Abdelaziz Kallel

Ant Colony Optimization for Image Regularization Based on a Nonstationary Markov Modeling

Ant colony optimization (ACO) has been proposed as a promising tool for regularization in image classification. The algorithm is applied here in a different way than the classical transposition of the graph color affectation problem. The ants collect information through the image, from one pixel to the others. The choice of the path is a function of the pixel label, favoring paths within the same image segment. We show that this corresponds to an automatic adaptation of the neighborhood to the segment form, and that it outperforms the fixed-form neighborhood used in classical Markov random field regularization techniques. The performance of this new approach is illustrated on a simulated image and on actual remote sensing images

Genetic particle filter application to land surface temperature downscaling

Thermal infrared data are widely used for surface flux estimation giving the possibility to assess water and energy budgets through land surface temperature (LST). Many applications require both high spatial resolution (HSR) and high temporal resolution (HTR), which are not presently available from space. It is therefore necessary to develop methodologies to use the coarse spatial/high temporal resolutions LST remote-sensing products for a better monitoring of fluxes at appropriate scales. For that purpose, a data assimilation method was developed to downscale LST based on particle filtering. The basic tenet of our approach is to constrain LST dynamics simulated at both HSR and HTR, through the optimization of aggregated temperatures at the coarse observation scale. Thus, a genetic particle filter (GPF) data assimilation scheme was implemented and applied to a land surface model which simulates prior subpixel temperatures. First, the GPF downscaling scheme was tested on pseudoobservations generated in the framework of the study area landscape (Crau-Camargue, France) and climate for the year 2006. The GPF performances were evaluated against observation errors and temporal sampling. Results show that GPF outperforms prior model estimations. Finally, the GPF method was applied on Spinning Enhanced Visible and InfraRed Imager time series and evaluated against HSR data provided by an Advanced Spaceborne Thermal Emission and Reflection Radiometer image acquired on 26 July 2006. The temperatures of seven land cover classes present in the study area were estimated with root-mean-square errors less than 2.4 K which is a very promising result for downscaling LST satellite products.

Surface Temperature Downscaling From Multiresolution Instruments Based on Markov Models

The spatial resolution of thermal infrared (TIR) instruments is often not sufficient for many applications, but this low resolution is counterbalanced by the high temporal resolution (for example the SEVIRI instrument onboard the European Meteosat 8 and 9 presents a spatial resolution of 3 km × 3 km at nadir and a temporal resolution of 15 mn). At kilometric scales, the observed pixel is generally heterogeneous in terms of land cover, and the temperatures of the different components may present large discrepancies. This paper presents a methodology to infer the temperatures of the various land cover/use classes composing a mixed pixel, from a whole pixel measurement. To infer intra-pixel temperature, information on the mixture within each low resolution pixel, e.g., the proportions of the land cover types derived from high spatial resolution imaging, account for a first constraint. However, in the absence of supplementary constraints, the number of unknown variables is greater than the number of measurements, and there is not uniqueness of the solution. Thus, we propose to take advantage of a priori knowledge provided by a land surface model (LSM), and of the temporal and spatial correlation features of the surface temperature. We propose a new downscaling method for estimating sub pixel signal. It applies to TIR data and: the inversion procedure provides as a result, the land surface temperature (LST) temporal series of each land cover/use class (called endmember) constituting the coarse resolution pixel. Three kinds of a priori information have been introduced, namely (1) a first guess subpixel temperature derived from the SEtHyS LSM; (2) a Markov Random Chain model of the surface temperature temporal dependencies from times t to t + 1 ; (3) a Markov Random Field model of the spatial dependencies between endmember temperatures. Then, the “Maximum A Posteriori” estimator provides the most likely endmember temperatures, given (1) the observed coarse resolution temperatures, (2) the composition of the pixels in terms of “land cover/land use,” and (3) the LSM first guess subpixel temperature values, (4) the a priori spatial and temporal Markov models. The performance of this new method has been first evaluated on simulated data (random Gaussian variables with means equal to endmember temperatures simulated using LSM). The method accuracy versus the observation errors and the number of endmembers was analyzed. The algorithm was then run on actual data, namely Meteosat SEVIRI Land Surface products acquired over an agricultural region in southeastern France. The performance evaluation was done by comparing the subpixel LST estimations to the high-resolution temperatures provided by the Terra/ASTER instrument. Due to the huge bias between sensors ( ~ 4 K), an intercalibration preprocessing between SEVIRI and ASTER was done. In this case, the achieved RMSE is lower than 2 K.

High spectral quality pansharpening approach based on MTF-matched filter banks

Pansharpening consists in merging a low-resolution multispectral image (MS) with a high spatial resolution panchromatic image (PAN) to produce a high resolution pansharpened MS image. It consists in enhancing spatially the low-resolution MS image by injecting the missing details provided by the high-resolution PAN image. In this paper, we propose a novel pansharpening approach based on decomposition/reconstruction processing using low-pass and high-pass filter banks. On the one hand, the low-pass approximation (taking into account the imaging system modulation transfer function MTF) of the pansharpened MS image is assumed to be equal to the original MS image in order to preserve the spectral quality. On the other hand, the high-pass filter allowing us to extract the high-frequency PAN details is designed as complementary filter to the low-pass one in order to provide perfect reconstruction in the ideal case. Quantitative assessment performed on reduced and full-resolution images are used to validate the proposed technique and compare it to state-of-art. Experimental results using Pléaides and GeoEye-1 data show that our proposed fusion schema outperforms the pre-existing methods visually as well as quantitatively.

Subpixel Temperature Estimation from Low Resolution Thermal Infrared Remote Sensing

The paper presents a new methodology adapted to the downscaling of low resolution IRT signals, i.e. the estimation of subpixel temperatures. The approach is based on the inversion of subpixel variables by multilinear regressions constrained by a priori temperature estimates provided by a physical land surface model. The method was developed and validated against a synthetic database built on model simulations. The precision of the methodology was analysed in terms of errors on the subpixel temperature estimations according to model and observation uncertainties. The impact of the number of observations used (i.e. the number of low resolution pixels considered) as well as the influence of the pixel heterogeneity were studied.

Multispectral image adaptive pansharpening based on wavelet transformation and NMDB approaches

In remote sensing, satellite images acquired from sensors provide either high spectral or high spatial resolution. The pansharpening framework is applied to remote-sensing systems to enhance the spatial quality of coarse-resolution multispectral (MS) images using information from panchromatic imagery. A multidecomposition pansharpening approach combining MS and panchromatic (PAN) images is proposed in this paper in order to bring the resolution of the low-resolution MS imagery up to that of the panchromatic images. In particular, multilevel wavelet decomposition is applied to the luminance-chrominance (YUV) space transformation (taking into account the red green and blue (RGB) bands) or extended-YUV transformation (taking into account the near infrared (NIR) band in addition to RGB) of the original MS channels, where geometrical details from the panchromatic image are introduced into the MS ones. Our approach contains a preprocessing step that consists of homogenizing the luminance, Y, and the panchromatic image reflectance, which are, respectively, a value integrated over a wavelength spectrum and simply a linear combination of some values in the same spectrum. Hence, as the panchromatic image reflectance and luminance reflectance correspond to different measurements, they do not correspond to the same physical information, which results in a difference between their histograms. Therefore, simple histogram matching is traditionally applied to panchromatic data to fit it to the luminance to avoid colour distortion after fusion. However, as the transformation concerns just the details of the panchromatic and MS images, a new scheme for matching the images which ignores the divergence between their approximations and maximizes the resemblance between their details is proposed in this work. After that, the fusion approach is applied, and in contrast to the original approach where the details of the fused MS luminance are set equal to the PAN luminance, we propose an adaptive approach in which just a part of the PAN details proportional to the similarity between the luminance and lowered PAN image is taken. Indeed, high-resolution geometrical details cannot be similar if the low-resolution details are not in good agreement. Besides, as the agreement between PAN and MS images depends on the occupation class, we have created a segmentation map and then computed separately the correlation in each region. Finally, the evaluation is done based on QuickBird and Pleiades-1A data sets showing rural and suburban areas. When compared to recent methods, our approach provides better results.

Application of ant colony optimization to image classification using a Markov model with non-stationary neighborhoods

In global classifications using Markov Random Field (MRF) modelling, the neighbourhood form is generally considered as independent of its location in the image. Such an approach may lead to classification errors for pixels located at the segment borders. The solution proposed here consists in relaxing the assumption of fixed-form neighbourhood. However this non-stationary neighbourhood modelling is useful only if an efficient heuristic can be defined to perform the optimization. Ant colony optimization (ACO) is currently a popular algorithm. It models upon the behavior of social insects for computing strategies: the information gathered by simple autonomous mobile agents, called ants, is shared and exploited for problem solving. Here we propose to use the ACO and to exploit its ability of self-organization. The ants collect information through the image, from one pixel to the others. The choice of the path is a function of the pixel label, favouring paths within a same image segment. We show that this corresponds to an automatic adaptation of the neighbourhood to the segment form. Performance of this new approach is illustrated on a simulated image and on actual remote sensing images, SPOT4/HRV, representing agricultural areas. In the studied examples, we found that it outperforms the fixed-form neighbourhood used in classical MRF classifications. The advantage of having a neighborhood shape that automatically adapts to the image segment clearly appears in these cases of images containing fine elements, lanes or thin fields, but also complex natural landscape structures.

Variational multiscale approach to LAI profile inversion based on LiDAR full waveform measurements

Light Detection and Ranging (LiDAR) is one of the important techniques of remote sensing that is currently attracting considerable interest in description of vegetation structure, obtaining information about the canopy height as well as the foliage density of vegetation layer profiles. In this study, we estimate one of the important structural properties of vegetation: the profile of leaf area index (LAI). It is retrieved based on airborne full waveform LiDAR data inversion. It consists of estimating the value of LAI each time an echo is recorded. The proposed approach approximates the scattering taking into account just the first pulse collision within the vegetation cover. Moreover, to be independent from both the scattering coefficient and the pulse energy, the ratio between two successive echoes is model instead of the echo itself. The proposed algorithm is based on Bayesian modeling. Indeed, we propose a variational approach having two components: data attachment (simulated waveform is close to actual one) and regularity (the LAI value slowly varies from a position to the next). The problem is finally written as a non-linear cost function to optimize. To solve it and overcome non-linearity, we propose a new multiscale gradient technique, which start by solving simpler problem and increases progressively the complexity until converging to the original problem. For evaluating our methods, we parametrize the DART model to simulate Lidar full waveform and vegetation scenes; one with Turbid medium and the other with imported 3D olive tree. The results are promising.

3-D vector radiative transfer for vegetation cover polarized BRDF modeling

In this study, we try to propose a 3-D Vector radiative transfer (VRT) model based on Monte Carlo (MC) forward ray tracing simulation to analyze vegetation canopy reflectance. Two kinds of scattering are taken into account: lambertian reflectance and transmittance as well as specular reflection. A new method to estimate the condition on leaf orientation to produce reflection is proposed, and its probability to occur, Pi, is computed. It was particularly shown that Pi is low, but when reflection happen, the corresponding radiance vector, Io, is very high. Such a phenomenon increases dramatically the MC variance and produces an irregular reflectance distribution function with a number of peaks corresponding to the specular effect. To be reduced, we propose a new MC approach that simulates reflection for each sunny leaf assuming that its orientation is random. It is shown in this case that the average canopy reflectance is proportional to Pi x Io. Our experimental results confirm that in forward direction, canopy polarizes horizontally light. In addition, they show that in inclined forward direction, diagonal polarization can be observed.

Iterative scheme for MS image pansharpening based on the combination of multi-resolution decompositions

ABSTRACT Image pansharpening in the remote-sensing domain may be defined as the technique of extracting high-resolution details from the panchromatic (PAN) image and injecting them into the multispectral (MS) one in a way to preserve the spectral signature and improve the spatial resolution. In this article, the authors propose an image fusion framework that tries to derive sharpened MS image such that: (i) when decimated taking into account the imagery system Modulation Transfer Function (MTF), it equals the original MS image; (ii) when decomposed using discrete wavelet transform (DWT), its geometrical details are those of the PAN image weighted by the compatibility PAN/MS. Indeed, MS sharpening is carried out in two steps. First, pre-pansharpened MS image is obtained using inverse DWT taking as approximations those of the upsampled original MS image and as details those of PAN (to reduce spectral distortion, PAN detail injection is performed proportionally to the similarity PAN/MS). Second, to satisfy (i) and to remove the PAN-MS disagreement, an iteration algorithm (alternatively corrects approximations and details) has been proposed. The proposed approach is designed in two versions inspired by the Generalized Laplacian Pyramid (GLP) and the Gram–Schmidt (GS) transformation, respectively. To validate our approach, Pléiades-1A, Geoeye-1, and Landsat Enhanced Thematic Mapper Plus (ETM+) images are tested. The results of qualitative and quantitative scores are presented and discussed. Compared to well-known techniques, our approach shows generally better results, particularly the one based on GLP formalism.