Vous êtes ici : GIPSA-lab > Formation > Thèses soutenues
XIA Junshi

Multiple Classifier System for the classification of hyperspectral data


Directeur de thèse :     Jocelyn CHANUSSOT

École doctorale : Electronique, electrotechnique, automatique, traitement du signal (EEATS)

Spécialité : Signal, image, parole, télécoms

Structure de rattachement : Autre

Établissement d'origine : China Univeristy of Mining and Technology - Chine

Financement(s) : bourse attribuée par un gouvernement étranger


Date d'entrée en thèse : 01/10/2011

Date de soutenance : 23/10/2014


Composition du jury :
M. Farid MELGANI, Professeur, Université de Trento, President
M. Jon Atli BENEDIKTSSON, Professeur, Université d''Islande, Rapporteur
M. Gregoire MERCIER, Professeur, Telecom Bretagne, Rapporteur
Mme Mireille GUILLAUME, Maître de Conférences, École Centrale de Marseille, Examinateur
M. Peijun DU, Professeur, Université de Nanjing, Co-encadrant
M. Jocelyn CHANUSSOT, Professeur, Grenoble INP, Directeur de thèse


Résumé : In this thesis, we propose several new techniques for the classification of hyperspectral remote sensing images based on multiple classifier system (MCS). Our proposed framework introduces significant innovations with regards to previous approaches in the same field, many of which are mainly based on an individual algorithm. First, we propose to use Rotation Forests with several linear feature extraction and compared them with the traditional ensemble approaches, such as Bagging, Boosting, Random subspace and Random Forest. Second, the integration of the support vector machines (SVM) with Rotation subspace framework for context classification is investigated. SVM and Rotation subspace are two powerful tools for high-dimensional data classification. Therefore, combining them can further improve the classification performance. Third, we extend the work of Rotation Forests by incorporating local feature extraction technique and spatial contextual information with Markov random Field (MRF) to design robust spatial-spectral methods. Finally, we presented a new general framework, Random subspace ensemble, to train series of effective classifiers, including decision trees and extreme learning machine (ELM), with extended multi-attribute profiles (EMAPs) for classifying hyperspectral data. Six RS ensemble methods, including Random subspace with DT (RSDT), Random Forest (RF), Rotation Forest (RoF), Rotation Random Forest (RoRF), RS with ELM (RSELM) and Rotation subspace with ELM (RoELM), are constructed by the multiple base learners. The effectiveness of the proposed techniques is illustrated by comparing with state-of-the-art methods by using real hyperspectral data sets with different contexts.

GIPSA-lab, 11 rue des Mathématiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - 33 (0)4 76 82 71 31