TY - JOUR
T1 - Robust ellipse and spheroid fitting
AU - Yu, Jieqi
AU - Kulkarni, Sanjeev R.
AU - Poor, H. Vincent
N1 - Funding Information:
This research was supported in part by the US Office of Naval Research under Grant Nos. N00014-07-1-0555 and N00014-09-1-0342 , the US Army Research Office under Grant No. W911NF-07-1-0185 , and the National Science Foundation under Science & Technology Center grant CCF-0939370 .
PY - 2012/4/1
Y1 - 2012/4/1
N2 - Ellipse and ellipsoid fitting has been extensively researched and has broad applications. Traditional ellipse fitting methods provide accurate estimation of ellipse parameters in the case of low noise. However, their performance is compromised when the noise level or the ellipse eccentricity are high. In this paper, an algorithm based on the geometric definition of an ellipse/spheroid (a special class of ellipsoid) is proposed. It performs well in high-noise, and high-eccentricity cases. The efficacy of the new algorithm is demonstrated through simulations.
AB - Ellipse and ellipsoid fitting has been extensively researched and has broad applications. Traditional ellipse fitting methods provide accurate estimation of ellipse parameters in the case of low noise. However, their performance is compromised when the noise level or the ellipse eccentricity are high. In this paper, an algorithm based on the geometric definition of an ellipse/spheroid (a special class of ellipsoid) is proposed. It performs well in high-noise, and high-eccentricity cases. The efficacy of the new algorithm is demonstrated through simulations.
KW - Curve fitting
KW - Parameter estimation
KW - Surface fitting
UR - http://www.scopus.com/inward/record.url?scp=84862820037&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84862820037&partnerID=8YFLogxK
U2 - 10.1016/j.patrec.2011.11.025
DO - 10.1016/j.patrec.2011.11.025
M3 - Article
AN - SCOPUS:84862820037
SN - 0167-8655
VL - 33
SP - 492
EP - 499
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
IS - 5
ER -