Search

Extinction profile (EP) is an effective feature extraction method which can well preserve the geometrical characteristics of a hyperspectral image (HSI) and by extracting the EP from first three independent components (ICs) of an HSI, three correlated and complementary groups of EP features can be constructed. In this paper, an EPs fusion (EPs-F) strategy is proposed for HSI classification by exploring spatial-spectral information within and among three EP features. In general, the EPs-F method includes two stages. In the first stage, within each EP feature, a superpixel-based composite kernel strategy is proposed to adaptively fuse the spatial information of EP and the spectral feature of HSI. Then, the obtained adaptive composite kernel is used to create a classification map for each EP. In the second stage, decision fusion is further applied on different classification maps to create the final classification result. Experiments on two real HSIs verify the effectiveness of the proposed EPs-F algorithm.

To improve the classification of hyperspectral images, this paper proposes an approach for multi-sensor data fusion of LiDAR and hyperspectral data using extinction profiles and Orthogonal Total Variation Component Analysis (OTVCA). Results on the benchmark Houston data indicate the superior performance of the proposed approach compared to other approaches used in the experiments based on classification accuracies.

The side-looking imaging geometry of synthetic aperture radar (SAR) causes inevitable layover in SAR images. Separating the contributions from different scatterers has been the fundamental for many applications. It is typically solved by explicit inversion of the SAR imaging model to retrieve the scattering profile along the mixed dimension (elevation), which is otherwise known as SAR tomography. This paper proposed a robust blind scatterer separation method to demix the layovered scatterers, avoiding the computationally expensive tomographic inversion. We demonstrate that the state-of-the-art principle component decomposition-based methods are heavily influenced by the nonergodicity of the selected samples, especially in urban area, such as point scatterers appearing often on facades. The proposed method is shown to be more robust than the state-of-the-art. Real data example shows that the proposed method outperforms the state-of-the-art by a factor of three in terms of the accuracy of the retrieved phase.

In this paper, we present a method for regularizing noisy 3D reconstructions, which is especially well suited for scenes containing planar structures like buildings. At horizontal structures, the input model is divided into slices and for each slice, an inside/outside labeling is computed. With the outlines of each slice labeling, we create an irregularly shaped volumetric cell decomposition of the whole scene. Then, an optimized inside/outside labeling of these cells is computed by solving an energy minimization problem. For the cell labeling optimization we introduce a novel smoothness term, where lines in the images are used to improve the regularization result. We show that our approach can take arbitrary dense meshed point clouds as input and delivers well regularized building models, which can be textured afterwards.

The launch of the wide-swath SAR missions with short repeat-pass cycles, such as Sentinel-1, will soon lead to an unprecedented large InSAR data archive. Time-series analysis on the rapidly growing data will thus become computationally demanding for a systematic monitoring of earth surface deformation. As the state-of-the-art approach in InSAR time-series analysis, the distributed scatterer interferometric (DSI) techniques shall adapt agile processing schemes to deal with the upcoming big data; an aspect to which limited attention has been dedicated so far. In this contribution, a sequential DSI scheme is proposed to address this demand. Based on SAR data reduction, the scheme allows for batch processing with negligible performance loss compared to the Cramér-Rao Lower Bound. The performance of the proposed sequential estimator is compared to the current DSI algorithms under two contradicting coherence scenarios. The application of the proposed sequential estimator to the real C- and L-band data is ongoing and will be presented in the final paper.

The use of fully polarimetric SAR data for oil spill detection is relatively new and shows great potential for operational off-shore platform monitoring. Greater availability of these kind of SAR data calls for a development of time critical processing chain capable of detecting and distinguishing oil spills from ‘look-alikes’. This paper describes the development of an automated Near Real Time (NRT) oil spill detection processing chain based on quad-pol RADARSAT-2 (RS-2) and quad-pol TerraSAR-X (TS-X) images, wherein we use polarimetric features (e.g. Lexicographic and Pauli Based features) to characterize oil spills and look-alikes. Numbers of TS-X and RS-2 images have been acquired over known off-shore platforms along with some near coincident (spatially and temporally) acquisition. Ten polarimetric feature parameters were extracted from different types of oil (e.g. crude oil, emulsion etc) and ‘look-alike’ (e.g. plant oil, met-oceanic phenomenon etc) spots and divided into training and validation dataset seperately for TerraSAR-X RADARSAT-2. Extracted features were then used for training and validation of a pixel based Artificial Neural Network (ANN) classifier. Initial performance estimation was carried out for the proposed methodology in order to evaluate its suitability for NRT operational service. Mutual information contents among extracted features were assessed and feature parameters were ranked according to their ability to discriminate between oil spills and look- alikes. Polarimetric features such as Scattering Diversity and Pauli-based features proved to be more discriminative than other polarimetric features.

Advanced Interferometric SAR (InSAR) technique, namely, Persistent Scatterer Interferometry (PSI), allows long term deformation time series analysis with millimeter accuracy. Reference network arcs construction, arcs estimation and integration for PSs are an important step in PSI. In rural regions, low density of PSs leads to separate clusters during reference network construction. Also, in case of wide-area PSI using ERS-1/2 or Sentinel-1 data, the computational load can be very high. Due to this, the reference network processing is usually divided into overlapping blocks and merged later. This can however lead to spatial error propagation. This paper presents algorithms for improving the reference network in wide-area PSI, with a focus on non-urban areas.

This paper reports a study aimed to detect changes at the northern part of the Vatnajokull glacier, Iceland, by exploiting a stack of Digital Elevation Models (DEMs) generated with Synthetic Aperture Radar (SAR) imagery. The stack is covering the Bardarbunga volcanic system, subject to large topographical variations during the 2014–2015 eruption. In particular, the collapse of the caldera and the restructuring of the glacier, with for instance the formation of new cauldrons, is well represented by the DEM stack, and a quantitative and a geophysical analysis of the results becomes feasible.