Reliability analysis of the rank transform for stereo matching

The rank transform is a nonparametric technique which has been recently pro posed for the stereo matching problem. The motivation behind its applicatio n to this problem is its invariance to certain types of image distortion an d noise, as well as its amenability to real-time implementation. This paper derives one constraint which must be satisfied for a correct match. This h as been termed the rank constraint. Experimental work has shown that this c onstraint is capable of resolving ambiguous matches, thereby improving matc hing reliability. A novel matching algorithm incorporating the rank constra int has also been proposed. This modified algorithm consistently resulted i n an increased percentage of correct matches, for all test imagery used. Fu rthermore, the rank constraint has been used to devise a method of identify ing regions of an image where the rank transform, and hence matching outcom e, is more susceptible to noise. Experimental results have shown that the e rrors predicted using this technique are consistent with the actual errors which result when images are corrupted with noise. Such a method could be u sed to identify matches which are likely to be incorrect and/or provide a m easure of confidence in a match.