Skip to main content
SpringerLink
Log in
Book cover

Soft Computing Applications pp 863–873Cite as

Recognition of Pedestrian Active Events by Robust to Noises Boost Algorithm

  • Conference paper
  • First Online:

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 357))

Abstract

The active events recognition is the essential part of surveillance systems. In such systems, the statistical training methods are very popular. In this research, the Robust for Noises Boost (RONBoost) algorithm is proposed. It is based on the classifying cascades and was tested on various scenarios of pedestrian behavior in the outdoor scenes. The satisfactory results were achieved not only by the RONBoost algorithm implementation but also the object capture and tracking based on the spatiotemporal filtering and the motion segmentation using the analysis of tensor structures. The error of motion segmentation was decreased to 4 %. The experiments demonstrate the satisfactory results: the deviation of moving regions is less 10 % and the classification error is around 2–5 %. For video sequences with worse luminance conditions, this error is increased up to 7–10 %.

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

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   219.99
Price excludes VAT (USA)
  • Compact, lightweight 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

Learn about institutional subscriptions

References

  1. Galar M, Fernández A, Barrenechea E, Bustince H, Herrera F (2012) A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid- based approaches. IEEE Trans Syst Man Cybern Part C Appl Rev 42(4):463–484

    Article  Google Scholar 

  2. Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140

    MATH  MathSciNet  Google Scholar 

  3. Freund Y, Schapire RE (1997) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci 55(1):119–139

    Article  MATH  MathSciNet  Google Scholar 

  4. Oza NC (2004) Aveboost2: boosting for noisy data. In: Roli F, Kittler J, Windeatt T (eds) Multiple classifier systems. LNCS 3077, Springer, Berlin, pp 31–40

    Google Scholar 

  5. Karmaker A, Kwek S (2006) A boosting approach to remove class label noise. Int J Hybrid Intell Syst Hybrid Intell Syst Ensembles 3(3):169–177

    MATH  Google Scholar 

  6. Rasolzadeh B, Petersson L, Pettersson N (2006) Response binning: improved weak classifiers for boosting. In: Proceedings of 2006 IEEE intelligent vehicle symposium (IVC 2006). Tokyo, Japan, pp 344–349

    Google Scholar 

  7. Schapire RE, Singer Y (1999) Improved boosting using confidence-rated predictions. Mach Learn 37(3):297–336

    Article  MATH  Google Scholar 

  8. Friedman J, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting. Ann Stat 38(2):337–374

    Article  MathSciNet  Google Scholar 

  9. Sochman J, Matas J (2005) Waldboost—learning for time constrained sequential detection. In: Proceedings of IEEE computer society conference on computer vision and pattern recognition (CVPR 2005), vol 2. San Diego, CA, USA, pp 150–156

    Google Scholar 

  10. Seiffert C, Khoshgoftaar T, Van Hulse J, Napolitano A (2010) RUSBoost: a hybrid approach to alleviating class imbalance. IEEE Trans Syst Man Cybern Part A Syst Humans 40(1):185–197

    Article  Google Scholar 

  11. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16(1):321–357

    MATH  Google Scholar 

  12. Liu XY, Wu J, Zhou ZH (2009) Exploratory undersampling for class-imbalance learning. IEEE Trans Syst Man Cybern B Cybern 39(2):539–550

    Article  Google Scholar 

  13. Galar M, Fernández A, Barrenechea E, Herrera F (2013) EUSBoost: enhancing ensembles for highly imbalanced data-sets by evolutionary undersampling. Pattern Recogn 46(12):3460–3471

    Article  Google Scholar 

  14. Ibarra-Manzano MA, Almanza-Ojeda DL (2012) An FPGA implementation for image interpretation based on adaptive boosting algorithm in the real-time systems. Procedia Technol 3:187–195

    Article  Google Scholar 

  15. Kim TK, Cipolla R (2013) Multiple classifier boosting and tree-structured classifiers. In: Cipolla R, Battiato S, Farinella GM (eds) Machine learning for computer vision. Springer, Berlin, SCI 411, pp 163–196

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Siberian State Aerospace University of Krasnoyarsk, Krasnoyarsk, Russian Federation

    M. Favorskaya

  2. University of Canberra, Canberra, Australia

    Lakhmi C. Jain

  3. University of South Australian, Adelaide, Australia

    Lakhmi C. Jain

  4. Faculty of Science and Technology, Data Science Institute, Bournemouth University, Poole, UK

    Lakhmi C. Jain

Authors
  1. M. Favorskaya
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lakhmi C. Jain
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to M. Favorskaya .

Editor information

Editors and Affiliations

  1. Department of Automation and Applied Informatics, Aurel Vlaicu University of Arad Faculty of Engineering, Arad, Romania

    Valentina Emilia Balas

  2. Faculty of Science and Technology, Data Science Institute, Bournemouth University, Poole, United Kingdom

    Lakhmi C. Jain

  3. University of Belgrade, Belgrade, Serbia

    Branko Kovačević

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing Switzerland

About this paper

Cite this paper

Favorskaya, M., Jain, L.C. (2016). Recognition of Pedestrian Active Events by Robust to Noises Boost Algorithm. In: Balas, V., Jain, L., Kovačević, B. (eds) Soft Computing Applications. Advances in Intelligent Systems and Computing, vol 357. Springer, Cham. https://doi.org/10.1007/978-3-319-18416-6_68

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-18416-6_68

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-18415-9

  • Online ISBN: 978-3-319-18416-6

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation