Christian Debes

Hyperspectral and LiDAR Data Fusion: Outcome of the 2013 GRSS Data Fusion Contest

The 2013 Data Fusion Contest organized by the Data Fusion Technical Committee (DFTC) of the IEEE Geoscience and Remote Sensing Society aimed at investigating the synergistic use of hyperspectral and Light Detection And Ranging (LiDAR) data. The data sets distributed to the participants during the Contest, a hyperspectral imagery and the corresponding LiDAR-derived digital surface model (DSM), were acquired by the NSF-funded Center for Airborne Laser Mapping over the University of Houston campus and its neighboring area in the summer of 2012. This paper highlights the two awarded research contributions, which investigated different approaches for the fusion of hyperspectral and LiDAR data, including a combined unsupervised and supervised classification scheme, and a graph-based method for the fusion of spectral, spatial, and elevation information.

Target Detection in Single- and Multiple-View Through-the-Wall Radar Imaging

A detector of targets behind walls and in enclosed structures is presented. The detector is applied to through-the-wall radar images obtained by wideband delay and sum beamforming. We consider the detection problem using single- and multiple-view imaging. The statistics of noise, clutter, and target images are examined and formulated using sample scenes. The effects of wall parameter errors on the image statistics are shown. An iterative detection scheme, which adapts itself to the image statistics, is presented. The proposed detection schemes are evaluated using real data.

Compressive sensing in through-the-wall radar imaging

High resolution through-the-wall radar imaging (TTWRI) demands wideband signals and large array apertures. Thus a vast amount of measurements is needed for a detailed reconstruction of the scene of interest. For practical TTWRI systems it is imperative to reduce the number of samples to cut down on hardware cost and/or acquisition time. This can be achieved by employing compressive sensing (CS). Existing approaches imply a point target assumption, which may not hold in practical applications. We apply a novel CS approach for TTWRI using the 2D discrete wavelet transform to sparsify images. In this fashion, we overcome the above stated limitation and are able to deal with extended targets. Experimental results show that high image qualities are obtained, similar to images generated using the full measurement set.

Adaptive Target Detection With Application to Through-the-Wall Radar Imaging

An adaptive detection scheme is proposed for radar imaging. The proposed detector is a postprocessing scheme derived for one-, two-, and three-dimensional data, and applied to through-the-wall imaging using synthetic aperture radar. The target image statistics depend on the target three-dimensional orientation and position. The statistics can also vary with the standoff distance of the imaging system because of the change in the corresponding scene image resolution. We propose an iterative target detection scheme for the cases in which no or partial a priori knowledge of the target image statistics is available. Properties of the proposed scheme, such as conditions of convergence and optimal configurations are introduced. The detector performance is examined under synthetic and real data. The latter is obtained using a synthetic aperture through-the-wall radar indoor imaging scanner implementing wideband delay and sum beamforming.

Target Discrimination and Classification in Through-the-Wall Radar Imaging

In this paper, a scheme for target discrimination and classification is proposed. The proposed scheme is applied to through-the-wall microwave images obtained by using a wideband radar implementing frequency-domain back-projection. We consider stationary targets where Doppler and change-detection based techniques are inapplicable. The proposed scheme applies image segmentation, followed by feature extraction. We map target returns to a feature space, where discrimination among different targets and clutter is performed. To achieve target-clutter discriminations independent of target location in range and cross-range, we use compensation methods to account for varying system resolution within the perimeter of the scene imaged. Real data collected using an indoor radar imaging scanner is used for validation of performance.

Ensemble Learning in Hyperspectral Image Classification: Toward Selecting a Favorable Bias-Variance Tradeoff

Automated classification of hyperspectral images is a fast growing field with numerous applications in the areas of security and surveillance, agriculture, urban management, and environmental monitoring. Although significant progress has been achieved in various aspects of hyperspectral classification (e.g., feature extraction, feature selection, classification, and post-classification processing), the problem has not been addressed so far from a bias-variance decomposition point of view. In this work, we introduce a consistent unified framework that jointly considers all steps in the hyperspectral image classification chain from a bias-variance decomposition perspective. Additionally, we show how state-of-the-art techniques in feature extraction, ensemble-based classification, and post-classification segmentation are related to the bias-variance tradeoff and how this relation can be used to improve classification accuracy. An important outcome of our analysis is that all the steps of the classification chain should be optimized jointly as this unified optimization can guide toward a more favorable bias-variance tradeoff. Experimental results of the proposed framework in the case of four hyperspectral datasets prove the effectiveness of our approach.

Compressive sensing and adaptive direct sampling in hyperspectral imaging

Hyperspectral imaging (HSI) is an emerging technique, which provides the continuous acquisition of electro-magnetic waves, usually covering the visible as well as the infrared light range. Many materials can be easily discriminated by means of their spectra rendering HSI an interesting method for the reliable classification of contents in a scene. Due to the high amount of data generated by HSI, effective compression algorithms are required. The computational complexity as well as the potentially high number of sensors render HSI an expensive technology. It is thus of practical interest to reduce the number of required sensor elements as well as computational complexity - either for cost or for energy reasons. In this paper, we present two different systems that acquire hyperspectral images with less samples than the actual number of pixels, i.e. in a low dimensional representation. First, a design based on compressive sensing (CS) is explained. Second, adaptive direct sampling (ADS) is utilized to obtain coefficients of hyperspectral images in the 3D (Haar) wavelet domain, simplifying the reconstruction process significantly. Both approaches are compared with conventionally captured images with respect to image quality and classification accuracy. Our results based on real data show that in most cases only 40% of the samples suffice to obtain high quality images. Using ADS, the rate can be reduced even to a greater extent. Further results confirm that, although the number of acquired samples is dramatically reduced, we can still obtain high classification rates.

Parametric Waveform Design Using Discrete Prolate Spheroidal Sequences for Enhanced Detection of Extended Targets

We propose a parametric waveform design approach for improved detection of extended targets embedded in uncorrelated signal-dependent clutter and noise, whose spectral densities are assumed to be known. Unlike canonical waveform design approaches, the transmit waveform is represented as a weighted linear combination of discrete prolate spheroidal sequences. In the optimization problem, the probability of detection is maximized with respect to the weighting factors of the associated discrete prolate spheroidal sequences under the transmit energy constraint. The weighting factors, which are resolved using a numerical method, lead directly to the desired transmit waveform in the time domain. In comparison to the canonical waveform design approaches, the extra step for time sequence synthesis is avoided and the loss in probability of detection produced therein is remedied. Simulation results demonstrate the improvement in the probability of detection for the proposed approach. However, the improvement comes at the cost of higher computational complexity.

Iterative target detection approach for Through-the-wall Radar Imaging

We consider the problem of target detection in Through-the-wall Radar Imaging when no a priori knowledge about the image statistics is available. An iterative approach which adapts itself to the unknown image statistics and thus allows for automatic target detection is presented. Two variants, based on 2D median filtering and morphological operations, are described in details. The proposed detection schemes are tested using experimental data, considering the problem of 3D reconstruction of a scene hidden behind a concrete wall.

Many Hands Make Light Work - On Ensemble Learning Techniques for Data Fusion in Remote Sensing

In this paper we discuss the use of ensemble methods in remote sensing. After a review of the relevant state of the art in ensemble learning - inside and outside the remote sensing community - we provide the necessary theoretical background of this research field. This includes a discussion of the bias/variance tradeoff that is a key notion in machine learning and especially ensemble learning. We provide a review of three of the most relevant and prominent techniques in ensemble learning, namely the Random Forest, Extra Trees and the Gradient Boosted Regression Trees algorithms. All algorithms are assessed in terms of their theoretical properties as well as applicability for remote sensing use cases. Finally, in the experimental section we compare their performance in challenging remote sensing datasets with different properties, while discussing again the reasons that the mechanics of each algorithm might give it an advantage under certain conditions.