Automatic soccer field of play registration

作者：

Highlights：

• Automatic registration of soccer images on a model of the field of play.

• Field of play segmentation and detection of representative line segments.

• Probabilistic decision tree to classify the set of all straight lines.

• Center circle modelling using a Least Square Fitting algorithm for ellipses.

• Three-step validation stage to determine whether the registration is correct.

摘要

•Automatic registration of soccer images on a model of the field of play.•Field of play segmentation and detection of representative line segments.•Probabilistic decision tree to classify the set of all straight lines.•Center circle modelling using a Least Square Fitting algorithm for ellipses.•Three-step validation stage to determine whether the registration is correct.

论文关键词：Soccer,Football,Field of play,Playing field,Registration,Segmentation,Line segment detection,Line classification,Validation

论文评审过程：Received 18 July 2019, Revised 30 December 2019, Accepted 12 February 2020, Available online 16 February 2020, Version of Record 24 February 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107278