Skip to main content
Springer Nature Link
Log in

An online learned hough forest model based on improved multi-feature fusion matching for multi-object tracking

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Object tracking has been one of the most important and active research areas in the field of computer vision. In order to solve low accuracy in object occlusion and deformation for multi-object tracking, an online learned Hough forest model based on improved multi-feature fusion matching for multi-object tracking is proposed in this paper. Firstly, positive and negative samples are selected online according to low-level association among detection responses and construct the feature model of the object with color histogram, histogram of oriented gradient (HOG) and optical flow information. Secondly, longer trajectory associations are generated based on the online learned Hough forest framework. Finally, a trajectory matching algorithm based on multi-feature fusion is proposed, and we introduce two methods of similarity measure in color histogram and feature points matching based on the Gabor filter to generate the probability matrix with the weighted factor. Therefore, it can further form the complete trajectories of the objects by associating them gradually. We evaluate our approach on three public data sets, and show significant improvements compared with state-of-art methods.

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
$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

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

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

Similar content being viewed by others

References

  1. Djuric PM, Vemula M, Bugallo MF (2008) Object tracking by particle filtering in binary sensor networks. IEEE Trans Sign Process 56(6):2229–2238

    Article  Google Scholar 

  2. Ghiyong P, Faliang C, Hongbin L et al (2015) Person re-identification algorithm based on HSV model and key-points matching. J Optoelectron Laser 26(8):1575–1582

    Google Scholar 

  3. Grabner H, Leistner C, Bischof H (2008) Semi-supervised on-line boosting for robust tracking. Comput Vision - ECCV 2008 Eur Conf Comput Vision Marseille, France. Proc: 234–247

  4. Heili A, Odobez JM (2014) Exploiting long-term connectivity and visual motion in CRF-based multi-person tracking. IEEE Trans Image Process 23(7):3010–3056

    Article  MathSciNet  Google Scholar 

  5. Huang Q, Yang J (2014) A multistage object tracker in image sequences. Infrared Phys Technol 65:122–128

    Article  Google Scholar 

  6. Huang C, Li Y, Nfva TR (2013) Multiple object tracking by learning-based hierarchical Association of Detection Responses. IEEE Trans Pattern Anal Mach Intell 35(4):898–910

    Article  Google Scholar 

  7. Kalal Z, Mikolajczyk K, Matas J (2010) Forward-backward error; automatic detection of tracking failures. Proc Int Conf Pattern Recogn Piscataway IEEE :2756–2759

  8. Kuo C-H, Nevatia R (2011) How docs person identity recognition help multi-person tracking?. Proc 2011 IEEE Conf Comput Vision Pattern Recogn. Piscataway IEEE : 1217–122

  9. Kyriakides I (2016) Object tracking using adaptive compressive sensing and processing. Signal Process 127:44–55

    Article  Google Scholar 

  10. Mei X, Ling H (2009) Robust visual tracking using &# x2113; 1 minimization. 2009 IEEE 12th Int Conf Comput Vision IEEE : 1436–1443

  11. Mei X, Ling H (2011) Robust visual tracking and vehicle classification via sparse representation. IEEE Trans Pattern Anal Mach Intell 33(11):2259–2272

    Article  Google Scholar 

  12. Qi H, Jun X, Jianhua H et al (2015) Multi-object tracking algorithm based on feature fusion and discriminative appearance model. J Imag Graph 20(9):1188–1198

    Google Scholar 

  13. Ristani E, Solera F, Zou R et al. (2016) Performance measures and a data set for multi-object, multi-camera tracking. Lecture Notes in Computer Science; 991. Heidelberg; Springer Verlag :17–35

  14. Wang X, Hua G, Han TX (2010) Discriminative tracking by metric learning. Comput Vision - ECCV 2010 Eur Conf Comput Vision Greece. Proc: 200–214

  15. Wu Y, Lim J, Yang M-H (2015) Object tracking benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence 37(9):1834–1848

    Article  Google Scholar 

  16. Xiang J, Sang N, Hou J (2015) An online learned hough forest model for multi-object tracking. Proc 2015 IEEE Int Conf Image Process Piscataway IEEE : 2398–2102

  17. Xianu J, Sang N, Hou J et al (2016) Hough Forest based association framework with occlusion handling for multi-object tracking. IEEE Sign Process Lett 23(2):257–261

    Article  Google Scholar 

  18. Xiude B, Hongbin L et al (2017) Multi-object tracking method based on adaptive fragment and multi-feature fusion. J Xidian Univ 44(2):163–168

    Google Scholar 

  19. Yang B, Nevatia R. Online learned discriminative part-based appearance models for multi-human tracking. Lect Notes Comput Sci; 7572. Heidelberg; Springer Verlag, 2012: 484–498

  20. Yang B, Nevatia R (2014) Multi-object tracking by online learning a CRF model of appearance and motion patterns. Int J Comput Vision 107(2):203–217

    Article  MathSciNet  Google Scholar 

  21. Zhan R, Wan J (2007) Iterated unscented kalman filter for passive object tracking. IEEE Trans Aerosp Electron Syst 43(3):1155–1163

    Article  Google Scholar 

Download references

Acknowledgements

This work was financially supported by key discipline for computer application and technology of Hunan University of Science and Engineering.

Project Number:

1. Project supported by the Science Foundation of Education Department of Hunan Province, China (Grant No. 16C0685).

Author information

Authors and Affiliations

  1. Experiment & Practice Training Center, Hunan University of Science and Engineering, Yongzhou, 425199, Hunan, China

    Wan Li & Cheng Wenzhi

Authors
  1. Wan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Cheng Wenzhi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wan Li.

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

Li, W., Wenzhi, C. An online learned hough forest model based on improved multi-feature fusion matching for multi-object tracking. Multimed Tools Appl 78, 8861–8874 (2019). https://doi.org/10.1007/s11042-018-6519-y

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-018-6519-y

Keywords

Search

Navigation