Feature-point based matching: a sequential approach based on relaxation labeling and relative orientation

Mauricio Galo
São Paulo State University - UNESP
Faculty of Sciences and Technology - FCT
Department of Cartography
CP 468, 19060-900, Presidente Prudente - SP
Brazil

Clésio L. Tozzi
State University of Campinas - UNICAMP
School of Electrical and Computer Engineering - FEEC
Department of Computer Engineering and Industrial Automation - DCA
CP 6101, 13083-970, Campinas - SP
Brazil

Abstract

This paper presents a solution for the problem of correspondence and relative orientation (RO) estimation for a pair of images. The solution is obtained by relaxation labeling using multiple metrics applied to image primitives. Besides the use of metrics based on radiometric elements (intensities, gradient, and coefficient of correlation), and on geometry (distance ratios), two additional metrics are considered. One is based on angular relations between primitives and another based on the volume of Matching Parallelepiped (MP) that allows the inclusion of the epipolar geometry constraint directly in the similarity and compatibility computation. The proposed solution was applied to synthetic and real images. The results showed that the use of multiple metrics contribute to the automation of the correspondence process and RO determination, even considering pairs of images subject to convergence, rotation, differences in scale, and presence of repetitive patterns.