Soft competitive adaptation: neural network learning algorithms based on fitting statistical mixtures
Comparing images using color coherence vectors
MULTIMEDIA '96 Proceedings of the fourth ACM international conference on Multimedia
A view of the EM algorithm that justifies incremental, sparse, and other variants
Learning in graphical models
Using Dynamic Time Warping to Bootstrap HMM-Based Clustering of Time Series
Sequence Learning - Paradigms, Algorithms, and Applications
Visual Surveillance of Human Activity
ACCV '98 Proceedings of the Third Asian Conference on Computer Vision-Volume II
AVSS '03 Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance
Dining Activity Analysis Using a Hidden Markov Model
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Video Behaviour Profiling and Abnormality Detection without Manual Labelling
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Conditional Random Fields for Contextual Human Motion Recognition
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Hidden Conditional Random Fields for Gesture Recognition
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Recognizing Interaction Activities using Dynamic Bayesian Network
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 01
Behavior Modeling and Recognition Based on Space-Time Image Features
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 01
Incremental ML estimation of HMM parameters for efficient training
ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 02
Adaptive real-time anomaly detection with incremental clustering
Information Security Tech. Report
Spectral clustering with eigenvector selection
Pattern Recognition
Conditional random fields for activity recognition
Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
Activity based surveillance video content modelling
Pattern Recognition
Incremental and adaptive abnormal behaviour detection
Computer Vision and Image Understanding
Using Density-Based Incremental Clustering for Anomaly Detection
CSSE '08 Proceedings of the 2008 International Conference on Computer Science and Software Engineering - Volume 03
Incremental Clustering Algorithm for Intrusion Detection Using Clonal Selection
PACIIA '08 Proceedings of the 2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application - Volume 01
Learning Motion Patterns in Surveillance Video using HMM Clustering
WMVC '08 Proceedings of the 2008 IEEE Workshop on Motion and video Computing
International Journal of Robotics Research
Improved background mixture models for video surveillance applications
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
Online anomaly detection for sensor systems: A simple and efficient approach
Performance Evaluation
Detecting unusual activity in video
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
ADWICE – anomaly detection with real-time incremental clustering
ICISC'04 Proceedings of the 7th international conference on Information Security and Cryptology
Hi-index | 0.01 |
We propose and evaluate an efficient method for automatic identification of suspicious behavior in video surveillance data that incrementally learns scene-specific statistical models of human behavior without requiring storage of large databases of training data. The approach begins by building an initial set of models explaining the behaviors occurring in a small bootstrap dataset. The bootstrap procedure partitions the bootstrap set into clusters then assigns new observation sequences to clusters based on the statistical tests of HMM log likelihood scores. Cluster-specific likelihood thresholds are learned rather than set arbitrarily. After bootstrapping, each new sequence is used to incrementally update the sufficient statistics of the HMM it is assigned to. In an evaluation on a real-world testbed video surveillance dataset, we find that within 1week of observation, the incremental method's false alarm rate drops below that of a batch method on the same data. The incremental method obtains a false alarm rate of 2.2% at a 91% hit rate. The method is thus a practical and effective solution to the problem of inducing scene-specific statistical models useful for bringing suspicious behavior to the attention of human security personnel.