Remotely sensed hyperspectral imaging instruments are capable of collecting hundreds of images corresponding to different wave length channels for the same area on the surface of the Earth. For instance, NASA is continuously gathering high dimensional image data with instruments such as the Jet Propulsion Laboratory's Airborne Visible-Infrared Imaging Spectrometer (AVIRIS). This advanced sensor for Earth observation records the visible and near-infrared spectrum of the reflected light using more than 200 spectral bands, thus producing a stack of images in which each pixel (vector) is represented by a spectral signal that uniquely characterizes the underlying objects. The resulting data volume typically comprises several gigabytes per flight. In this article, we describe the state of the art in the devel opment and application of image and signal processing techniques for advanced information extraction from hyperspectral data. The article also describes new trends for efficient pro cessing of such data using parallel and distributed processing techniques in the context of time-critical applications.

Remotely sensed hyperspectral sensors provide image data containing rich information in both the spatial and the spectral domain, and this information can be used to address detection tasks in many applications. In many surveillance applications, the size of the objects (targets) searched for constitutes a very small fraction of the total search area and the spectral signatures associated to the targets are generally different from those of the background, hence the targets can be seen as anomalies. In hyperspectral imaging, many algorithms have been proposed for automatic target and anomaly detection. Given the dimensionality of hyperspectral scenes, these techniques can be time-consuming and difficult to apply in applications requiring real-time performance. In this paper, we develop several new parallel implementations of automatic target and anomaly detection algorithms. The proposed parallel algorithms are quantitatively evaluated using hyperspectral data collected by the NASA's Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) system over theWorld Trade Center (WTC) in New York, five days after the terrorist attacks that collapsed the two main towers in theWTC complex.

Multispectral images collected by the European Space Agency (ESA)'s Sentinel-2 satellite offer a powerful resource for accurately and efficiently mapping areas affected by the distribution of invasive aquatic plants. In this work, we use different spectral indices to detect invasive aquatic plants in the Guadiana river, Spain. Our methodology uses a convolutional neural network (CNN) as the baseline classifier and trains it using spectral indices calculated using different Sentinel-2 band combinations. Specifically, we consider the following spectral indices: with two bands, we calculate the normalized difference vegetation index (NDVI), normalized difference water index (NDWI), and normalized difference infrared index (NDII). With three bands, we calculate the red-green-blue (RGB) composite and the floating algae index (FAI). Finally, we also use four bands to calculate the bare soil index (BSI). In our results, we observed that CNNs can better map invasive aquatic plants in the considered case study when trained intelligently (using spectral indices) as compared to using all spectral bands provided by the Sentinel-2 instrument.

A model based on the known high correlation between photosynthetically active radiation (PAR) and global horizontal irradiance (GHI) was implemented to estimate PAR from GHI measurements in this present study. The model has been developed using satellite-derived GHI and PAR estimations. Both variables can be estimated using Kato bands, provided by Satellite Application Facility on Climate Monitoring (CM-SAF), and its ratio may be used as the variable of interest in order to obtain the model. The study area, which was located in mainland Spain, has been split by cluster analysis into regions with similar behavior, according to this ratio. In each of these regions, a regression model estimating PAR from GHI has been developed. According to the analysis, two regions are distinguished in the study area. These regions belong to the two climates dominating the territory: an Oceanic climate on the northern edge; and a Mediterranean climate with hot summer in the rest of the study area. The models obtained for each region have been checked against the ground measurements, providing correlograms with determination coefficients higher than 0.99.