Scene modelling using an adaptive mixture of Gaussians in colour and space

Dickinson, Patrick and Hunter, Andrew (2005) Scene modelling using an adaptive mixture of Gaussians in colour and space. In: IEEE Conference on Advanced Video and Signal based Surveillance, 15-15 Sept 2005, Como, Italy.

This is the latest version of this item.

Documents
avss2005pld.pdf
[img]
[Download]
[img]
Preview
PDF
avss2005pld.pdf

397kB

Official URL: http://dx.doi.org/10.1109/AVSS.2005.1577244

Abstract

We present an integrated pixel segmentation and region
tracking algorithm, designed for indoor environments. Visual monitoring systems often use frame differencing techniques to independently classify each image pixel as either foreground or background. Typically, this level of processing does not take account of the global image structure, resulting in frequent misclassification.
We use an adaptive Gaussian mixture model in colour and space to represent background and foreground regions of the scene. This model is used to probabilistically classify observed pixel values, incorporating the global scene structure into pixel-level segmentation. We evaluate our system over 4 sequences and show that it successfully segments foreground pixels and tracks major foreground regions as they move through the scene.

Item Type:Conference or Workshop Item (Poster)
Additional Information:We present an integrated pixel segmentation and region tracking algorithm, designed for indoor environments. Visual monitoring systems often use frame differencing techniques to independently classify each image pixel as either foreground or background. Typically, this level of processing does not take account of the global image structure, resulting in frequent misclassification. We use an adaptive Gaussian mixture model in colour and space to represent background and foreground regions of the scene. This model is used to probabilistically classify observed pixel values, incorporating the global scene structure into pixel-level segmentation. We evaluate our system over 4 sequences and show that it successfully segments foreground pixels and tracks major foreground regions as they move through the scene.
Keywords:Background model, Adaptive background model, Surveillance
Subjects:G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
ID Code:83
Deposited By: Patrick Dickinson
Deposited On:23 Feb 2006
Last Modified:13 Mar 2013 08:21

Available Versions of this Item

  • Scene modelling using an adaptive mixture of Gaussians in colour and space. (deposited 23 Feb 2006) [Currently Displayed]

Repository Staff Only: item control page