1.
Scene modelling using an adaptive mixture of Gaussians in colour and space - Dickinson, Patrick; Hunter, Andrew
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...
(application/pdf) - 08-may-2009
2.
An FPGA-based infant monitoring system - Dickinson, Patrick; Appiah, Kofi; Hunter, Andrew; Ormston, Stephen
We have designed an automated visual surveillance system for monitoring sleeping infants. The low-level image
processing is implemented on an embedded Xilinx’s Virtex
II XC2v6000 FPGA and quantifies the level of scene activity using a specially designed background subtraction algorithm. We present our algorithm and show how we have
optimised it for this platform.
- 08-may-2009
3.
Body region labelling for action recognition - Dickinson, Patrick; Hunter, Andrew
We present a novel method for automatically labelling the head, torso, and legs of a human body tracked through a video sequence. An appearance-based body model is constructed by dividing the initial silhouette into a series of spatial slices, and building a colour distribution histogram for each. In subsequent frames a labelling hypothesis is constructed for each new silhouette by matching against these distributions, and used to identify each body region under a range of poses. We use the body model to extract feature points, which we use as the basis for an action recognition scheme. Actions are represented by...
- 27-may-2009
4.
An intelligent reconfigurable infant monitoring system - Appiah, Kofi; Dickinson, Patrick; Hunter, Andrew
We have devised an automated visual surveillance system for monitoring sleeping infants. The system architecture requires that low-level image processing is executed on camera by an embedded signal processing unit: thus in tegrating more functionality into a single chip and realising lower product cost. The processing unit quantifies the level of scene activity using a specially designed background subtraction algorithm. In this paper we begin by describing the overall structure of our system. We proceed by present ing our algorithms, and demonstrating their effectiveness in measuring scene activity. We conclude by describing the FPGA-based low-level processing functions, and show how...
- 27-may-2009
1.
