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.
Similar content being viewed by others
References
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):253–272
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):1–12
Wang X, Gao M, He X et al (2014) An abnormal crowd behavior detection algorithm based on fluid mechanics. J Comput 9(5):1144–1149
Cui J, Liu W, Xing W (2014) Crowd behaviors analysis and abnormal detection based on surveillance data. J Vis Lang Comput 25(6):628–636
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):135–145
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):1106–1114
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):29–33
Zhu S, Hu J, Shi Z (2016) Local abnormal behavior detection based on optical flow and spatio-temporal gradient. Multimed Tools Appl 75(15):9445–9459
Alvar M, Torsello A, Sanchez-Miralles A et al (2014) Abnormal behavior detection using dominant sets. Mach Vis Appl 25(5):1351–1368
Zhang X, Zhang Q, Hu S et al (2018) Energy level-based abnormal crowd behavior detection. Sensors 18(2):423
Chan YT (2017) Extracting foreground ensemble features to detect abnormal crowd behavior in intelligent video-surveillance systems. J Electron Imaging 26(5):051402
Balasubramanian Y (2015) Human crowd behavior analysis based on graph modeling and matching in a synoptic video. Volume 3(3):1050–1056
Zhao F, Li J (2014) Pedestrian motion tracking and crowd abnormal behavior detection based on intelligent video surveillance. J Netw 9(10):2598
Sang HF, Yu C, Da-HE K (2016) Crowd gathering and running behavior detection based on overall features. J Optoelectron Laser 27(1):52–60
Pan S, Sun W, Zheng Z (2017) Video segmentation algorithm based on superpixel link weight model. Multimed Tools Appl 76(19):19741–19760
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):10269–10278
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):2611–2618
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):32–44
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):18027–18045
Acknowledgements
This paper is supported by the Science and Technology Research Project of Chongqing Municipal Education Committee (Grant: KJ1704089).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Xie, S., Zhang, X. & Cai, J. Video crowd detection and abnormal behavior model detection based on machine learning method. Neural Comput & Applic 31 (Suppl 1), 175–184 (2019). https://doi.org/10.1007/s00521-018-3692-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-018-3692-x