Statistical classification of byperspectral data is challenging because the inputs are high in dimension and represent multiple classes that are sometimes quite mixed, while the amount and quality of ground truth in the form of labeled data is typically limited. The resulting classifiers are often unstable and have poor generalization. This work investigates two approaches based on the concept of random forests of classifiers implemented within a binary hierarchical multiclassifier system, with the goal of achieving improved generalization of the classifier in analysis of hyperspectral data, particularly when the quantity of training data is limited. A new classifier is proposed that incorporates bagging of training samples and adaptive random subspace feature selection within a binary hierarchical classifier (BHC), such that the number of features that is selected at each node of the tree is dependent on the quantity of associated training data. Results are compared to a random forest implementation based on the framework of classification and regression trees. For both methods, classification results obtained from experiments on data acquired by the National Aeronautics and Space Administration (NASA) Airborne Visible/Infrared Imaging Spectrometer instrument over the Kennedy Space Center, Florida, and by Hyperion on the NASA Earth Observing 1 satellite over the Okavango Delta of Botswana are superior to those from the original best basis BHC algorithm and a random subspace extension of the BHC.

/pdf/investigation-of-the-random-forest-framework-for-24k2es63h7.pdf

Investigation of the random forest framework for classification of hyperspectral data

Multi- and hyperspectral geologic remote sensing: A review

Geologists have used remote sensing data since the advent of the technology for regional mapping, structural interpretation and to aid in prospecting for ores and hydrocarbons. This paper provides a review of multispectral and hyperspectral remote sensing data, products and applications in geology. During the early days of Landsat Multispectral scanner and Thematic Mapper, geologists developed band ratio techniques and selective principal component analysis to produce iron oxide and hydroxyl images that could be related to hydrothermal alteration. The advent of the Advanced Spaceborne Thermal Emission and Reflectance Radiometer (ASTER) with six channels in the shortwave infrared and five channels in the thermal region allowed to produce qualitative surface mineral maps of clay minerals (kaolinite, illite), sulfate minerals (alunite), carbonate minerals (calcite, dolomite), iron oxides (hematite, goethite), and silica (quartz) which allowed to map alteration facies (propylitic, argillic etc.). The step toward quantitative and validated (subpixel) surface mineralogic mapping was made with the advent of high spectral resolution hyperspectral remote sensing. This led to a wealth of techniques to match image pixel spectra to library and field spectra and to unravel mixed pixel spectra to pure endmember spectra to derive subpixel surface compositional information. These products have found their way to the mining industry and are to a lesser extent taken up by the oil and gas sector. The main threat for geologic remote sensing lies in the lack of (satellite) data continuity. There is however a unique opportunity to develop standardized protocols leading to validated and reproducible products from satellite remote sensing for the geology community. By focusing on geologic mapping products such as mineral and lithologic maps, geochemistry, P-T paths, fluid pathways etc. the geologic remote sensing community can bridge the gap with the geosciences community. Increasingly workflows should be multidisciplinary and remote sensing data should be integrated with field observations and subsurface geophysical data to monitor and understand geologic processes.

Multi - and hyperspectral geologic remote sensing : a review

Advances in computing technology have fostered the development of new and powerful deep learning (DL) techniques, which have demonstrated promising results in a wide range of applications. Particularly, DL methods have been successfully used to classify remotely sensed data collected by Earth Observation (EO) instruments. Hyperspectral imaging (HSI) is a hot topic in remote sensing data analysis due to the vast amount of information comprised by this kind of images, which allows for a better characterization and exploitation of the Earth surface by combining rich spectral and spatial information. However, HSI poses major challenges for supervised classification methods due to the high dimensionality of the data and the limited availability of training samples. These issues, together with the high intraclass variability (and interclass similarity) –often present in HSI data– may hamper the effectiveness of classifiers. In order to solve these limitations, several DL-based architectures have been recently developed, exhibiting great potential in HSI data interpretation. This paper provides a comprehensive review of the current-state-of-the-art in DL for HSI classification, analyzing the strengths and weaknesses of the most widely used classifiers in the literature. For each discussed method, we provide quantitative results using several well-known and widely used HSI scenes, thus providing an exhaustive comparison of the discussed techniques. The paper concludes with some remarks and hints about future challenges in the application of DL techniques to HSI classification. The source codes of the methods discussed in this paper are available from: https://github.com/mhaut/hyperspectral_deeplearning_review .

Deep learning classifiers for hyperspectral imaging: A review

This paper describes a novel method to derive 3D hyperspectral information from lightweight snapshot cameras for unmanned aerial vehicles for vegetation monitoring. Snapshot cameras record an image cube with one spectral and two spatial dimensions with every exposure. First, we describe and apply methods to radiometrically characterize and calibrate these cameras. Then, we introduce our processing chain to derive 3D hyperspectral information from the calibrated image cubes based on structure from motion. The approach includes a novel way for quality assurance of the data which is used to assess the quality of the hyperspectral data for every single pixel in the final data product. The result is a hyperspectral digital surface model as a representation of the surface in 3D space linked with the hyperspectral information emitted and reflected by the objects covered by the surface. In this study we use the hyperspectral camera Cubert UHD 185-Firefly, which collects 125 bands from 450 to 950 nm. The obtained data product has a spatial resolution of approximately 1 cm for the spatial and 21 cm for the hyperspectral information. The radiometric calibration yields good results with less than 1% offset in reflectance compared to an ASD FieldSpec 3 for most of the spectral range. The quality assurance information shows that the radiometric precision is better than 0.13% for the derived data product. We apply the approach to data from a flight campaign in a barley experiment with different varieties during the growth stage heading (BBCH 52 – 59) to demonstrate the feasibility for vegetation monitoring in the context of precision agriculture. The plant parameters retrieved from the data product correspond to in-field measurements of a single date field campaign for plant height (R2 = 0.7), chlorophyll (BGI2, R2 = 0.52), LAI (RDVI, R2 = 0.32) and biomass (RDVI, R2 = 0.29). Our approach can also be applied for other image-frame cameras as long as the individual bands of the image cube are spatially co-registered beforehand.

Generating 3D hyperspectral information with lightweight UAV snapshot cameras for vegetation monitoring: From camera calibration to quality assurance

The Hyperion Imaging Spectrometer was the first imaging spectrometer to routinely acquire science-grade data from Earth orbit. Instrument performance was validated and carefully monitored through a combination of calibration approaches: solar, lunar, earth (vicarious) and atmospheric observations complemented by onboard calibration lamps and extensive prelaunch calibration. Innovative techniques for spectral calibration of space-based sensors were also tested and validated. Instrument performance met or exceeded predictions including continued operation well beyond the planned one-year program.

D. Beiso

Papers

Hyperion, a space-based imaging spectrometer