1,721,185 research outputs found
Mapping the urban surface in a sub-pixel level with multispectral high resolution satellite imagery
No full textSpectral unmixing provides information on a sub-pixel level, which is extremely useful for studying the urban areas. Nevertheless, the high spatial diversity of man-made structures, the spectral variability of urban materials and the three-dimensional structure of the cities makes the sub-pixel mapping of urban surfaces one of the most challenging tasks of remote sensing science. In this study, these issues are addressed using an artificial neural network trained with endmember and non-linearly mixed synthetic spectra to inverse the pixel spectral mixture in high resolution multispectral imagery. A spectral library is built, consisting of endmember spectra collected from the images and synthetic spectra, produced using a non-linear model specifically developed for urban scenes. The proposed method is easily transferable to any city and fast in terms of computations, which makes it ideal for implementation with operational services for cities
On-Board Image Compression using Convolutional Autoencoder: Performance Analysis and Application Scenarios
No full textThe amount of raw data generated by instruments on board Earth Observation (EO) satellites is quite often more than what can be transmitted to the ground, so new advanced onboard processing procedures are required. Artificial Intelligence (AI) and Deep Learning (DL) can provide advanced information from EO data and thanks to specific hardware platforms these algorithms can be used also in space. We present here the Convolutional AutoEncoder (CAE)-based algorithm developed for on-board lossy image compression of the European Space Agency (ESA) Phi-Sat-2 mission. DL algorithms have already been successfully applied for image compression however performance degradation may occur in the context of a representative onboard environment. Therefore, besides analyzing the results for the local hardware environment, we investigate the performance variation for the on-board setting. Moreover, we introduced an applicative metric for the evaluation of the compression to assess the applicability of the reconstructed images for other tasks
Sentinel-2 change detection based on deep features
No full textIn this manuscript, we address the problem of change detection for Sentinel-2 data. The proposed method is based on deep features representation. First, multilevel convolutional neural network (CNN) features are extracted from input images acquired at different times. Then, euclidean distance is applied to generate dissimilarity map that indicate change probabilities of each pixel. Finally, bounding boxes corresponding the change areas can be obtained with clustering and an optimizing connected component labeling algorithm. Experiments on a manually annotated dataset demonstrate the feasibility and effectiveness of the proposed method
Convolutional Autoencoder Algorithm for On-Board Image Compression
No full textThe growing amount of data currently collected by earth observation satellites requires new processing procedures able to manage huge quantity of information. Among these, data reduction techniques represent a viable solution. In particular, data reduction on-board is significant because allows to save on-board storage space and bandwidth for data transmission to the ground. However, the algorithm used for compression must be able to preserve the key information contained in the acquired data, so that the applicability of the collected information is still guaranteed in the different fields of work. Artificial intelligence, and in particular deep learning, are well suited for this purpose because of their ability to extract valuable information from complex data.This work proposes a lossy image compression procedure based on a Convolutional Autoencoder (CAE) that can be performed on-board the satellite. The images acquired by the sensor can be compressed through the algorithm, stored, and sent to the ground where they are reconstructed, saving space and bandwidth for data transmission. The performance of the compression algorithm will be evaluated in terms of original-reconstructed image similarity and also with regard to the applicability of the reconstructed images to common applicative cases.The algorithm here proposed has been idealized and is currently in development in the context of the European Space Agency's (ESA) PhiSat-2 mission, that aims at demonstrating the advantages of the Artificial Intelligence (AI) on-board for Earth observation applications
Nonlinear Spectral Unmixing of Landsat Imagery for Urban Surface Cover Mapping
No full textThe high spatial diversity of man-made structures, the spectral variability of urban materials, and the three-dimensional structure of the cities make the mapping of urban surfaces using Earth Observation data, one of the most challenging tasks in remote sensing field. Spectral unmixing techniques can be proven useful with medium spectral resolution data to assess urban surface cover information on a subpixel level. Due to the large spectral variability of urban materials and the multiple scattering of light between surfaces in urban areas, multiple endmembers should be used, and the nonlinearity of spectral mixture should be accounted for. In this study, these issues are addressed using an artificial neural network trained with endmember and nonlinearly mixed synthetic spectra to inverse the pixel spectral mixture in Landsat imagery. A spectral library is built, consisting of endmember spectra collected from the image and synthetic spectra, produced using a nonlinear model specifically developed for urban areas. The method was tested over a case study, and the validation against higher resolution products revealed an accuracy of around 90% for all abundance maps. The comparison performed between the linear and nonlinear implementation of the method proved the need for including the nonlinear term, especially for improving the built-up abundance map. The proposed method is easily transferable to any city and fast in terms of computations, which makes it ideal for the implementation of operational urban services
Dynamic mapping of flood boundaries: current possibilities offered by earth observation system and cellular automata
Full text linkFlooding is an ongoing and complex problem in Italy. Very large floods caused inundation of the closest areas to the city centre in Rome in 1937, 1976, 1992, 2005 and most recently in 2008. Rome is located at the bottom of the Tiber River catchment, which cover an area of 16 000km2 5 . Intense precipitations struck the Tyrrhenian Sea side of the peninsula inducing a flood event on the Tiber and Aniene’s (Tiber’s tributary) basins – which captured the attention of the national and international media. Actually there is no validated model in operation for real-time flood forecasting. This research aims at comparing the Cellular Model CAESAR (Cellular Automation Evolutionary Slope And 10 River) application on a reach of the Aniene River with Earth Observation Systems. The main result expected is the prediction of future channel dynamics on short and medium time scale
A comparison of feature extraction methodologies applied on hyperspectral data
No full textIn this paper we present a comparative study for features extraction from hyperspectral data where the performance given by three different unsupervised techniques is considered. Among the three, one technique is rather innovative in the field of hyperspectral data processing and is based on neural networks algorithms. The study has been carried out for a set of hyper-spectral data collected by the Airborne Hyper-spectral line-Scanner radiometer (AHS) over a
test site in Northeast Germany. The results have been quantitatively evaluated and critically analyzed either in terms of their capability of representing the hyperspectral
data with a reduced number of components or
in terms of the accuracy obtained on the final derived produc
Hyperspectral and multi-angle CHRIS proba images for the generation of land cover maps
No full textAbstract—The small hyperspectral imager Compact High-Resolution Imaging Spectrometer (CHRIS) is the most important instrument for Earth observation included in the payload
of the European Space Agency Third-Part Mission Project for On-Board Autonomy (PROBA)-1 satellite. This instrument has
provided dozens of images in several target areas in the world, and a good number of acquisitions are available for the test site
of Frascati and Tor Vergata, Italy. This paper reports several results concerning the generation of thematic maps obtained from
CHRIS mode-3 imagery. The potential of the use of different configurations for the input vector exploiting multispectral, multiangular, and multitemporal measurements has been investigated, and the results have been evaluated and compared in terms of
accuracy in the classification. The core of the decision task has been developed using the neural network methodology. Indeed,
this approach is characterized by a particular ease in performing nonlinear mapping of a multidimensional set of inputs into the output one
Features extraction from hyperspectral images: an approach based on spectral, textural and spatial information applied to urban environments
No full textA method to automatically extract features from hyperspectral images is presented. The technique has been tested on two images: one from MIVIS airborne sensor and the other from AHS airborne sensors. The methodology has been organized in two parts: the first
one performed a cluster extraction based on Kohonen’s neural networks (unsupervised); the second used the pixels belonging to the extracted clusters to train a supervised neural network (supervised approach). Both
neural networks have been trained with spectral and textural parameters. Segmentation parameters have been
also considered to help road discrimination. The obtained results showed the advantages of automatic classification in urban areas with neural networks, achieving a satisfactory accuracy in feature extractio
- …
