Convolutional neural networks (CNNs) are relevant tools for remote sensing data processing in the last few years. Kernels process and integrate the spatial information of remotely sensed hyperspectral images (HSIs) accurately enough, so as to reduce the noise and spectral variations present in the data. Despite the great efficiency of the CNNs with HSI data, kernels need to be composed of a large number of layers and parameters to be able to obtain good performance, forcing the model to process a large amount of information from the datasets and making the model prone to overfitting, due to the limited number of labels in some cases. On the other hand, with that huge amount of data to consume, a large number of kernels are needed, making the model less efficient due to computational complexity. To overcome these challenges, this letter presents a new technique to reduce the computational cost and increase the model accuracy [based on adaptable rectangular convolutions (ARCs)], leading to a substantial reduction of the number of parameters and improving the model, in order to achieve better results in the context of HSI semantic segmentation. Thus, the model learns through the convolution the dimensions and offsets of the kernel of this Adaptable layer, performing the average operation based on integral image works to achieve better results with fewer parameters, reducing the risk of overfitting and computational cost. The source code can be found in the repository available at the link. [ https://github.com/jlgs96/segHSI ]

Spectral unmixing is an important technique for hyperspectral data exploitation. It amounts at finding a set of pure spectral signatures (endmembers) of the most representative materials in the scene, and estimating their abundance fractions. The integration of spatial information prior to spectral unmixing of hyperspectral data has attracted much attention in recent years. Several approaches have been developed for the purpose of guiding endmember identification algorithms to spatially representative, yet spectrally pure endmembers. In particular, the spatial preprocessing (SPP) algorithm can be used prior to most existing spectral-based endmember identification techniques, thus promoting the selection of endmembers in spatially representative areas of the scene. However, most SPP techniques are computationally expensive, which adds significant burden to the spectral unmixing process. In this paper, we present three parallel implementations of SPP that have been specifically developed for commodity graphics processing units (GPUs). We perform an evaluation of these techniques using two GPU architectures from NVidia: GeForce GTX 580 and GeForce GTX 870M, which reveals that real-time processing performance can be obtained for real hyperspectral data sets collected by the airborne visible infra-red imaging spectrometer (AVIRIS).

Solving the mixture problem in remotely sensed hyperspectral images remains a challenging task. In particular, solutions are needed in order to obtain a response for applications with real-time constraints. In the last decade, several efforts have been developed, many of them using graphics processing units (GPUs) and focused on the exploitation of spectral information alone. However, a few spectral unmixing chains have been developed using other architectures such as multicore processors, field programmable gate arrays, or Intel Xeon Phi coprocessors. In this letter, we develop a new parallel unmixing chain for multicore processors. Compared with other approaches, the proposed spatial-spectral alternative takes advantage of the complementary information provided by the spatial correlation of the pixels in the image in addition to the spectral information. Our implementation has been optimized using the application program interface OpenMP and the Intel Math Kernel Library on two multicore architectures, and using real analysis scenarios. The results reveal competitive real-time performance compared with another compute unified device architecture implementation previously developed for GPUs.

The identification of pure spectral signatures (endmembers) in remotely sensed hyperspectral images has traditionally focused on the spectral information alone. Recently, techniques such as the spatial-spectral endmember extraction (SSEE) have incorporated both the spectral and the spatial information contained in the scene. Since hyperspectral images contain very detailed information in the spatial and spectral domain, the integration of these two sources of information generally comes with a significant increase in computational complexity. In this paper, we develop a new computationally efficient implementation of SSEE using commodity graphics processing units (GPUs). The relevance of GPUs comes from their very low cost, compact size, and the possibility to obtain significant acceleration factors by exploiting properly the GPU hardware architecture. Our experimental results, focused on evaluating the candidate endmembers produced by SSEE and also the computational performance of the GPU implementation, indicated significant acceleration factors that allow exploiting the SSEE method in computationally efficient fashion.

Spectral unmixing has been a popular technique for analyzing remotely sensed hyperspectral images. The goal of unmixing is to find a collection of pure spectral constituents (called endmembers) that can explain each (possibly mixed) pixel of the scene as a combination of endmembers, weighted by their coverage fractions in the pixel or abundances. Over the last years, many algorithms have been presented to address the three main parts of the spectral unmixing chain: 1) estimation of the number of endmembers; 2) identification of the endmember signatures; and 3) estimation of the per-pixel fractional abundances. However, to date, there is no standardized tool that integrates these algorithms in a unified framework. In this letter, we present HyperMix, an open-source tool for spectral unmixing that integrates different approaches for spectral unmixing and allows building unmixing chains in graphical fashion, so that the end-user can define one or several spectral unmixing chains in fully configurable mode. HyperMix provides efficient implementations of most of the algorithms used for spectral unmixing, so that the tool automatically recognizes if the computer has a graphics processing unit (GPU) available and optimizes the execution of these algorithms in the GPU. This allows for the execution of spectral unmixing chains on large hyperspectral scenes in computationally efficient fashion. The tool is available online from http://hypercomphypermix. blogspot.com.es and has been validated with real hyperspectral scenes, providing state-of-the-art unmixing results.