Dynamic Ensemble Selection Approach for Hyperspectral Image Classification With Joint Spectral and Spatial Information

Abstract

Accurate generation of a land cover map using hyperspectral data is an important application of remote sensing. Multiple classifier system (MCS) is an effective tool for hyperspectral image classification. However, most of the research in MCS addressed the problem of classifier combination, while the potential of selecting classifiers dynamically is least explored for hyperspectral image classification. The goal of this paper is to assess the potential of dynamic classifier selection/dynamic ensemble selection (DCS/DES) for classification of hyperspectral images, which consists in selecting the best (subset of) optimal classifier(s) relative to each input pixel by exploiting the local information content of the image pixel. In order to have an accurate as well as computationally fast DCS/DES, we proposed a new DCS/DES framework based on extreme learning machine (ELM) regression and a new spectral-spatial classification model, which incorporates the spatial contextual information by using the Markov random field (MRF) with the proposed DES method. The proposed classification framework can be considered as a unified model to exploit the full spectral and spatial information. Classification experiments carried out on two different airborne hyperspectral images demonstrate that the proposed method yields a significant increase in the accuracy when compared to the state-of-the-art approaches.Index Terms-Dynamic classifier selection, dynamic ensemble selection, hyperspectral image classification, markov random field model, multiple classifier system, spectral-spatial classification.

Robust Dynamic Classifier Selection for Remote Sensing Image Classification

“…where s ∈ R + 0 , n(c) and n(c, f i ) hold the same definition in Section II. In practical application, we initiate s from 0 and increase its value over a specific scale (we use 0.1) in each iteration until s does not satisfy (9). We will use this perturbation threshold as an indicator to provide selection strategies for R-DCS in the following section.…”

“…Usually, this classifier choice is made based on a local region of the feature space where the query sample is located in. Most works define this local region by applying the K-Nearest Neighbors technique, which groups samples with similar features to construct a local region [8], [9]. In this work, we group samples differently, by incorporating the concept of robustness to the model specification.…”

Scalable Bag of Subpaths Kernel for Learning on Hierarchical Image Representations and Multi-Source Remote Sensing Data Classification

“…Such technique has been applied for remote sensing datasets [18]. However, most of the remote sensing applications use CRF to enforce smoothness over adjacent regions and increase the classification accuracy (known as the Potts model) [19,20]. This is mainly due to the extremely costly and time-consuming training of a complex model and learning its parameters, as it often requires manual annotation of full scenes.…”

Spectral–Spatial Discriminant Feature Learning for Hyperspectral Image Classification

“…Some features contain less discriminatory information than others, which are not useful for producing a desired learning result, and the limited observations may lead the learning algorithm to overfit to the noise. Therefore, to achieve an excellent classification performance, a dimensionality reduction (DR) [33][34][35][36] procedure is required before training the classifier, which is used to reduce computational complexity and improve classification accuracy. The common dimensionality reduction method can be summarized as feature selection and feature extraction.…”