nov. 2023, pp. 1-17. https://doi.org/10.1109/TPAMI.2023.3303397
[19]	Zheng. Z, Wang. P, Liu. W, et al, Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression, presented at Proceedings of the AAAI Conference on Artificial Intelligence, Feb. 2020, pp. 12993-13000. https://doi.org/10.48550/arXiv.1911.08287
[20]	Li. Y, Fu. C, Ding. F, et al, Auto Track: Towards high-performance visual tracking for UAV with automatic spatio-temporal regularization, presented at Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Jun. 2020, pp. 11923-11932. https://doi.org/10.48550/arXiv.2003.12949
[21]	Wang. N, Zhou. W, Tian. Q, et al, Multi-cue correlation filters for robust visual tracking, presented at Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2018, pp. 4844-4853. https://doi.org/10.1109/CVPR.2018.00509
[22]	Zhang. T, Xu. C, Yang. M. H, Multi-task correlation particle filter for robust object tracking, presented at Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Jul. 2017, pp. 4335-4343. https://doi.org/10.1109/CVPR.2017.512
[23]	Danelljan. M, Hager. G, Shahbaz. Khan. F, et al, Learning spatially regularized correlation filters for visual tracking, presented at Proceedings of the IEEE International Conference on Computer Vision, Dec.2015, pp. 4310-4318. https://doi.org/10.48550/arXiv.1608.05571
[24]	Yang. K, He. Z, Pei. W, et al, Siam Corners: Siamese corner networks for visual tracking, IEEE Transactions on Multimedia, vol. 24, pp.1956-1967, Apr. 2021. https://doi.org/10.1109/TMM.2021.3074239
[25]	Xu. Y, Wang. Z, Li. Z, et al, Siamfc++: Towards robust and accurate visual tracking with target estimation guidelines, presented at Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no.07, pp. 12549-12556, Apr. 2020. https://doi.org/10.48550/arXiv.1911.06188
[26]	Mueller. M, Smith. N, Ghanem. B, A benchmark and simulator for uav tracking, presented at European conference on computer vision, Sep. 2016, pp. 445-461. https://doi.org/10.1007/978-3-319-46448-0_27
[27]	Li. S, Yeung. DY, Visual object tracking for unmanned aerial vehicles: a benchmark and new motion models, presented at Proceedings of the AAAI conference on artificial intelligence, Feb. 2017, pp. 4140-4146.
[28]	Huang. Z, Fu. C, Li. Y, et al, Learning aberrance repressed correlation filters for real-time UAV tracking, presented at Proceedings of the IEEE/CVF International Conference on Computer Vision, Oct. 2019, pp. 2891-2900. https://doi.org/10.48550/arXiv.1908.02231
[29]	Yang. S, Chen. H, Xu. F, et al, High-performance UAVs visual tracking based on siamese network, The Visual Computer, 2021. https://doi.org/10.1007/s00371-021-02271-7

Cite This Article

Plain Text BibTeX RIS

APA Style

Zhao, S., Chen, Y., Yang, S. (2024). UAV Visual Tracking with Enhanced Feature Information. Automation, Control and Intelligent Systems, 12(2), 35-47. https://doi.org/10.11648/j.acis.20241202.12

Copy | Download

ACS Style

Zhao, S.; Chen, Y.; Yang, S. UAV Visual Tracking with Enhanced Feature Information. Autom. Control Intell. Syst. 2024, 12(2), 35-47. doi: 10.11648/j.acis.20241202.12

Copy | Download

AMA Style

Zhao S, Chen Y, Yang S. UAV Visual Tracking with Enhanced Feature Information. Autom Control Intell Syst. 2024;12(2):35-47. doi: 10.11648/j.acis.20241202.12

Copy | Download

@article{10.11648/j.acis.20241202.12,
  author = {Shuduo Zhao and Yunsheng Chen and Shuaidong Yang},
  title = {UAV Visual Tracking with Enhanced Feature Information
},
  journal = {Automation, Control and Intelligent Systems},
  volume = {12},
  number = {2},
  pages = {35-47},
  doi = {10.11648/j.acis.20241202.12},
  url = {https://doi.org/10.11648/j.acis.20241202.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.acis.20241202.12},
  abstract = {Unmanned aerial vehicles (UAVs) visual tracking is an important research direction. The tracking object is lost due to the problems of target occlusion, illumination variation, flight vibration and so on. Therefore, based on a Siamese network, this study proposes a UAVs visual tracker named SiamDFT++ to enhance the correlation of depth features. First, the network width of the three-layer convolution after the full convolution neural network is doubled, and the appearance information of the target is fully utilized to complete the feature extraction of the template frame and the detection frame. Then, the attention information fusion module and feature deep convolution module are proposed in the template branch and the detection branch, respectively. The feature correlation calculation methods of the two depths can effectively suppress the background information, enhance the correlation between pixel pairs, and efficiently complete the tasks of classification and regression. Furthermore, this study makes full use of shallow features to enhance the extraction of object features. Finally, this study uses the methods of deep cross-correlation operation and complete intersection over union to complete the matching and location tasks. The experimental results show that the tracker has strong robustness in UAVs short-term tracking scenes and long-term tracking scenes.
},
 year = {2024}
}

Copy | Download

TY  - JOUR
T1  - UAV Visual Tracking with Enhanced Feature Information

AU  - Shuduo Zhao
AU  - Yunsheng Chen
AU  - Shuaidong Yang
Y1  - 2024/08/15
PY  - 2024
N1  - https://doi.org/10.11648/j.acis.20241202.12
DO  - 10.11648/j.acis.20241202.12
T2  - Automation, Control and Intelligent Systems
JF  - Automation, Control and Intelligent Systems
JO  - Automation, Control and Intelligent Systems
SP  - 35
EP  - 47
PB  - Science Publishing Group
SN  - 2328-5591
UR  - https://doi.org/10.11648/j.acis.20241202.12
AB  - Unmanned aerial vehicles (UAVs) visual tracking is an important research direction. The tracking object is lost due to the problems of target occlusion, illumination variation, flight vibration and so on. Therefore, based on a Siamese network, this study proposes a UAVs visual tracker named SiamDFT++ to enhance the correlation of depth features. First, the network width of the three-layer convolution after the full convolution neural network is doubled, and the appearance information of the target is fully utilized to complete the feature extraction of the template frame and the detection frame. Then, the attention information fusion module and feature deep convolution module are proposed in the template branch and the detection branch, respectively. The feature correlation calculation methods of the two depths can effectively suppress the background information, enhance the correlation between pixel pairs, and efficiently complete the tasks of classification and regression. Furthermore, this study makes full use of shallow features to enhance the extraction of object features. Finally, this study uses the methods of deep cross-correlation operation and complete intersection over union to complete the matching and location tasks. The experimental results show that the tracker has strong robustness in UAVs short-term tracking scenes and long-term tracking scenes.

VL  - 12
IS  - 2
ER  -

Copy | Download

Author Information

Shuduo Zhao

School of Electric and Information, Southwest Petroleum University, Chengdu, China

Contact Email

http://orcid.org/0009-0004-7345-5863
Yunsheng Chen

School of Automation, Chongqing University, Chongqing, China

Contact Email
Shuaidong Yang

School of Electric and Information, Southwest Petroleum University, Chengdu, China

Contact Email

http://orcid.org/0000-0002-8133-4525

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Zhao, S., Chen, Y., Yang, S. (2024). UAV Visual Tracking with Enhanced Feature Information. Automation, Control and Intelligent Systems, 12(2), 35-47. https://doi.org/10.11648/j.acis.20241202.12

Copy | Download

ACS Style

Zhao, S.; Chen, Y.; Yang, S. UAV Visual Tracking with Enhanced Feature Information. Autom. Control Intell. Syst. 2024, 12(2), 35-47. doi: 10.11648/j.acis.20241202.12

Copy | Download

AMA Style

Zhao S, Chen Y, Yang S. UAV Visual Tracking with Enhanced Feature Information. Autom Control Intell Syst. 2024;12(2):35-47. doi: 10.11648/j.acis.20241202.12

Copy | Download

@article{10.11648/j.acis.20241202.12,
  author = {Shuduo Zhao and Yunsheng Chen and Shuaidong Yang},
  title = {UAV Visual Tracking with Enhanced Feature Information
},
  journal = {Automation, Control and Intelligent Systems},
  volume = {12},
  number = {2},
  pages = {35-47},
  doi = {10.11648/j.acis.20241202.12},
  url = {https://doi.org/10.11648/j.acis.20241202.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.acis.20241202.12},
  abstract = {Unmanned aerial vehicles (UAVs) visual tracking is an important research direction. The tracking object is lost due to the problems of target occlusion, illumination variation, flight vibration and so on. Therefore, based on a Siamese network, this study proposes a UAVs visual tracker named SiamDFT++ to enhance the correlation of depth features. First, the network width of the three-layer convolution after the full convolution neural network is doubled, and the appearance information of the target is fully utilized to complete the feature extraction of the template frame and the detection frame. Then, the attention information fusion module and feature deep convolution module are proposed in the template branch and the detection branch, respectively. The feature correlation calculation methods of the two depths can effectively suppress the background information, enhance the correlation between pixel pairs, and efficiently complete the tasks of classification and regression. Furthermore, this study makes full use of shallow features to enhance the extraction of object features. Finally, this study uses the methods of deep cross-correlation operation and complete intersection over union to complete the matching and location tasks. The experimental results show that the tracker has strong robustness in UAVs short-term tracking scenes and long-term tracking scenes.
},
 year = {2024}
}

Copy | Download

TY  - JOUR
T1  - UAV Visual Tracking with Enhanced Feature Information

AU  - Shuduo Zhao
AU  - Yunsheng Chen
AU  - Shuaidong Yang
Y1  - 2024/08/15
PY  - 2024
N1  - https://doi.org/10.11648/j.acis.20241202.12
DO  - 10.11648/j.acis.20241202.12
T2  - Automation, Control and Intelligent Systems
JF  - Automation, Control and Intelligent Systems
JO  - Automation, Control and Intelligent Systems
SP  - 35
EP  - 47
PB  - Science Publishing Group
SN  - 2328-5591
UR  - https://doi.org/10.11648/j.acis.20241202.12
AB  - Unmanned aerial vehicles (UAVs) visual tracking is an important research direction. The tracking object is lost due to the problems of target occlusion, illumination variation, flight vibration and so on. Therefore, based on a Siamese network, this study proposes a UAVs visual tracker named SiamDFT++ to enhance the correlation of depth features. First, the network width of the three-layer convolution after the full convolution neural network is doubled, and the appearance information of the target is fully utilized to complete the feature extraction of the template frame and the detection frame. Then, the attention information fusion module and feature deep convolution module are proposed in the template branch and the detection branch, respectively. The feature correlation calculation methods of the two depths can effectively suppress the background information, enhance the correlation between pixel pairs, and efficiently complete the tasks of classification and regression. Furthermore, this study makes full use of shallow features to enhance the extraction of object features. Finally, this study uses the methods of deep cross-correlation operation and complete intersection over union to complete the matching and location tasks. The experimental results show that the tracker has strong robustness in UAVs short-term tracking scenes and long-term tracking scenes.

VL  - 12
IS  - 2
ER  -

Copy | Download