TY - JOUR
T1 - Analysis of algebraic and geometric distances for projective transformation estimation
AU - Rios-Orellana, Obed I.
AU - Juarez-Salazar, Rigoberto
AU - Diaz-Ramirez, Victor H.
N1 - Publisher Copyright:
© 2020 COPYRIGHT SPIE.
PY - 2020
Y1 - 2020
N2 - Estimation of projective transformations is an essential process in modern vision-based applications. Usually, the provided experimental point correspondences required to estimate the projective transformations are corrupted with random noise. Thus, for an accurate estimation of the actual projective transformation, a robust optimization criterion must be employed. In this work, we analyze a two-step estimation approach for robust projective transformation estimation. First, the algebraic distance is employed to obtain an initial guess. Then, the geometric distance is used to refine this initial guess. Three geometric-based refining methods are evaluated, namely, the one-image error, the symmetric-transfer error, and reprojection. The obtained results confirm a high accuracy and robustness of the analyzed approach.
AB - Estimation of projective transformations is an essential process in modern vision-based applications. Usually, the provided experimental point correspondences required to estimate the projective transformations are corrupted with random noise. Thus, for an accurate estimation of the actual projective transformation, a robust optimization criterion must be employed. In this work, we analyze a two-step estimation approach for robust projective transformation estimation. First, the algebraic distance is employed to obtain an initial guess. Then, the geometric distance is used to refine this initial guess. Three geometric-based refining methods are evaluated, namely, the one-image error, the symmetric-transfer error, and reprojection. The obtained results confirm a high accuracy and robustness of the analyzed approach.
KW - Algebraic distance
KW - Computer vision
KW - Homography estimation
KW - Projective transformation
UR - http://www.scopus.com/inward/record.url?scp=85092551588&partnerID=8YFLogxK
U2 - 10.1117/12.2569761
DO - 10.1117/12.2569761
M3 - Artículo de la conferencia
AN - SCOPUS:85092551588
SN - 0277-786X
VL - 11509
JO - Proceedings of SPIE - The International Society for Optical Engineering
JF - Proceedings of SPIE - The International Society for Optical Engineering
M1 - 115090A
T2 - Optics and Photonics for Information Processing XIV 2020
Y2 - 24 August 2020 through 4 September 2020
ER -