Advertisement

Neural Computing and Applications

, Volume 31, Supplement 1, pp 175–184 | Cite as

Video crowd detection and abnormal behavior model detection based on machine learning method

  • Shaoci XieEmail author
  • Xiaohong Zhang
  • Jing Cai
S.I. : Machine Learning Applications for Self-Organized Wireless Networks
  • 154 Downloads

Abstract

Pedestrian detection and abnormal behavior detection is the computer for a given image and video, to determine whether there are pedestrians and their behavior is normal. Pedestrian detection is the basis and premise of pedestrian tracking, behavior analysis, gait analysis, pedestrian identity recognition and so on. A good pedestrian detection algorithm can provide strong support and guarantee for the latter. The overall goal of this project is to learn different data mining methods and try to improve the detection accuracy of video crowd machine abnormal behavior. Aiming at the shortage of user behavior anomaly detection model proposed by Lane et al., a new IDS anomaly detection model is proposed. This model improves the representation of user behavior patterns and behavior profiles and adopts a new similarity assignment method. Experiments based on Unix user shell command data show that the detection model proposed in this paper has higher detection performance.

Keywords

Machine learning Image and video Pedestrian detection Anomaly detection 

Notes

Acknowledgements

This paper is supported by the Science and Technology Research Project of Chongqing Municipal Education Committee (Grant: KJ1704089).

References

  1. 1.
    Mohammadi S, Galoogahi HK, Perina A, Murino V (2017) Physics-inspired models for detecting abnormal behaviors in crowded scenes. Group Crowd Behav Comput Vis 1(12):253–272Google Scholar
  2. 2.
    Rabiee H, Mousavi H, Nabi M, Ravanbakhsh M (2017) Detection and localization of crowd behavior using a novel tracklet-based model. Int J Mach Learn Cybern 2(2):1–12Google Scholar
  3. 3.
    Wang X, Gao M, He X et al (2014) An abnormal crowd behavior detection algorithm based on fluid mechanics. J Comput 9(5):1144–1149Google Scholar
  4. 4.
    Cui J, Liu W, Xing W (2014) Crowd behaviors analysis and abnormal detection based on surveillance data. J Vis Lang Comput 25(6):628–636Google Scholar
  5. 5.
    Roubtsova ANS, With PHND (2013) Group localisation and unsupervised detection and classification of basic crowd behaviour events for surveillance applications. Proc SPIE Int Soc Opt Eng 8663(3):135–145Google Scholar
  6. 6.
    Zhang X, Wang M, Zuo J et al (2015) Abnormal crowd behavior detection based on motion clustering of mesoscopic group. Yi Qi Yi Biao Xue Bao/Chin J Sci Instrum 36(5):1106–1114Google Scholar
  7. 7.
    Abardeig J, Cai J, Zhu Z (2016) Study on the method of detecting the crowd abnormality in the sensitive media image based on behavior analysis. Recent Adv Electr Electron Eng 9(1):29–33Google Scholar
  8. 8.
    Zhu S, Hu J, Shi Z (2016) Local abnormal behavior detection based on optical flow and spatio-temporal gradient. Multimed Tools Appl 75(15):9445–9459Google Scholar
  9. 9.
    Alvar M, Torsello A, Sanchez-Miralles A et al (2014) Abnormal behavior detection using dominant sets. Mach Vis Appl 25(5):1351–1368Google Scholar
  10. 10.
    Zhang X, Zhang Q, Hu S et al (2018) Energy level-based abnormal crowd behavior detection. Sensors 18(2):423Google Scholar
  11. 11.
    Chan YT (2017) Extracting foreground ensemble features to detect abnormal crowd behavior in intelligent video-surveillance systems. J Electron Imaging 26(5):051402Google Scholar
  12. 12.
    Balasubramanian Y (2015) Human crowd behavior analysis based on graph modeling and matching in a synoptic video. Volume 3(3):1050–1056Google Scholar
  13. 13.
    Zhao F, Li J (2014) Pedestrian motion tracking and crowd abnormal behavior detection based on intelligent video surveillance. J Netw 9(10):2598Google Scholar
  14. 14.
    Sang HF, Yu C, Da-HE K (2016) Crowd gathering and running behavior detection based on overall features. J Optoelectron Laser 27(1):52–60Google Scholar
  15. 15.
    Pan S, Sun W, Zheng Z (2017) Video segmentation algorithm based on superpixel link weight model. Multimed Tools Appl 76(19):19741–19760Google Scholar
  16. 16.
    Shehab A, Elhoseny M, Muhammad K, Sangaiah AK, Yang P, Huang H, Hou G (2018) Secure and robust fragile watermarking scheme for medical images. IEEE Access 6(1):10269–10278Google Scholar
  17. 17.
    Zheng Z, Huang T, Zhang H et al (2016) Towards a resource migration method in cloud computing based on node failure rule. J Intell Fuzzy Syst 31(5):2611–2618Google Scholar
  18. 18.
    Tharwat A, Mahdi H, Elhoseny M, Hassanien AE (2018) Recognizing human activity in mobile crowdsensing environment using optimized k-NN algorithm. Expert Syst Appl 107(1):32–44Google Scholar
  19. 19.
    Zheng Z, Jeong HY, Huang T et al (2017) KDE based outlier detection on distributed data streams in multimedia network. Multimed Tools Appl 76(17):18027–18045Google Scholar

Copyright information

© The Natural Computing Applications Forum 2018

Authors and Affiliations

  1. 1.School of Big Data and Software EngineeringChongqing UniversityChongqingChina
  2. 2.School of Communication and Information EngineeringChongqing University of Posts and TelecommunicationsChongqingChina

Personalised recommendations