Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

A Survey on GPU-Based Visual Trackers

  • Chapter
  • First Online:
Recent Advances in Computer Vision Applications Using Parallel Processing

Part of the book series: Studies in Computational Intelligence ((SCI,volume 1073))

  • 357 Accesses

  • 2 Citations

Abstract

The object tracking problem is a key one in computer vision, and it is critical in a variety of applications such as guided missiles, unmanned aerial vehicles, and video surveillance. Despite several types of research on visual tracking, there are still a number of challenges during the tracking process, including computationally intensive tasks that make real-time object tracking impossible. By offloading computation to the graphics processing unit, we may overcome the processing limitations of visual tracking algorithms (GPU). In this work, object tracking algorithms that use GPU parallel computing are summarized. Firstly, the related works are briefly discussed. Secondly, object trackers are classified, summarized, and analyzed from two aspects: Single Object Tracking(SOT) and Multiple Object Tracking (MOT). Finally, we’ll go through parallel computing—what it is and how it’s used, as well as a strategy for designing a parallel algorithm, various types of methods for analyzing parallel algorithm performance for parallel computers, and how to reformulate computational issues in the language of graphics cards.

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

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 139.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 179.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 179.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. O. Appiah, M. Asante, J.B. Hayfron-Acquah, Improved approximated median filter algorithm for real-time computer vision applications. J. King Saud Univ. - Comput. Inf. Sci. (2020)

    Google Scholar 

  2. S. Arabi, A. Haghighat, A. Sharma, A deep-learning-based computer vision solution for construction vehicle detection. Comput.-Aided Civil Infrastruct. Eng. 35(7), 753–767 (2020)

    Article  Google Scholar 

  3. L. Barba-Guaman, J.E. Naranjo, A. Ortiz, Deep learning framework for vehicle and pedestrian detection in rural roads on an embedded GPU. Electronics 9(4), 589 (2020)

    Google Scholar 

  4. S. Bhattacharjee, D.M. Chakkaravarhty, M. Chakkaravarty, L.B.A. Rahim, A.W. Ramadhani, A GPU unified platform to secure big data transportation using an error-prone elliptic curve cryptography, in Data Management, Analytics and Innovation (Springer Singapore, 2020), pp. 263–280

    Google Scholar 

  5. A. Blug, D.J. Regina, S. Eckmann, M. Senn, A. Bertz, D. Carl, C. Eberl, Real-time GPU-based digital image correlation sensor for marker-free strain-controlled fatigue testing. Appl. Sci. 9(10), 2025 (2019)

    Article  Google Scholar 

  6. M. Cao, W. Jia, S. Li, Y. Li, L. Zheng, X. Liu, GPU-accelerated feature tracking for 3d reconstruction. Opt. & Laser Technol. 110, 165–175 (2019)

    Article  Google Scholar 

  7. B.X. Chen, J. Tsotsos, Fast visual object tracking using ellipse fitting for rotated bounding boxes, in 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) (IEEE, 2019)

    Google Scholar 

  8. X. Chen, B. Yan, J. Zhu X. Yang, H. Lu, Transformer Tracking (Dong Wang, 2021)

    Google Scholar 

  9. K. Choi, D. Joo, J. Kim, Kapre: on-gpu audio preprocessing layers for a quick implementation of deep neural network models with keras (2017)

    Google Scholar 

  10. P. Chu, H. Ling, Famnet: joint learning of feature, affinity and multi-dimensional assignment for online multiple object tracking (2019)

    Google Scholar 

  11. P. Dai, R. Weng, W. Choi, C. Zhang, Z. He, W. Ding, Learning a proposal classifier for multiple object tracking (2021)

    Google Scholar 

  12. A. Forero, F. Calderon, Vehicle and pedestrian video-tracking with classification based on deep convolutional neural network, in XXII Symposium on Image (Signal Processing and Artificial Vision (STSIVA) (IEEE, 2019), p. 2019

    Google Scholar 

  13. I. Foster, Designing and Building Parallel Programs: Concepts and Tools for Parallel Software Engineering (Addison-Wesley, Reading, Mass, 1995)

    Google Scholar 

  14. R. Greenlaw, Limits to Parallel Computation: P-Completeness Theory (Oxford University Press, New York, 1995)

    Google Scholar 

  15. S. Jiang, B. Xu, J. Zhao, F. Shen, Faster and simpler siamese network for single object tracking (2021)

    Google Scholar 

  16. P. Kang, S. Lim, A taste of scientific computing on the GPU-accelerated edge device. IEEE Access 8, 208337–208347 (2020)

    Article  Google Scholar 

  17. D. Kim, H. Kim, J. Shin, Y. Mok, J. Paik, Real-time multiple pedestrian tracking based on object identification, in 2019 IEEE 9th International Conference on Consumer Electronics (ICCE-Berlin) (IEEE, 2019)

    Google Scholar 

  18. D.E. Knuth, Computer programming as an art. Commun. ACM 17(12), 667–673 (1974)

    Article  MATH  Google Scholar 

  19. S. Kulik, A. Shtanko, Using convolutional neural networks for recognition of objects varied in appearance in computer vision for intellectual robots. Proc. Comput. Sci. 169, 164–167 (2020)

    Article  Google Scholar 

  20. D.-H. Lee, One-shot scale and angle estimation for fast visual object tracking. IEEE Access 7, 55477–55484 (2019)

    Article  Google Scholar 

  21. D-H. Lee. CNN-based single object detection and tracking in videos and its application to drone detection. Multimedia Tools and Applications (2020)

    Google Scholar 

  22. F. Leighton, Introduction to Parallel Algorithms and Architectures: Arrays, Trees, Hypercubes (M. Kaufmann Publishers, San Mateo, Calif, 1992)

    Google Scholar 

  23. J. Liang, A. Handa, K. Van Wyk, V. Makoviychuk, O. Kroemer, D. Fox, In-hand object pose tracking via contact feedback and GPU-accelerated robotic simulation (2020)

    Google Scholar 

  24. F. Luo, S. Wang, S. Wang, X. Zhang, S. Ma, W. Gao, GPU-based hierarchical motion estimation for high efficiency video coding. IEEE Trans. Multimed. 21(4), 851–862 (2019)

    Article  Google Scholar 

  25. Y. Mao, Z. He, Z. Ma, X. Tang, Z. Wang, Efficient convolution neural networks for object tracking using separable convolution and filter pruning. IEEE Access 7, 106466–106474 (2019)

    Article  Google Scholar 

  26. R. Santiago T. De Menezes, J.V. Alves Luiz, A.M. Henrique-Alves, R.M. Santa Cruz, H. Maia, Mice tracking using the YOLO algorithm, in Anais do Seminário Integrado de Software e Hardware (SEMISH 2020). Sociedade Brasileira de Computação - SBC (2020)

    Google Scholar 

  27. I. Mutis, A. Ambekar, V. Joshi, Real-time space occupancy sensing and human motion analysis using deep learning for indoor air quality control. Autom. Construct. 116, 103237 (2020)

    Google Scholar 

  28. K. Nalaie, R. Zheng, Deepscale: an online frame size adaptation framework to accelerate visual multi-object tracking (2021)

    Google Scholar 

  29. Stan Openshaw, High Performance Computing and the Art of Parallel Programming: An Introduction for Geographers, Social scientists, and Engineers (Routledge, London New York, 2000)

    Google Scholar 

  30. H.A. Peelle, To teach newton’s square root algorithm. ACM SIGAPL APL Quote Quad 5(4), 48–50 (1974)

    Article  Google Scholar 

  31. O.E. Perez-Cham, C. Puente, C. Soubervielle-Montalvo, G. Olague, C.A. Aguirre-Salado, A.S. Nuñez-Varela, Parallelization of the honeybee search algorithm for object tracking. Appl. Sci. 10(6), 2122 (2020)

    Article  Google Scholar 

  32. J. Shin, H. Kim, D. Kim, J. Paik, Fast and robust object tracking using tracking failure detection in kernelized correlation filter. Appl. Sci. 10(2), 713 (2020)

    Article  Google Scholar 

  33. S. Sun, N. Akhtar, H. Song, A. Mian, M. Shah, Deep affinity network for multiple object tracking (2018)

    Google Scholar 

  34. S. Sun, N. Akhtar, X. Song, H. Song, A. Mian, M. Shah, Simultaneous detection and tracking with motion modelling for multiple object tracking, in Computer Vision – ECCV 2020 (Springer International Publishing, 2020), pp. 626–643

    Google Scholar 

  35. S. Sun, Y. Yin, X. Wang, X. De, Robust visual detection and tracking strategies for autonomous aerial refueling of UAVs. IEEE Trans. Instrum. Meas. 68(12), 4640–4652 (2019)

    Article  Google Scholar 

  36. U. Taygan, A. Ozsoy, Performance analysis and GPU parallelisation of ECO object tracking algorithm. New Trends Issues Proc. Adv. Pure Appl. Sci. 12, 109–118 (2020)

    Google Scholar 

  37. O. Urbann, O. Bredtmann, M. Otten, J-P. Richter, T. Bauer, D. Zibriczky, Online and real-time tracking in a surveillance scenario (2021)

    Google Scholar 

  38. Y. Xu, M. Li, L.Cui, S. Huang, F. Wei, M. Zhou, LayoutLM: pre-training of text and layout for document image understanding, in Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (ACM, 2020)

    Google Scholar 

  39. J. Yin, W. Wang, Q. Meng, R. Yang, J. Shen, A unified object motion and affinity model for online multi-object tracking (2020)

    Google Scholar 

  40. Y-C. Yoon, D.Y. Kim, Y.M. Song, K. Yoon, M. Jeon, Online multiple pedestrians tracking using deep temporal appearance matching association (2019)

    Google Scholar 

  41. Yu. Hongyang, G. Li, S. Li, B. Zhong, H. Yao, Q. Huang, Conditional GAN based individual and global motion fusion for multiple object tracking in UAV videos. Pattern Recognit. Lett. 131, 219–226 (2020)

    Article  Google Scholar 

  42. A. Yusuf, S. Alawneh, GPU Implementation for Automatic Lane Tracking in Self-Driving Cars. In SAE Technical Paper Series (SAE International, 2019)

    Google Scholar 

  43. J. Zhang, S. Zhou, J. Wang, D. Huang, Frame-wise motion and appearance for real-time multiple object tracking (2019)

    Google Scholar 

  44. Q. Zhang, C. Bai, Z. Liu, L.T. Yang, Yu. Hang, J. Zhao, H. Yuan, A GPU-based residual network for medical image classification in smart medicine. Inf. Sci. 536, 91–100 (2020)

    Article  Google Scholar 

  45. Y. Zhang, Y. Tang, B. Fang, Z. Shang, Multi-object tracking using deformable convolution networks with tracklets updating. Int. J. Wavelets Multiresolut. Inf. Process. 17(06), 1950042 (2019)

    Article  MATH  Google Scholar 

  46. P. Zhu, L. Wen, D. Dawei, X. Bian, H. Qinghua, H. Ling, Past, present and future, Vision meets drones (2020)

    Google Scholar 

  47. Y. Zou, W. Zhang, W. Weng, Z. Meng, Multi-vehicle tracking via real-time detection probes and a Markov decision process policy. Sensors 19(6), 1309 (2019)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Faculty of Computers and Informatics, Zagazig University, Zagazig, Egypt

    Islam Mohamed, Ibrahim Elhenawy & Ahmad Salah

  2. Technical Research and Development Center, Cairo, Egypt

    Islam Mohamed

  3. Department of Information Technology, CAS-Ibri, The University of Technology and Applied Sciences, Muscat, Oman

    Ahmad Salah

Authors
  1. Islam Mohamed
    View author publications

    Search author on:PubMed Google Scholar

  2. Ibrahim Elhenawy
    View author publications

    Search author on:PubMed Google Scholar

  3. Ahmad Salah
    View author publications

    Search author on:PubMed Google Scholar

Corresponding author

Correspondence to Ahmad Salah .

Editor information

Editors and Affiliations

  1. Department of Information Technology, Zagazig University, Sharkia, Egypt

    Khalid M. Hosny

  2. College of Computing and Information Sciences, University of Technology and Applied Sciences, Ibri, Oman

    Ahmad Salah

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Mohamed, I., Elhenawy, I., Salah, A. (2023). A Survey on GPU-Based Visual Trackers. In: Hosny, K.M., Salah, A. (eds) Recent Advances in Computer Vision Applications Using Parallel Processing . Studies in Computational Intelligence, vol 1073. Springer, Cham. https://doi.org/10.1007/978-3-031-18735-3_4

Download citation

Publish with us

Policies and ethics