NorMaL: Non-compact Markovian Likelihood for change detection

This paper presents a new normalcy model of a scene for change detection using images taken from multiple views and varying illumination conditions. Each coregistered pixel site is statistically modeled by a probability distribution conditioned on a set of pixels in a non-local neighborhood that are less likely to be affected by a change that happens at the pixel of interest. These "non-compact neighbors" are located using information theoretic approaches. The associated change detection algorithm is called Non-compact Markovian Likelihood (NorMaL), which predicts normalcy of a scene based on non-compact neighborhoods using non-parametric conditional density estimation.

• Type: Conference
• Year: 2008
• Where: ICPR
• Authors: David B. Cooper, Joseph L. Mundy, Osman Gokhan Sezer, Yucel Altunbasak
• Keywords: Change Detection Algorithm, Computer Vision, ICPR 2008, Non-compact Markovian Likelihood, Non-parametric Conditional Density