Analyse d'image hyperspectrale

Abstract : This dissertation addresses hyperspectral image analysis, a set of techniques enabling exploitation of micro-spectroscopy images. Images produced by these sensors constitute cubic arrays, meaning that every pixel in the image is actually a spectrum.The size of these images, which is often quite large, calls for an upgrade for classical image analysis algorithms.We start out our investigation with clustering techniques. The main idea is to regroup every spectrum contained in a hyperspectralimage into homogeneous clusters. Spectrums taken across the image can indeed be generated by similar materials, and hence display spectral signatures resembling each other. Clustering is a commonly used method in data analysis. It belongs nonetheless to a class of particularly hard problems to solve, named NP-hard problems. The efficiency of a few heuristics used in practicewere poorly understood until recently. We give theoretical arguments guaranteeing success when the groups studied displaysome statistical property.We then study unmixing techniques. The objective is no longer to decide to which class a pixel belongs, but to understandeach pixel as a mix of basic signatures supposed to arise from pure materials. The mathematical underlying problem is again NP-hard.After studying its complexity, and suggesting two lengthy relaxations, we describe a more practical way to constrain the problemas to obtain regularized solutions.We finally give an overview of other hyperspectral image analysis methods encountered during this thesis, amongst whomare independent component analysis, non-linear dimension reduction, and regression against a spectrum library.
Document type :
Complete list of metadatas

Cited literature [110 references]  Display  Hide  Download
Contributor : Abes Star <>
Submitted on : Tuesday, September 25, 2018 - 4:49:07 PM
Last modification on : Wednesday, September 26, 2018 - 1:12:50 AM
Long-term archiving on : Wednesday, December 26, 2018 - 4:00:49 PM


Version validated by the jury (STAR)


  • HAL Id : tel-01881335, version 1



Adrien Faivre. Analyse d'image hyperspectrale. Théorie spectrale [math.SP]. Université Bourgogne Franche-Comté, 2017. Français. ⟨NNT : 2017UBFCD075⟩. ⟨tel-01881335⟩



Record views


Files downloads