Recent advances in airborne and spaceborne hyperspectral imaging technology have provided end users with rich spectral, spatial, and temporal information. They have made a plethora of applications feasible for the analysis of large areas of the Earth?s surface. However, a significant number of factors-such as the high dimensions and size of the hyperspectral data, the lack of training samples, mixed pixels, light-scattering mechanisms in the acquisition process, and different atmospheric and geometric distortions-make such data inherently nonlinear and complex, which poses major challenges for existing methodologies to effectively process and analyze the data sets. Hence, rigorous and innovative methodologies are required for hyperspectral image (HSI) and signal processing and have become a center of attention for researchers worldwide.

Hyperspectral image classification has been a vibrant area of research in recent years. Given a set of observations, i.e., pixel vectors in a hyperspectral image, classification approaches try to allocate a unique label to each pixel vector. However, the classification of hyperspectral images is a challenging task for a number of reasons, such as the presence of redundant features, the imbalance among the limited number of available training samples, and the high dimensionality of the data.

Convolutional neural networks (CNNs) exhibit good performance in image processing tasks, pointing themselves as the current state-of-the-art of deep learning methods. However, the intrinsic complexity of remotely sensed hyperspectral images still limits the performance of many CNN models. The high dimensionality of the HSI data, together with the underlying redundancy and noise, often makes the standard CNN approaches unable to generalize discriminative spectral-spatial features. Moreover, deeper CNN architectures also find challenges when additional layers are added, which hampers the network convergence and produces low classification accuracies. In order to mitigate these issues, this paper presents a new deep CNN architecture specially designed for the HSI data. Our new model pursues to improve the spectral-spatial features uncovered by the convolutional filters of the network. Specifically, the proposed residual-based approach gradually increases the feature map dimension at all convolutional layers, grouped in pyramidal bottleneck residual blocks, in order to involve more locations as the network depth increases while balancing the workload among all units, preserving the time complexity per layer. It can be seen as a pyramid, where the deeper the blocks, the more feature maps can be extracted. Therefore, the diversity of high-level spectral-spatial attributes can be gradually increased across layers to enhance the performance of the proposed network with the HSI data. Our experiments, conducted using four well-known HSI data sets and 10 different classification techniques, reveal that our newly developed HSI pyramidal residual model is able to provide competitive advantages (in terms of both classification accuracy and computational time) over the state-of-the-art HSI classification methods.

Linear spectral unmixing is a commonly accepted approach to mixed-pixel classification in hyperspectral imagery. This approach involves two steps. First, to find spectrally unique signatures of pure ground components, usually known as endmembers, and, second, to express mixed pixels as linear combinations of endmember materials. Over the past years, several algorithms have been developed for autonomous and supervised endmember extraction from hyperspectral data. Due to a lack of commonly accepted data and quantitative approaches to substantiate new algorithms, available methods have not been rigorously compared by using a unified scheme. In this paper, we present a comparative study of standard endmember extraction algorithms using a custom-designed quantitative and comparative framework that involves both the spectral and spatial information. The algorithms considered in this study represent substantially different design choices. A database formed by simulated and real hyperspectral data collected by the Airborne Visible and Infrared Imaging Spectrometer (AVIRIS) is used to investigate the impact of noise, mixture complexity, and use of radiance/reflectance data on algorithm performance. The results obtained indicate that endmember selection and subsequent mixed-pixel interpretation by a linear mixture model are more successful when methods combining spatial and spectral information are applied.

Spectral mixture analysis provides an efficient mechanism for the interpretation and classification of remotely sensed multidimensional imagery. It aims to identify a set of reference signatures (also known as endmembers) that can be used to model the reflectance spectrum at each pixel of the original image. Thus, the modeling is carried out as a linear combination of a finite number of ground components. Although spectral mixture models have proved to be appropriate for the purpose of large hyperspectral dataset subpixel analysis, few methods are available in the literature for the extraction of appropriate endmembers in spectral unmixing. Most approaches have been designed from a spectroscopic viewpoint and, thus, tend to neglect the existing spatial correlation between pixels. This paper presents a new automated method that performs unsupervised pixel purity determination and endmember extraction from multidimensional datasets; this is achieved by using both spatial and spectral information in a combined manner. The method is based on mathematical morphology, a classic image processing technique that can be applied to the spectral domain while being able to keep its spatial characteristics. The proposed methodology is evaluated through a specifically designed framework that uses both simulated and real hyperspectral data.