Article: Crowd behaviour analysis and anomaly detection by statistical modelling of flow patterns Journal: International Journal of Data Mining, Modelling and Management (IJDMMM) 2014 Vol.6 No.2 pp.168 - 186 Abstract: In this paper, we investigate the crowd behaviours and localise the anomalies due to individual's abrupt dissipation. The novelty of proposed approach is described in three aspects. First, we create the spatio-temporal flow-blocks of the video sequence allowing the marginalisation of arbitrarily flow field. Second, the observed flow field in each flow-block is treated as 2D distribution of samples and mixtures of Gaussian is used to parameterise the flow field. These mixtures of Gaussian result in the distinct representation of flow field named as flow patterns for each flow-block. Third, conditional random field is employed to classify the flow patterns as normal and abnormal for each flow-block. Experiments are conducted on two challenging benchmark datasets PETS 2009 and UMN, and results show that our method achieves higher recognition rates in detecting specific and overall crowd behaviours. In addition, proposed approach shows dominating performance during the comparative analysis with similar approaches. Inderscience Publishers - linking academia, business and industry through research

Title: Crowd behaviour analysis and anomaly detection by statistical modelling of flow patterns

Authors: Saira Saleem Pathan; Ayoub Al-Hamadi; Bernd Michaelis

Addresses: Institute for Electronics, Signal Processing and Communications (IESK), Otto-von-Guericke-University, Building 09, 39106 Magdeburg, Germany ' Institute for Electronics, Signal Processing and Communications (IESK), Otto-von-Guericke-University, Building 09, 39106 Magdeburg, Germany ' Institute for Electronics, Signal Processing and Communications (IESK), Otto-von-Guericke-University, Building 09, 39106 Magdeburg, Germany

Abstract: In this paper, we investigate the crowd behaviours and localise the anomalies due to individual's abrupt dissipation. The novelty of proposed approach is described in three aspects. First, we create the spatio-temporal flow-blocks of the video sequence allowing the marginalisation of arbitrarily flow field. Second, the observed flow field in each flow-block is treated as 2D distribution of samples and mixtures of Gaussian is used to parameterise the flow field. These mixtures of Gaussian result in the distinct representation of flow field named as flow patterns for each flow-block. Third, conditional random field is employed to classify the flow patterns as normal and abnormal for each flow-block. Experiments are conducted on two challenging benchmark datasets PETS 2009 and UMN, and results show that our method achieves higher recognition rates in detecting specific and overall crowd behaviours. In addition, proposed approach shows dominating performance during the comparative analysis with similar approaches.

Keywords: crowd behaviour analysis; Gaussian mixtures; conditional random field; anomaly detection; statistical modelling; flow patterns; video sequences.

DOI: 10.1504/IJDMMM.2014.063196

International Journal of Data Mining, Modelling and Management, 2014 Vol.6 No.2, pp.168 - 186

Published online: 06 Aug 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Crowd behaviour analysis and anomaly detection by statistical modelling of flow patterns

Keep up-to-date