Color Template Matching Based on Fuzzy Density Clustering for Vision Sensor Based Shoe Detection in Human-Robot Coexisting Environment

Abstract

Fast-Match Algorithm is a fast and randomized template matching algorithm based on affine transformations. However, it is not suitable for color images as they are converted into greyscale images, and hence the color information is lost. An improved algorithm named Color Fast Affine Template Matching (CFAsT-Match), was thus proposed which utilizes all the three color channels (R, G, B). Our previous works have demonstrated how CFAsT-Match can be effectively used in shoe detection problem, wherein a robot can successfully track a target person from consecutive frames captured by an onboard camera. This paper proposes a new technique which extends the template matching algorithm using the Fuzzy Density based Clustering Algorithm instead of the traditional DBSCAN Algorithm. Three variants of Fuzzy based DBSCAN algorithms have been implemented here and a novel similarity measure called Fuzzy-based-colour-sum-of-absolute-differences (FCSAD) has been proposed. Experimental results firmly demonstrate that Fuzzy DBSCAN based CFAsT-Match algorithms can comfortably outperform recently proposed crisp DBSCAN based CFAsT-Match algorithms for shoe detection in human-robot coexisting environments.