Open AccessDirect solution for pose estimation of single circle with detected centre
Author(s) -
Wang Changyuan,
Chen Derong,
Li Meng,
Gong Jiulu
Publication year - 2016
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
eISSN - 1350-911X
pISSN - 0013-5194
DOI - 10.1049/el.2015.3883
Subject(s) - context (archaeology) , transformation (genetics) , process (computing) , pose , artificial intelligence , image (mathematics) , feature (linguistics) , computer vision , algorithm , coordinate system , matrix (chemical analysis) , monocular , computer science , feature vector , transformation matrix , mathematics , space (punctuation) , paleontology , biochemistry , chemistry , linguistics , philosophy , materials science , physics , kinematics , classical mechanics , biology , composite material , gene , operating system
A direct and analytical algorithm for pose estimation of single space circle in the context of monocular machine vision is proposed. Circular feature with detected centre in the image is used to find two special diameters, one is primarily found for estimating the location of space circle, the other is for estimating the normal vector. The proposed algorithm formulates the problem with solving equations instead of matrix transformation; by solving the equations efficiently, it obtains the single‐valued true solution automatic without choosing the process. Experiments on real images prove that the proposed algorithm can achieve high accuracy. Automatic, efficiency and accuracy together make the proposed algorithm applicable especially in real‐time system.