Title
Recognition of Anomalous Motion Patterns in Urban Surveillance.
Abstract
We investigate the unsupervised K-means clustering and the semi-supervised hidden Markov model (HMM) to automatically detect anomalous motion patterns in groups of people (crowds). Anomalous motion patterns are typically people merging into a dense group, followed by disturbances or threatening situations within the group. The application of K-means clustering and HMM are illustrated with datasets...
Year
DOI
Venue
2013
10.1109/JSTSP.2013.2237882
IEEE Journal of Selected Topics in Signal Processing
Keywords
Field
DocType
Hidden Markov models,Clustering algorithms,Surveillance,Optical filters,Pattern recognition,Merging,Algorithm design and analysis
Crowds,Computer vision,Pattern recognition,Computer science,Pattern clustering,Artificial intelligence,Merge (version control),Cluster analysis,Hidden Markov model,Machine learning
Journal
Volume
Issue
ISSN
7
1
1932-4553
Citations 
PageRank 
References 
7
0.46
9
Authors
4
Name
Order
Citations
PageRank
Maria Andersson1223.35
Fredrik Gustafsson22287281.33
Louis St-Laurent3121.89
Donald Prévost4253.62