Nonlocal patch similarity based heterogeneous remote sensing change detection

作者：

Highlights：

• An unsupervised change detection framework is proposed by constructing graphs based on nonlocal patch similarity to make heterogeneous data comparable.

• The graphs are compared on the same domain to avoid the leakage of heterogeneous data.

• The forward and backward change detection results are fused by distribution oriented way.

摘要

•An unsupervised change detection framework is proposed by constructing graphs based on nonlocal patch similarity to make heterogeneous data comparable.•The graphs are compared on the same domain to avoid the leakage of heterogeneous data.•The forward and backward change detection results are fused by distribution oriented way.

论文关键词：Unsupervised change detection,Heterogeneous data,Nonlocal similarity,Graph

论文评审过程：Received 28 April 2020, Revised 17 July 2020, Accepted 16 August 2020, Available online 17 August 2020, Version of Record 20 August 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107598