A Multiple SVM System for Classification of Hyperspectral Remote Sensing Data

Abstract

With recent technological advances in remote sensing sensors and systems, very highdimensional hyperspectral data are available for a better discrimination among different complex landcover classes. However, the large number of spectral bands, but limited availability of training samples creates the problem of Hughes phenomenon or 'curse of dimensionality' in hyperspectral data sets. Moreover, these high numbers of bands are usually highly correlated. Because of these complexities of hyperspectral data, traditional classification strategies have often limited performance in classification of hyperspectral imagery. Referring to the limitation of single classifier in these situations, Multiple Classifier Systems (MCS) may have better performance than single classifier. This paper presents a new method for classification of hyperspectral data based on a band clustering strategy through a multiple Support Vector Machine system. The proposed method uses the band grouping process based on a modified mutual information strategy to split data into few band groups. After the band grouping step, the proposed algorithm aims at benefiting from the capabilities of SVM as classification method. So, the proposed approach applies SVM on each band group that is produced in a previous step. Finally, Naive Bayes (NB) as a classifier fusion method combines decisions of SVM classifiers. Experimental results on two common hyperspectral data sets show that the proposed method improves the classification accuracy in comparison with the standard SVM on entire bands of data and feature selection methods.

Learning or assessment of classification algorithms relying on biased ground truth data: what interest?

“…41 Other approaches belonging to this category make use of classifiers like SVM and multilayer perceptron. [42][43][44][45][46][47][48][49] Whatever the method or approach within this category, the experimental results and the comparisons made by using these two GTs are hardly exploitable since specific regions considered as homogeneous in the associated GT are actually not. In addition to this difficulty, another problem is the choice of the learning samples and their number within each class, because the classification results are highly dependent on these.…”

A decision-based multi-sensor classification system using thermal hyperspectral and visible data in urban area

“…The extracted features should comprise distinct descriptors to separate several objects (Table 3). Hyperspectral remote-sensing images consist of extremely narrow spectral bands that result in high inter-band correlation and timeconsuming image analysis operations; excessive descriptors can lead to the curse of dimensionality problem, also called Hughes phenomenon, in case of using standard classifiers (S. Bigdeli et al, 2013;Li et al, 2011). In this context, DR is used to transform the data volume into a reduced dimensionality form with distinct descriptor information to overcome the mentioned phenomenon (Hasanlou, Samadzadegan, & Homayouni, 2015).…”

“…With recent technological advances in remote-sensing systems and the accessibility of multi-sensor information, the research community has motivated an increasing utilization of well-defined features measured by various sensors to obtain an improved classification accuracy of remotely sensed data (S. Bigdeli, Samadzadegan, & Reinartz, 2013;Li, Wu, Wan, & Zhu, 2011;Lu, Zhang, Li, & Zhang, 2015). Fusion of multi-sensor data provides complementary data from the same observed site results in a superior comprehension of the scene which is impossible with single sensor data (Bigdeli, Samadzadegan, & Reinartz, 2014;Du, Liu, Xia, & Zhao, 2013;Lu et al, 2015).…”

Spectral–spatial feature learning for hyperspectral imagery classification using deep stacked sparse autoencoder

“…With the recent technological advances in remote sensing systems and the accessibility of hyperspectral data, the geoscience and remote sensing research community is increasing utilization of well-defined spectral information of hyperspectral images in a wide range of practical applications. 1,2 Hyperspectral image data are comprised of hundreds of continuous narrow spectral bands, resulting in high spectral information for the identification of diverse physical materials and leading thereby to enhanced image classification results. 3,4 In the last decade, a large number of methods have been widely investigated for addressing the ill-posed classification problems of hyperspectral remote sensing data by considering high dimensionality and complexity of spectral features.…”