Quantized Census for Stereoscopic Image Matching

Current depth capturing devices show serious drawbacks in certain applications, for example ego-centric depth recovery: they are cumbersome, have a high power requirement, and do not portray high resolution at near distance. Stereo-matching techniques are a suitable alternative, but whilst the idea behind these techniques is simple it is well known that recovery of an accurate disparity map by stereo-matching requires overcoming three main problems: occluded regions causing absence of corresponding pixels, existence of noise in the image capturing sensor and inconsistent color and brightness in the captured images. We propose a modified version of the Census-Hamming cost function which allows more robust matching with an emphasis on improving performance under radiometric variations of the input images.