Feature matching in omnidirectional images with a large sensor motion for map generation of a mobile robot

摘要

This paper deals with a matching problem of finding correspondences of features in two omnidirectional images. To produce reliable matching results even though there are large translation and rotation of a sensor, we proposed a method that combines the advantages of sum of squared difference (SSD) and dynamic time warping (DTW). Dominant corresponding feature pairs are found using a proximity matrix and an SSD-based similarity matrix, and then the remaining feature matching is accomplished by DTW. Experimental results show that a zero failure rate of matching can be achieved in an indoor environment if the baseline is less than 20 cm.