Search

This paper presents a new method based on recent optimization technique to detect slow-moving landslides (<150m/year) in time series of displacement field generated by satellite images. Sparse optimization is applied simultaneously on the 3-D data set in space as well as in time. The proposed method takes into account the distinctive signal physical properties in space and time, by enforcing a sparse representation by blocks in space, but a continuing and monotonous representation in time of the landslides. As a result, we show that a mixed $\ell _{1,2}$ -norm is the most suitable norm for this detection problem, compared to pure $\ell _{1}$ -norm or $\ell _{2}$ -norm. Moreover, an outlier estimation step is included that sets apart the Gaussian noise from locally sparse processing errors in the data. The performance of this approach is tested by applying it both on synthetic data and on a time series of displacements fields over 16 dates in the Colca Valley, Peru. This detection presents commission and omission errors for landslides of 29% and 14%, respectively, using a medium resolution (10 m) data set of optical satellite images. It detects all important landslides, already known from field investigations. Moreover, it also points out other smaller or unknown landslides, increasing the existing slow-moving landslide inventory by +50%. [ABSTRACT FROM AUTHOR]

In real hyperspectral images, there exist variations within spectra of materials. The inherent spectral variability is one of the major obstacles for the successful hyperspectral image target detection. Although several hyperspectral image target detection algorithms have been proposed, there are few algorithms considering the spectral variability. Under such circumstances, in this paper, we propose a hyperspectral image target detection algorithm that is robust to the target spectral variability. The proposed algorithm utilizes an inequality constraint to guarantee that the outputs of target spectra, which vary in a certain set, are larger than one, so that these target spectra could be detected. The proposed algorithm transforms the target detection to a convex optimization problem and uses a kind of interior point method named barrier method to solve the formulated optimization problem effectively. Two synthetic hyperspectral images and two real hyperspectral images are used to conduct experiments. The experimental results demonstrate the proposed algorithm is robust to the target spectral variability and performs better than other classical algorithms. [ABSTRACT FROM AUTHOR]

This paper proposes a new method that solves the problem of inverse synthetic aperture radar image cross-range scaling by estimating the rotational velocity (RV) using the expansion–rotation–scale relationship between two range–Doppler (RD) images. This method is composed of three steps. The first step is preprocessing to construct 2-D Fourier transform images and initial polar-mapped images. In this step, two RD images are 2-D Fourier transformed to avoid the necessity of finding the rotation center; then, the transformed images are polar mapped with identical polar grids to convert rotation into translation in the \theta-direction only. The second step is a coarse search that finds the angular shift that provides the maximum correlation between two polar images. The angular shift found is used as the initial relative rotation angle (RA), and the initial relative scaling factor (RSF) is calculated using the RV which is equal to the angular shift divided by the time delay between the images. The third step is the optimization of the relative RA using the Nelder–Mead approach, with the RSF updated using the relative RA derived during each iteration. In simulations using a Mig-25 aircraft, composed of ideal point scatterers, and the measured data from a Boeing 747-400, the targets were properly rescaled in the range–cross-range domain due to the accurate estimation of the RV. [ABSTRACT FROM AUTHOR]

The linear mixture model is a convenient way to describe image pixels as a linear combination of pure spectra – termed endmembers. The fractional contribution from each endmember is calculated through inversion of the linear model. Despite the simplicity of the model, a nonnegativity constraint that is imposed on the fractions leads to an unmixing problem for which it is hard to find a closed analytical solution. Current solutions to this problem involve iterative algorithms, which are computationally intensive and not appropriate for unmixing large number of pixels. This paper presents an algorithm to build fuzzy membership functions that are equivalent to the least square solution of the fully constrained linear spectral unmixing problem. The efficiency and effectiveness of the proposed solution is demonstrated using both simulated and real data. [ABSTRACT FROM AUTHOR]

This paper proposes an improved subspace-based optimization method (SOM) by using a new construction method for the ambiguous part of the induced current. The new current construction method reduces not only the computational complexity of the current construction in every iteration of the optimization but also the computational complexity of the singular-value decomposition of the mapping from the induced current to scattered fields. Thus, the improved SOM is able to deal with the 3-D inverse-scattering problems. Numerical tests validate the algorithm. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel method that aims at assisting the ground-truth expert through an automatic detection of potentially mislabeled learning samples. This method is based on viewing the mislabeled sample detection issue as an optimization problem where it is looked for the best subset of learning samples in terms of statistical separability between classes. This problem is formulated within a genetic optimization framework, where each chromosome represents a candidate solution for validating/invalidating the learning samples collected by the ground-truth expert. The genetic optimization process guided by the joint optimization of two different criteria which are the maximization of a between-class statistical distance and the minimization of the number of invalidated samples. Experiments conducted on both simulated and real data sets show that the proposed ground-truth validation method succeeds in the following: 1) in detecting the mislabeled samples with a high accuracy, even when up to 30% of the learning samples are mislabeled, and 2) strongly limiting the negative impact of the mislabeling issue on the accuracy of the classification process. [ABSTRACT FROM AUTHOR]

Hyperspectral unmixing is a process to identify the constituent materials and estimate the corresponding fractions from the mixture. During the last few years, nonnegative matrix factorization (NMF), as a suitable candidate for the linear spectral mixture model, has been applied to unmix hyperspectral data. Unfortunately, the local minima caused by the nonconvexity of the objective function makes the solution nonunique, thus only the nonnegativity constraint is not sufficient enough to lead to a well-defined problem. Therefore, in this paper, two inherent characteristics of hyperspectral data, piecewise smoothness (both temporal and spatial) of spectral data and sparseness of abundance fraction of every material, are introduced to NMF. The adaptive potential function from discontinuity adaptive Markov random field model is used to describe the smoothness constraint while preserving discontinuities in spectral data. At the same time, two NMF algorithms, nonsmooth NMF and NMF with sparseness constraint, are used to quantify the degree of sparseness of material abundances. A gradient-based optimization algorithm is presented, and the monotonic convergence of the algorithm is proved. Three important facts are exploited in our method: First, both the spectra and abundances are nonnegative; second, the variation of the material spectra and abundance images is piece-wise smooth in wavelength and spatial spaces, respectively; third, the abundance distribution of each material is almost sparse in the scene. Experiments using synthetic and real data demonstrate that the proposed algorithm provides an effective unsupervised technique for hyperspectral unmixing. [ABSTRACT FROM AUTHOR]

In this paper, a new method is presented for a subpixelic land cover classification using both high-resolution structural information and coarse-resolution (CR) temporal information. To that aim, the linear mixture model is used for pixel disaggregation. It enables us to describe a CR time series in terms of the mixture of classes that are represented within each pixel. Then, the Bayes' rule and the maximum a posteriori criterion lead to the definition of an energy function whose minimum corresponds to the researched optimal classification. A theoretical analysis of the labeling errors that may be obtained using this energy function is provided, raising the main parameters for labeling performance. The optimal classification is computed by combining linear regressions and simulated annealing, leading to an unsupervised algorithm. The method is validated with numerical results obtained on two different agricultural scenes (i.e., the Danubian plain and the Coet Dan watershed). [ABSTRACT FROM AUTHOR]

Using an inverse technique for the array electromagnetic propagated resistivity logging (EPRL) data, a fine interpretation can be obtained about the resistivity distribution of an invaded profile. Generally, the Gauss-Newton algorithm (GN) is an efficient technique for the inverse problems; however, as a gradient-type optimization method, its accuracy and convergence depend strongly on the initial value. Even though this problem can be avoided by using a differential evolutionary algorithm (DE) as a global search optimization, it is computationally less efficient. In this paper, a hybrid inversion method of differential evolution has been developed to remove the strong dependence of the accuracy and convergence on the initial value. In this new method, an additional operation, which is designed with GN, is performed only to the best individual with a delay in the evolution processes of DE. Hence, the GN operation is used for the improvement of the convergence speed without leading to any decrease of the robustness of DE. The hybrid method is then extended to apply the inversion of EPRL data. Our results demonstrate its speed, steadiness, and efficiency of this hybrid method. [ABSTRACT FROM AUTHOR]

In the context of remote-sensing image analysis, Markov random field (MRF) models play an important role, due to their ability to integrate the use of contextual information associated with the image data in the analysis process, through the definition of suitable energy functions. However, especially when dealing with MRF models for supervised classification, the estimation of the parameters characterizing an MRF model is still an open issue, which is typically addressed by using time-expensive interactive "trial-and-error" procedures. In this paper, by focusing on a broad class of MRF models, in which the energy functions can be expressed as linear combinations of distinct contributions (e.g., representing different typologies of contextual interactions), an automatic supervised procedure for the optimization of the weight parameters of the combinations is proposed. Formulating the parameter-estimation problem as the solution of a system of linear inequalities, the problem is solved by extending to the present context the Ho-Kashyap algorithm, which is typically applied by the pattern-recognition community in computing linear discriminant functions for binary classification. The method is validated experimentally on three different (both single-date and multitemporal) datasets, which are endowed with distinct MRF models formalizing the spatial contextual information associated with a single remote-sensing image and/or the spatio-temporal contextual information associated with an image sequence. [ABSTRACT FROM AUTHOR]