HMM-based unusual motion detection without tracking

We propose novel pixel dense modeling of motion of urban traffic in noisy environments with the help of multidimensional Gaussian Mixture Models (GMMs) and Hidden Markov Models (HMMs). In our approach there is no need for object tracking in order to detect anomalous motion or to model and visualize...

Full description

Saved in:
Bibliographic Details
Main Authors: Utasi, A., Czuni, L.
Format: Conference Proceeding
Language:English
Subjects:
Fluctuations
Gaussian noise
Hidden Markov models
Motion detection
Multidimensional systems
Object detection
Tracking
Traffic control
Visualization
Working environment noise
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We propose novel pixel dense modeling of motion of urban traffic in noisy environments with the help of multidimensional Gaussian Mixture Models (GMMs) and Hidden Markov Models (HMMs). In our approach there is no need for object tracking in order to detect anomalous motion or to model and visualize the fluctuation of traffic. We propose a new scaling method introduced into the HMM to get a robust tool for the analysis of hundreds of motion vector samples at a time. We show the use of our model with a photorealistic video synthetized from real life recordings.
ISSN:1051-4651
2831-7475
DOI:10.1109/ICPR.2008.4761676