A New GPU Implementation of Support Vector Machines for Fast Hyperspectral Image Classification

Abstract

The storage and processing of remotely sensed hyperspectral images (HSIs) is facing important challenges due to the computational requirements involved in the analysis of these images, characterized by continuous and narrow spectral channels. Although HSIs offer many opportunities for accurately modeling and mapping the surface of the Earth in a wide range of applications, they comprise massive data cubes. These huge amounts of data impose important requirements from the storage and processing points of view. The support vector machine (SVM) has been one of the most powerful machine learning classifiers, able to process HSI data without applying previous feature extraction steps, exhibiting a robust behaviour with high dimensional data and obtaining high classification accuracies. Nevertheless, the training and prediction stages of this supervised classifier are very time-consuming, especially for large and complex problems that require an intensive use of memory and computational resources. This paper develops a new, highly efficient implementation of SVMs that exploits the high computational power of graphics processing units (GPUs) to reduce the execution time by massively parallelizing the operations of the algorithm while performing efficient memory management during data-reading and writing instructions. Our experiments, conducted over different HSI benchmarks, demonstrate the efficiency of our GPU implementation.

Machine-Learning Classification of Soil Bulk Density in Salt Marsh Environments

“…Furthermore, these classifiers can be successfully used to select and rank those variables with the greatest ability to discriminate between the target classes [ 82 , 84 , 85 ]. This is an important asset given that the high dimensionality of remotely sensed data makes the selection of the most relevant variables a time-consuming, error-prone, and subjective task [ 82 , 84 , 86 , 87 ]. SVM is particularly appealing in remote sensing due to its ability to successfully handle the high dimensionality of remotely sensed data [ 78 , 88 ], often producing higher classification accuracy than the traditional methods [ 89 , 90 , 91 ].…”

Rotation Equivariant Convolutional Neural Networks for Hyperspectral Image Classification

“…Traditionally, HSI information has been exploited in machine learning (ML) by pixel-wise methods which consider HSI data as a list of spectral vectors, assuming that each pixel is pure and typically labeled as a single land cover type [32]- [34]. In the current literature, there are abundant pixelwise methods, such as the popular support vector machines (SVMs) [35], [36], K-nearest neighbor (KNN) [37], [38], multinomial logistic regression (MLR) [39], [40], random forests (RFs) [41], [42] and standard artificial neural networks (ANNs) [43], among others. As these methods conduct only spectral processing to assign each pixel to its corresponding land-cover class, their reliability (in terms of classification accuracy) is strongly related to the number and spectral-quality of training samples.…”

Mapping Essential Urban Land Use Categories in Beijing with a Fast Area of Interest (AOI)-Based Method

“…Powerful in self-adaptive capability, machine-learning methods are popularly applied in land-use classification. Random Forests, support vector machines, and artificial neural networks have made a great contribution to land-cover/land-use classification [4][5][6][7][8][9][10][11]. The support vector machine (SVM) is applied to reduce the execution time of storing and processing hyperspectral images [11].…”

“…Random Forests, support vector machines, and artificial neural networks have made a great contribution to land-cover/land-use classification [4][5][6][7][8][9][10][11]. The support vector machine (SVM) is applied to reduce the execution time of storing and processing hyperspectral images [11]. Simple/multiple linear regression, random forest (RF), and support vector regression (SVR) were used to estimate canopy nitrogen weight of maize leaves, and the results showed that both machine learning models performed much better than linear regression [4].…”