MSIM: A change detection framework for damage assessment in natural disasters

作者：

Highlights：

• A new social image model by exploiting tags and locations is proposed.

• Image pair identification can be enhanced by clustering and hash techniques.

• Proposed relative position annulus model is robust to boundary rotation.

• Proposed change detection method outperforms the existing techniques.

摘要

•A new social image model by exploiting tags and locations is proposed.•Image pair identification can be enhanced by clustering and hash techniques.•Proposed relative position annulus model is robust to boundary rotation.•Proposed change detection method outperforms the existing techniques.

论文关键词：Change detection,Social images,Disaster assessment

论文评审过程：Received 17 August 2017, Revised 9 December 2017, Accepted 20 December 2017, Available online 27 December 2017, Version of Record 8 January 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.12.038