Multiple Action Detection in Videos

  • M. N. Renuka Devi
  • Gowri Srinivasa
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 103)


In this work, we present the efficient detection of multiple actions occurring simultaneously in streaming video of various real-world applications using a frame differencing-based method for background detection. We compare our method with other modeling methods (such as multi-channel nonlinear SVM) for multiple action detection on various video datasets. We demonstrate through quantitative performance evaluation metrics such as performance accuracy, standard deviation and detection F-score, and the efficacy of the proposed method over those reported in the literature.


Background subtraction Feature detection Frame differencing method Nonlinear SVM 


  1. 1.
    Escorcia V, Dao CD, Jain M, Ghanem B, Snoek C (2018) Guess where? Actor-supervision for spatiotemporal action localization. arXiv preprint arXiv:1804.01824
  2. 2.
    Zhang M et al (2018) Recurrent attention network using spatial-temporal relations for action recognition. Signal Process 145:137–145CrossRefGoogle Scholar
  3. 3.
    CAVIAR: “Context aware vision using image-based active recognition” funded by the EC’s Information Society Technology’s programmed project IST 2001 37540Google Scholar
  4. 4.
    Weinland D, Ronfard R, Boyer E (2011) A survey of vision-based methods for action representation, segmentation, and recognition. Comput Vis Image Underst 115(2):224–241CrossRefGoogle Scholar
  5. 5.
    Pecka P et al (2018) Solving large markov models described with standard programming language. In: International symposium on computer and information sciences. Springer, ChamGoogle Scholar
  6. 6.
    Xiao C, Yu M (2018) Model-based quantitative distributed fault diagnosis using system decomposition. In: 2018 prognostics and system health management conference (PHM-Chongqing). IEEEGoogle Scholar
  7. 7.
    Asghari P, Soelimani E, Nazerfard E (2019) Online human activity recognition employing hierarchical hidden Markov models. arXiv preprint arXiv:1903.04820CrossRefGoogle Scholar
  8. 8.
    Tu NA et al (2019) ML-HDP: a hierarchical bayesian nonparametric model for recognizing human actions in video. IEEE Trans Circuits Syst Video Technol 29(3):800–814CrossRefGoogle Scholar
  9. 9.
    Wang H et al (2011) Action recognition by dense trajectories. 2011 IEEE conference on computer vision and pattern recognition (CVPR). IEEEGoogle Scholar
  10. 10.
    Aggarwal JK, Ryoo MS (2011) Human activity analysis: a review. ACM Comput Surv 43(3):1–43CrossRefGoogle Scholar
  11. 11.
    Wu D et al (2016) Deep dynamic neural networks for multimodal gesture segmentation and recognition. IEEE Trans Pattern Anal Mach Intell 38(8):1583–1597CrossRefGoogle Scholar
  12. 12.
    Laptev I et al (2008) Learning realistic human actions from movies. IEEE conference on computer vision and pattern recognition, CVPR 2008. IEEEGoogle Scholar
  13. 13.
    Devi R, Srinivasa A, Srinivasa G (2016) Detection of multiple, co-occurring actions in video frames. In: International conference on wireless communications, signal processing and networking (WiSPNET). IEEEGoogle Scholar
  14. 14.
    Zhang B et al (2017) Action recognition using 3D histograms of texture and a multi-class boosting classifier. IEEE Trans Image ProcessGoogle Scholar
  15. 15.
    Geertsema EE et al (2019) Automated remote fall detection using impact features from video and audio. J BiomechGoogle Scholar
  16. 16.
    Zhou W et al (2018) Foreground detection based on co-occurrence background model with hypothesis on degradation modification in background changes. In: 2018 12th France-Japan and 10th Europe-Asia congress on mechatronics. IEEE Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • M. N. Renuka Devi
    • 1
  • Gowri Srinivasa
    • 1
  1. 1.PESIT South CampusBengaluruIndia

Personalised recommendations