Robust power line extraction from aerial image using object-based Gaussian–Markov random field with gravity property parameters

作者：

Highlights：

• Gaussian–Markov model is extended to contactless and irregular neighborhood system.

• A parameter estimation model with gravity property is defined.

• The OGMRF-GPP method requires no prior knowledge or auxiliary object.

摘要

•Gaussian–Markov model is extended to contactless and irregular neighborhood system.•A parameter estimation model with gravity property is defined.•The OGMRF-GPP method requires no prior knowledge or auxiliary object.

论文关键词：Aerial image,Power line extraction,Object-based Markov random field,Gaussian–Markov model,Gravity property model

论文评审过程：Received 14 April 2021, Revised 7 December 2021, Accepted 2 January 2022, Available online 10 January 2022, Version of Record 25 January 2022.

论文官网地址：https://doi.org/10.1016/j.image.2022.116634