Ellipse fitting by spatial averaging of random ensembles

作者：

Highlights：

• An ellipse fitting method based on random ensembles is presented.

• The method is robust to outliers due to the use of the L1 median.

• The algorithm fits ellipses over a certain number of subsets of samples and filters the effect of bad fits.

• Our approach outperforms state-of-art methods in both synthetic and real datasets.

摘要

•An ellipse fitting method based on random ensembles is presented.•The method is robust to outliers due to the use of the L1 median.•The algorithm fits ellipses over a certain number of subsets of samples and filters the effect of bad fits.•Our approach outperforms state-of-art methods in both synthetic and real datasets.

论文关键词：Ellipse fitting,Geometric curve fitting,Ensemble methods,Spatial median,Robust estimation

论文评审过程：Received 24 February 2020, Accepted 28 April 2020, Available online 1 May 2020, Version of Record 20 May 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107406