Switching Hidden Markov Models for Learning of Motion Patterns in Videos

Authors:
Matthias Höffken;Daniel Oberhoff;Marina Kolesnik
Affiliations:
Fraunhofer Institut FIT, Schloss Birlinghoven, Sankt Augustin, Germany 53754;Fraunhofer Institut FIT, Schloss Birlinghoven, Sankt Augustin, Germany 53754;Fraunhofer Institut FIT, Schloss Birlinghoven, Sankt Augustin, Germany 53754
Venue:
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Year:
2009

Citing 6
Cited 0

Multi-View Face Tracking with Factorial and Switching HMM

WACV-MOTION '05 Proceedings of the Seventh IEEE Workshops on Application of Computer Vision (WACV/MOTION'05) - Volume 1 - Volume 01
Disambiguating Visual Motion Through Contextual Feedback Modulation

Neural Computation
Variational Learning for Switching State-Space Models

Neural Computation
Disambiguating Visual Motion by Form-Motion Interaction--a Computational Model

International Journal of Computer Vision
Actions as Space-Time Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence
Switching observation models for contour tracking in clutter

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Building on the current understanding of neural architecture of the visual cortex, we present a graphical model for learning and classification of motion patterns in videos. The model is composed of an arbitrary amount of Hidden Markov Models (HMMs) with shared Gaussian mixture models. The novel extension of our model is the use of additional Markov chain, serving as a switch for indicating the currently active HMM. We therefore call the model a Switching Hidden Markov Model (SHMM). SHMM learns from input optical flow in an unsupervised fashion. Functionality of the model is tested with artificially simulated time sequences. Tests with real videos show that the model is capable of learning and recognition of motion activities of single individuals, and for classification of motion patterns exhibited by groups of people. Classification rates of about 75 percent for real videos are satisfactory taking into account a relative simplicity of the model.