Foreground detection using loopy belief propagation

This paper develops a simple and effective method for detection of sows and piglets in grayscale video recordings of farrowing pens. This approach consists of three stages: background updating, calculation of pseudo-wavelet coefficients and foreground object segmentation. In the first stage, the texture integration is used to update the background modelling (i.e. the reference image). In the second stage, we apply an “à trous” wavelet transform on the current reference image and then perform subtraction between the current original image and the approximation of the current reference image. In the third stage, the pairwise relationships between a pixel and its neighbours on a factor graph are modelled based on the pseudo-wavelet coefficients, and the image probabilities are approximated by using loopy belief propagation. Experiments have shown promising results in extracting foreground objects from complex farrowing pen scenes, such as sudden light changes and dynamic background as well as motionless foreground objects.