ADAPTIVE CENSUS AND INTERPOLATION BASED DISPARITY ESTIMATION USING WEIGHTED AUTOREGRESSIVE MODELS

Abstract

This paper deals with an adaptive general scale interpolation algorithm that is capable of arbitrary scaling factors considering the non-stationarity of natural images. The proposed AR terms are modeled by pixels with their adjacent unknown HR neighbors. A novel stereo matching algorithm is proposed that utilizes color segmentation on the reference image and a self-adapting matching score that maximizes the number of reliable correspondences. Modified Census Transform is a form of non-parametric local transform used in image processing within a square window to a bit string, thereby capturing the image structure. The centre pixel’s intensity value is replaced by the bit string composed of set of boolean comparisons such that in a square window, moving left to right. A new technique is used and found a solution for correspondence problem that makes use of non-parametric local transforms as the basis for correlation. Non-parametric transforms rely on the relative ordering of local intensity values, and not on the intensity values themselves. Correlation using such transforms can tolerate a significant number of images. This can result in improved performance near object boundaries when compared with conventional methods such as normalized correlation.