Skip to Main content Skip to Navigation
Conference papers

Joint Bayesian Hyperspectral Unmixing for change detection

Abstract : Spectral unmixing allows to extract endmembers and estimate their proportions in hyperspectral data. Each observed pixel is considered to be a linear combination of several endmembers spectra. Based on a novel hierarchical Bayesian model, change detection into hyperspectral images is achieved by unmixing. A Gibbs sampler is proposed to overcome the complexity of integrating the resulting posterior distribution. The performance of the proposed Bayesian change detection method is evaluated on real data. It provides binary detection with a precision rate up to 98.90%.
Document type :
Conference papers
Complete list of metadata

Cited literature [12 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02942312
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Thursday, September 17, 2020 - 5:01:21 PM
Last modification on : Wednesday, June 9, 2021 - 10:00:33 AM
Long-term archiving on: : Thursday, December 3, 2020 - 10:24:41 AM

File

gharbi_26413.pdf
Files produced by the author(s)

Identifiers

Citation

Walma Gharbi, Lotfi Chaari, Amel Benazza-Benyahia. Joint Bayesian Hyperspectral Unmixing for change detection. Mediterranean and Middle-East Geoscience and Remote Sensing Symposium (M2GARSS 2020), Mar 2020, Tunis, Tunisia. pp.37-40, ⟨10.1109/M2GARSS47143.2020.9105275⟩. ⟨hal-02942312⟩

Share

Metrics

Record views

33

Files downloads

63