F. Del Frate

Neural networks for oil spill detection using ERS-SAR data

A neural network approach for semi-automatic detection of oil spills in European remote sensing satellite-synthetic aperture radar (ERS-SAR) imagery is presented. The network input is a vector containing the values of a set of features characterizing an oil spill candidate. The classification performance of the algorithm has been evaluated on a data set containing verified examples of oil spill and look-alike. A direct analysis of the information content of the calculated features has been also carried out through an extended pruning procedure of the net.

Use of Neural Networks for Automatic Classification From High-Resolution Images

The effectiveness of multilayer perceptron (MLP) networks as a tool for the classification of remotely sensed images has been already proven in past years. However, most of the studies consider images characterized by high spatial resolution (around 15-30 m) while a detailed analysis of the performance of this type of classifier on very high resolution images (around 1-2 m) such as those provided by the Quickbird satellite is still lacking. Moreover, the classification problem is normally understood as the classification of a single image while the capabilities of a single network of performing automatic classification and feature extraction over a collection of archived images has not been explored so far. In this paper, besides assessing the performance of MLP for the classification of very high resolution images, we investigate on the generalization capabilities of this type of algorithms with the purpose of using them as a tool for fully automatic classification of collections of satellite images, either at very high or at high-resolution. In particular, applications to urban area monitoring have been addressed

SAR polarimetric features of agricultural areas

Abstract The potential of synthetic aperture radar (SAR) in monitoring soil and vegetation parameters is being evaluated in extensive investigations, worldwide. A significant experiment on this subject, the Multi-sensor Airborne Campaign (MAC 91), was carried out in the summer of 1991 on several sites in Europe, based on the NASA/JPL polarimetric synthetic aperture radar (AIR-SAR). The site of Montespertoli (Italy) was imaged three times during this campaign at P-, L-, and C-band and at different incidence angles between 20° and 50°. Calibrated full polarimetric data collected over the agricultural area of this site have been analysed and a critical analysis of the information contained in linear and circular co-polar and cross-polar data has also been carried out. Here a guideline for the formulation of crop discrimination algorithms is suggested. It has been found that P-band data are rather effective only in discriminating broad classes of agricultural landscape, while finer detail can be obtained by i...

Urban Mapping Using Coarse SAR and Optical Data: Outcome of the 2007 GRSS Data Fusion Contest

The 2007 data fusion contest that was organized by the IEEE Geoscience and Remote Sensing Data Fusion Technical Committee was dealing with the extraction of a land use/land cover maps in and around an urban area, exploiting multitemporal and multisource coarse-resolution data sets. In particular, synthetic aperture radar and optical data from satellite sensors were considered. Excellent indicators for mapping accuracy were obtained by the top teams. The best algorithm is based on a neural classification enhanced by preprocessing and postprocessing steps.

Retrieving soil moisture and agricultural variables by microwave radiometry using neural networks

Two neural network algorithms trained by a physical vegetation model are used to retrieve soil moisture and vegetation variables of wheat canopies during the whole crop cycle. The first algorithm retrieves soil moisture using L band, two polarizations and multiangular radiometric data, for each single date of radiometric acquisition. The algorithm includes roughness and vegetation effects, but does not require a priori knowledge of roughness and vegetation parameters for the specific field. The second algorithm retrieves vegetation variables using dual band, V polarization and multiangular radiometric data. This algorithm operates over the whole multitemporal data set. Previously retrieved soil moisture values are also used as a priori information. The algorithms have been tested considering measurements carried out in 1993 and 1996 over wheat fields at the INRA Avignon test site.

Pixel Unmixing in Hyperspectral Data by Means of Neural Networks

Neural networks (NNs) are recognized as very effective techniques when facing complex retrieval tasks in remote sensing. In this paper, the potential of NNs has been applied in solving the unmixing problem in hyperspectral data. In its complete form, the processing scheme uses an NN architecture consisting of two stages: the first stage reduces the dimension of the input vector, while the second stage performs the mapping from the reduced input vector to the abundance percentages. The dimensionality reduction is performed by the so-called autoassociative NNs, which yield a nonlinear principal component analysis of the data. The evaluation of the whole performance is carried out for different sets of experimental data. The first one is provided by the Airborne Hyperspectral Scanner. The second set consists of images from the Compact High-Resolution Imaging Spectrometer on board the Project for On-Board Autonomy satellite, and it includes multiangle and multitemporal acquisitions. The third set is represented by Airborne Visible/InfraRed Imaging Spectrometer measurements. A quantitative performance analysis has been carried out in terms of effectiveness in the dimensionality reduction phase and in terms of the accuracy in the final estimation. The results obtained, when compared with those produced by appropriate benchmark techniques, show the advantages of this approach.

Automatic Change Detection in Very High Resolution Images With Pulse-Coupled Neural Networks

A novel approach based on pulse-coupled neural networks (PCNNs) for image change detection is presented. PCNNs are based on the implementation of the mechanisms underlying the visual cortex of small mammals, and, with respect to more traditional NNs architectures, such as multilayer perceptron, own interesting advantages. In particular, they are unsupervised and context sensitive. This latter property may be particularly useful when very high resolution images are considered as, in this case, an object analysis might be more suitable than a pixel-based one. The qualitative and more quantitative results are reported. The performance of the algorithm has been evaluated on a pair of QuickBird images taken over the test area of Tor Vergata University, Rome.

Crop classification using multiconfiguration C-band SAR data

This paper reports on an investigation aimed at evaluating the performance of a neural-network based crop classification technique, which makes use of backscattering coefficients measured in different C-band synthetic aperture radar (SAR) configurations (multipolarization/multitemporal). To this end, C-band AirSAR and European Remote Sensing Satellite (ERS) data collected on the Flevoland site, extracted from the European RAdar-Optical Research Assemblage (ERA-ORA) library, have been used. The results obtained in classifying seven types of crops are discussed on the basis of the computed confusion matrices. The effect of increasing the number of polarizations and/or measurements dates are discussed and a scheme of interyear dynamic classification of five crop types is considered.

Application of neural algorithms for a real-time estimation of ozone profiles from GOME measurements

The thermal structure of trace gases, their distribution in the atmosphere, and their circulation mechanisms result from a complex interplay between radiative, physical, and dynamical processes. Neural-network algorithms can be a useful tool to face such complexities in retrieval operations. In this paper, their potentialities have been exploited to design real-time procedures for the estimation of vertical profiles of ozone concentration from spectral radiances measured by GOME, the first instrument of the European Space Agency capable of monitoring global distribution of ozone and other trace gases.

Comparing Statistical and Neural Network Methods Applied to Very High Resolution Satellite Images Showing Changes in Man-Made Structures at Rocky Flats

Parametric and nonparametric approaches to evaluate land-cover change detection using very high resolution (VHR) satellite imagery are applied to the analysis of the demolition of the Rocky Flats nuclear weapons facility located near Denver, CO. Both maximum-likelihood and neural network classifiers are used to validate a new parallel architecture which improves the accuracy when applied to VHR satellite imagery for the study of land-cover change between sequential satellite acquisitions. An enhancement of about 14% was found between the single-step classification and the new parallel architecture, confirming the advantage and the robust improvement obtained with this architecture regardless of the classification algorithm used. In this paper, we demonstrate and document the demolition and removal of hundreds of buildings taken down to bare soil between 2003 and 2005 at the Rocky Flats site.