Skip to content
/ NPSG Public

[PR 2021] Nonlocal Patch Similarity based Graph (NPSG) for heterogeneous remote sensing change detection

License

Notifications You must be signed in to change notification settings

yulisun/NPSG

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

27 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

NPSG

[PR 2021] Nonlocal Patch Similarity based Graph (NPSG) for heterogeneous remote sensing change detection

Code: NPSG - PR 2021

This is a test program for the NPSG. NPSG is based on the image self-similarity. The relationship between the target patch and its similar patches can be regarded as the structure of this target patch, which is quite well preserved across the different types of imaging modality, then it can be used to build the relationship between heterogeneous images.

The computational time of NPSG is relatively long, to reduce the computational complexity, we recommend using a larger opt.delt_s and opt.delt_p.

Another suggestion is to use the INLPG algorithm we proposed (https://github.com/yulisun/INLPG) or the IRG-McS algorithm (https://github.com/yulisun/IRG-McS).

If you use this code for your research, please cite our papers.

@article{sun109nonlocal, title={Nonlocal patch similarity based heterogeneous remote sensing change detection},
author={Sun, Yuli and Lei, Lin and Li, Xiao and Sun, Hao and Kuang, Gangyao},
journal={Pattern Recognition},
volume={109},
pages={107598},
publisher={Elsevier}}

If you have any queries, please do not hesitate to contact me (sunyuli@mail.ustc.edu.cn ).

About

[PR 2021] Nonlocal Patch Similarity based Graph (NPSG) for heterogeneous remote sensing change detection

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages