Search

Background Diagnosis of schizophrenia (SCZ) is made exclusively clinically, since specific biomarkers that can predict the disease accurately remain unknown. Machine learning (ML) represents a promising approach that could support clinicians in the diagnosis of mental disorders. Objectives A systematic review, according to the PRISMA statement, was conducted to evaluate its accuracy to distinguish SCZ patients from healthy controls. Methods We systematically searched PubMed, Embase, MEDLINE, PsychINFO and the Cochrane Library through December 2018 using generic terms for ML techniques and SCZ without language or time restriction. Thirty-five studies were included in this review: eight of them used structural neuroimaging, twenty-six used functional neuroimaging and one both, with a minimum accuracy >60% (most of them 75–90%). Sensitivity, Specificity and accuracy were extracted from each publication or obtained directly from authors. Results Support vector machine, the most frequent technique, if associated with other ML techniques achieved accuracy close to 100%. The prefrontal and temporal cortices appeared to be the most useful brain regions for the diagnosis of SCZ. ML analysis can efficiently detect significantly altered brain connectivity in patients with SCZ (eg, default mode network, visual network, sensorimotor network, frontoparietal network and salience network). Conclusion The greater accuracy demonstrated by these predictive models and the new models resulting from the integration of multiple ML techniques will be increasingly decisive for early diagnosis and evaluation of the treatment response and to establish the prognosis of patients with SCZ. To achieve a real benefit for patients, the future challenge is to reach an accurate diagnosis not only through clinical evaluation but also with the aid of ML algorithms.

Nowadays, modern Earth Observation systems continuously generate huge amounts of data. A notable example is the Sentinel-2 Earth Observation mission, developed by the European Space Agency as part of the Copernicus Programme, which supplies images from the whole planet at high spatial resolution (up to 10 m) with unprecedented revisit time (every 5 days at the equator). In this data-rich scenario, the remote sensing community is showing a growing interest toward modern supervised machine learning techniques (e.g., deep learning) to perform information extraction, often underestimating the need for reference data that this framework implies. Conversely, few attention is being devoted to the use of network analysis techniques, which can provide a set of powerful tools for unsupervised information discovery, subject to the definition of a suitable strategy to build a network-like representation of image data. The aim of this work is to provide clues on how Satellite Image Time Series can be profitably represented using complex network models, by proposing a methodology to build a multilayer network from such data. This is the first work to explore the possibility to exploit this model in the remote sensing domain. An example of community detection over the provided network in a real-case scenario for the mapping of complex land use systems is also presented, to assess the potential of this approach.

International audience; The huge amount of data currently produced by modern Earth Observation (EO) missions has allowed for the design of advanced machine learning techniques able to support complex Land Use/Land Cover (LULC) mapping tasks. The Copernicus programme developed by the European Space Agency provides, with missions such as Sentinel-1 (S1) and Sentinel-2 (S2), radar and optical (multi-spectral) imagery, respectively, at 10 m spatial resolution with revisit time around 5 days. Such high temporal resolution allows to collect Satellite Image Time Series (SITS) that support a plethora of Earth surface monitoring tasks. How to effectively combine the complementary information provided by such sensors remains an open problem in the remote sensing field. In this work, we propose a deep learning architecture to combine information coming from S1 and S2 time series, namely TWINNS (TWIn Neural Networks for Sentinel data), able to discover spatial and temporal dependencies in both types of SITS. The proposed architecture is devised to boost the land cover classification task by leveraging two levels of complementarity, i.e., the interplay between radar and optical SITS as well as the synergy between spatial and temporal dependencies. Experiments carried out on two study sites characterized by different land cover characteristics (i.e., the Koumbia site in Burkina Faso and Reunion Island, a overseas department of France in the Indian Ocean), demonstrate the significance of our proposal.

Images provided by the ESA Sentinel-2 mission are rapidly becoming the main source of information for the entire remote sensing community, thanks to their unprecedented combination of spatial, spectral and temporal resolution, as well as their associated open access policy. Due to a sensor design trade-off, images are acquired (and delivered) at different spatial resolutions (10, 20 and 60 m) according to specific sets of wavelengths, with only the four visible and near infrared bands provided at the highest resolution (10 m). Although this is not a limiting factor in general, many applications seem to emerge in which the resolution enhancement of 20 m bands may be beneficial, motivating the development of specific super-resolution methods. In this work, we propose to leverage Convolutional Neural Networks (CNNs) to provide a fast, upscalable method for the single-sensor fusion of Sentinel-2 (S2) data, whose aim is to provide a 10 m super-resolution of the original 20 m bands. Experimental results demonstrate that the proposed solution can achieve better performance with respect to most of the state-of-the-art methods, including other deep learning based ones with a considerable saving of computational burden.

International audience; A major issue affecting optical imagery is the presence of clouds. The need of cloud-free scenes at specific date is crucial in a number of operational monitoring applications. On the other hand, the cloud-insensitive SAR sensors are a solid asset and they provide orthogonal information with respect to optical satellite, that enable the retrieval of information lost in optical images due to cloud cover. In the context of an increasing availability of both optical and SAR images, thank to the Sentinel constellation, we propose a deep learning method to reconstruct (gap-fill) optical data, polluted by cloud phenomena, exploiting multi-temporal SAR and optical images.

[Departement_IRSTEA]Territoires [TR1_IRSTEA]SYNERGIE [Axe_IRSTEA]TETIS-SISO [Axe_IRSTEA]TETIS-ATTOS [ADD1_IRSTEA]Dynamiques spatiales d'anthropisation; International audience; Nowadays, modern Earth Observation systems continuously generate huge amounts of data. A notable example is represented by the Sentinel-2 mission, which provides images at high spatial resolution (up to 10m) with high temporal revisit period (every 5 days), which can be organized in Satellite Image Time Series (SITS). While the use of SITS has been proved to be beneficial in the context of Land Use/Land Cover (LULC) map generation, unfortunately, machine learning approaches commonly leveraged in remote sensing field fail to take advantage of spatio-temporal dependencies present in such data. Recently, new generation deep learning methods allowed to significantly advance research in this field. These approaches have generally focused on a single type of neural network, i.e., Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs), which model different but complementary information: spatial autocorrelation (CNNs) and temporal dependencies (RNNs). In this work, we propose the first deep learning architecture for the analysis of SITS data, namely \method{} (DUal view Point deep Learning architecture for time series classificatiOn), that combines Convolutional and Recurrent neural networks to exploit their complementarity. Our hypothesis is that, since CNNs and RNNs capture different aspects of the data, a combination of both models would produce a more diverse and complete representation of the information for the underlying land cover classification task. Experiments carried out on two study sites characterized by different land cover characteristics (i.e., the \textit{Gard} site in France and the \textit{Reunion Island} in the Indian Ocean), demonstrate the significance of our proposal.

Radar and Optical Satellite Image Time Series (SITS) are sources of information that are commonly employed to monitor earth surfaces for tasks related to ecology, agriculture, mobility, land management planning and land cover monitoring. Many studies have been conducted using one of the two sources, but how to smartly combine the complementary information provided by radar and optical SITS is still an open challenge. In this context, we propose a new neural architecture for the combination of Sentinel-1 (S1) and Sentinel-2 (S2) imagery at object level, applied to a real-world land cover classification task. Experiments carried out on the Reunion Island, a overseas department of France in the Indian Ocean, demonstrate the significance of our proposal.

Sentinel-2 data represent a rich source of information for the community due to the free access and to the temporal-spatial coverage assured. However, some of the spectral bands are sensed at reduced resolution due to a compromise between technological limitations and Copernicus program's objectives. For this reason in this work we present a new super-resolution method based on Convolutional Neural Networks (CNNs) to rise the resolution of the short wave infra-red (SWIR) band from 20 to 10 meters, that is the highest resolution provided. This is accomplished by fusing the target band with the finer-resolution ones. The proposed solution compares favourably against several alternative methods according to different quality indexes. In addition we have also tested the use of the super-resolved band from an applicative perspective by detecting water basins through the Modified Normalized Difference Water Index (MNDWI).

International audience; Mapping winter vegetation quality is a challenging problem in remote sensing. This is due to cloud coverage in winter periods, leading to a more intensive use of radar rather than optical images. The aim of this letter is to provide a better understanding of the capabilities of Sentinel-1 radar images for winter vegetation quality mapping through the use of deep learning techniques. Analysis is carried out on a multitemporal Sentinel-1 data over an area around Charentes-Maritimes, France. This data set was processed in order to produce an intensity radar data stack from October 2016 to February 2017. Two deep recurrent neural network (RNN)-based classifiers were employed. Our work revealed that the results of the proposed RNN models clearly outperformed classical machine learning approaches (support vector machine and random forest).

Sensitivity to weather conditions, and specially to clouds, is a severe limiting factor to the use of optical remote sensing for Earth monitoring applications. A possible alternative, is to resort to weather-insensitive synthetic aperture radar (SAR) images. However, in many real-world applications, critical decisions are made based on some informative spectral features, such as water, vegetation or soil indices, which cannot be extracted from SAR images. In the absence of optical sources, these data must be estimated. The current practice is to perform linear interpolation between data available at temporally close time instants. In this work, we propose to estimate missing spectral features through data fusion and deep-learning. Several sources of information are taken into account - optical sequences, SAR sequences, DEM - so as to exploit both temporal and cross-sensor dependencies. Based on these data, and a tiny cloud-free fraction of the target image, a compact convolutional neural network (CNN) is trained to perform the desired estimation. To validate the proposed approach, we focus on the estimation of the normalized difference vegetation index (NDVI), using coupled Sentinel-1 and Sentinel-2 time-series acquired over an agricultural region of Burkina Faso from May to November 2016. Several fusion schemes are considered, causal and non-causal, single-sensor or joint-sensor, corresponding to different operating conditions. Experimental results are very promising, showing a significant gain over baselines methods according to all performance indicators.

A new technique for the segmentation of single- and multiresolution (MR) remote sensing images is proposed. To guarantee the preservation of details at fine scales, edge-based watershed is used, with automatically generated markers that help in limiting oversegmentation. For MR images, the panchromatic and multispectral components are processed independently, extracting both the edge maps and the morphological and spectral markers that are eventually fused at the highest resolution, thus avoiding any information loss induced by pansharpening. Numerical results on object layer extraction and simple classification tasks prove the proposed techniques to provide accurate segmentation maps, which preserve fine details and, contrary to state-of-the-art products, can single out objects equally well at very different scales.

We present the enrichment of the Prague Texture Segmentation Data-Generator and Benchmark (PTSDB) to include the assessment of the remote sensing (RS) image segmenters. The PTSDB tool is a Web-based (http://mosaic.utia.cas.cz) service designed for real-time performance evaluation, mutual comparison, and ranking of various supervised or unsupervised static or dynamic image segmenters. PTSDB supports rapid verification and development of new segmentation approaches. The RS datasets contain ten spectral Advanced Land Imager (ALI) satellite images, their RGB subsets, and very-high-resolution GeoEye RGB images, with optional additive-noise-resistance checking. Alternative setting options allow us to also test scale, rotation, or illumination invariance. The meaningfulness of the newly proposed dataset is demonstrated by testing and comparing several RS segmentation algorithms, and showing that the benchmark figures provide a solid framework for the fair and critical comparison among different techniques.

We propose a new synthetic aperture radar (SAR) despeckling technique based on nonlocal filtering and driven by a coregistered optical image. A preliminary homogeneous versus heterogeneous classification of the image is used to decide where the optical guide can be safely used, thus preventing any distortion of the SAR geometry. Even in regions where the use of optical data is enabled, despeckling is carried out exclusively in the SAR domain, and the optical guide is used only to improve the predictor selection in nonlocal filtering and, hence, in the estimation process. Experiments on real-world imagery confirm the potential of the proposed approach.

Since optical remote sensing images are useless in cloudy conditions, a possible alternative is to resort to synthetic aperture radar (SAR) images. However, many conventional techniques for Earth monitoring applications require specific spectral features which are defined only for multispectral data. For this reason, in this work we propose to estimate missing spectral features through data fusion and deep learning, exploiting both temporal and cross-sensor dependencies on Sentinel-1 and Sentinel-2 time-series. The proposed approach, validated focusing on the estimation of the normalized difference vegetation index (NDVI), shows very interesting results with a large performance gain over the linear regression approach according to several accuracy indicators.

Nowadays, modern earth observation programs produce huge volumes of satellite images time series (SITS) that can be useful to monitor geographical areas through time. How to efficiently analyze such kind of information is still an open question in the remote sensing field. Recently, deep learning methods proved suitable to deal with remote sensing data mainly for scene classification (i.e. Convolutional Neural Networks - CNNs - on single images) while only very few studies exist involving temporal deep learning approaches (i.e Recurrent Neural Networks - RNNs) to deal with remote sensing time series. In this letter we evaluate the ability of Recurrent Neural Networks, in particular the Long-Short Term Memory (LSTM) model, to perform land cover classification considering multi-temporal spatial data derived from a time series of satellite images. We carried out experiments on two different datasets considering both pixel-based and object-based classification. The obtained results show that Recurrent Neural Networks are competitive compared to state-of-the-art classifiers, and may outperform classical approaches in presence of low represented and/or highly mixed classes. We also show that using the alternative feature representation generated by LSTM can improve the performances of standard classifiers.

We propose a new approach for remote sensing data exploration, based on a tight human-machine interaction. The analyst uses a number of powerful and user-friendly image classification/segmentation tools to obtain a satisfactory thematic map, based only on visual assessment and expertise. All processing tools are in the framework of the tree-structured MRF model, which allows for a flexible and spatially adaptive description of the data. We test the proposed approach for the exploration of multitemporal COSMO-SkyMed data, that we appropriately registered, calibrated, and filtered, obtaining a performance that is largely superior, in both subjective and objective terms, to that of comparable noninteractive methods.

In this paper, we propose a new algorithm for the segmentation of multiresolution remote-sensing images, which fits into the general split-and-merge paradigm. The splitting phase singles out clusters of connected regions that share the same spatial and spectral characteristics. These clusters are then regarded as atomic elements of more complex structures, particularly textures, that are gradually retrieved during the merging phase. The whole process is based on a recently developed hierarchical model of the image, which accurately describes its textural properties. In order to reduce the computational burden and preserve contours at the highest spatial definition, the algorithm works on the high-resolution panchromatic data first, using low-resolution full spectral information only at a later stage to refine the segmentation. It is completely unsupervised, with just a few parameters set at the beginning, and its final product is not a single segmentation map but rather a sequence of nested maps which provide a hierarchical description of the image, at various scales of observations. The first experimental results, obtained on a remote-sensing Ikonos image, are very encouraging and confirm the algorithm potential.

In this paper a new object-oriented segmentation method for high-resolution remote sensing images is proposed. To limit computational complexity, a preliminary superpixel representation of the image is obtained by means of a suitable watershed transform. Then, a region adjacency graph is associated with the superpixels, with edge weights accounting for region similarity/dissimilarity. The final segmentation is then obtained by means of a graph-cutting approach, following a correlation clustering formulation. The optimal cut can be obtained by solving a Integer Linear Programming (ILP) problem, whose complexity, however, grows rapidly with the image size. Much faster near-optimal solutions are obtained, here, with a greedy solution. Experiments on a real-world high-resolution remote sensing image prove the potential of the approach.

We address the problem of SAR despeckling by resorting to nonlocal filtering guided by an optical image. In fact, given the increasing availability of remote-sensing optical images, it makes perfect sense trying to use them to improve the performance of despeckling. Our technique exploits the optical image to reliably estimate the statistical similarity among pixels, which is used to evaluate the weights of nonlocal filtering. Optical data are not used to estimate SAR values, but only to guide the overall process. In addition, they are discarded altogether in regions where SAR and optical images present different local geometries, identified by a preliminary classification step, avoiding thus any additional distortion. Experimental results show the proposed approach to provide images of better quality than state-of-the-art conventional filters.

Reliable segmentation of SAR images requires some forms of user supervision: we resort here to the interactive version of the Tree-Structured Markov Random Field (TS-MRF) segmentation suite. The TS-MRF model, and the associated segmentation tool, provide a flexible and spatially adaptive description of the data. In the interactive version, the user can drive the process based on the inspection of the current result, deciding step-by-step which direction to take, and switching from one segmentation modality to another. Experiments with the segmentation and classification of multitemporal SAR images prove the potential of the interactive approach and of the TS-MRF tool.

Recursive tree-structured segmentation is a powerful tool to deal with the non-stationary nature of images. By fitting model parameters to each region/class under analysis one can adapt the segmentation algorithm to the local image statistics, thus improving accuracy. However, a single model/segmenter cannot fit regions with wildly different nature, and one should be allowed to select in a suitable library the tool most suited to the local statistics. In this paper, we implement this dynamic segmentation/classification paradigm, using two segmenters, based on spectral and textural properties, respectively, and defining suitable rules for switching model locally. Experiments on remote-sensing mosaics show that the multiple-model dynamic algorithm largely outperforms comparable single-model segmenters.

A new watershed-based technique is proposed for the segmentation of multiresolution remote-sensing images. These images are composed by a high-resolution panchromatic band and a low-resolution multispectral set. To achieve a segmentation with the high resolution of the panchromatic image and the high accuracy granted by the spectral information, the two components are processed jointly, using both spectral and morphological properties. In addition, a fully automatic marker generation procedure is introduced to reduce the oversegmentation typical of watershed methods. Experiments on WorldView-2 multiresolution images demonstrate the potential of the technique.

Quality of experience in future home devices is foreseen to drastically increase, with the increase in image resolution. Displays with a horizontal resolution of 4K pixels are already appearing, and 8K Super-HiVision has already been demonstrated. Currently, only spatial upsampling of conventional HD format is performed to match the resolution of such displays. In this paper, we propose a novel method for high-quality up-conversion of legacy visual content in order to fit the screen resolution. More precisely, by assuming that we have various versions of the same image at standard resolution, encoded with different parameters, we try to reconstruct the high resolution image with higher quality than a simple interpolation. To this end, we adopt a variational formulation of the problem and construct a convex constrained criterion that incorporates both a fidelity term (linked to the acquisition process) and some a priori information. A recent primal-dual proximal algorithm is used to solve the associated minimization problem and simulation results show the good performance and behavior of the proposed approach.

Segmentation of remote sensing images is challenging task not only for the intrinsic complexity of imaged scenes but also for their multiple-scale interpretation. Hierarchical techniques, which provide a sequence of nested segmentation maps for the scene at different scales are therefore very promising. The Texture fragmentation and reconstruction technique (TFR) carries out a hierarchical image segmentation based mainly on textural image properties. In this work we consider its improved version, Recursive-TFR, based on recursive binary segmentation, assess its performance experimentally on a suitable segmentation benchmark, prove its potential for remore-sensing imagery and point out promising developments.

The segmentation of very high resolution (VHR) images portraying complex urban scenarios is a rather challenging problem. In particular, great attention must be devoted to preserve fine man-made details, of major interest for most user applications. For this reason, edge-based segmentation methods are likely preferable to region-based methods. The latter, in fact, e.g. [1], [2], succeed in taking into account long range interactions and hence perform typically well in terms of “global” accuracy, but exhibit a lower “local” accuracy with respect to former, [3].

International audience; High resolution satellite images provided by the last generation sensors significantly increased the potential of almost all the image information mining (IIM) applications related to earth observation. This is especially true for the extraction of road information, task of primary interest for many remote sensing applications, which scope is more and more extended to complex urban scenarios thanks to the availability of highly detailed images. This context is particularly challenging due to such factors as the variability of road visual appearence and the occlusions from entities like trees, cars and shadows. On the other hand, the peculiar geometry and morphology of man-made structures, particularly relevant in urban areas, is enhanced in high resolution images, making this kind of information especially useful for road detection. In this work, we provide a new insight on the use of morphological image analysis for road extraction in complex urban scenarios, and propose a technique for road segmentation that only relies on this domain. The keypoint of the technique is the use of skeletons as powerful descriptors for road objects: the proposed method is based on an ad-hoc skeletonization procedure that enhances the linear structure of road segments, and extracts road objects by first detecting their skeletons and then associating each of them with a region of the image. Experimental results are presented on two different high resolution satellite images of urban areas.

Information mining systems typically do not carry out image segmentation because a single algorithm could never perform well on the wide variety of sources and user applications encountered in practice. On the other hand, a large number of tools have been proposed in the literature that handle specific segmentation tasks very well. Dynamic segmentation is a possible solution, where the image is split recursively, in a hierarchical fashion, and different tools are used at each step to address specific segmentation tasks. In this work, the segmentation of a high-resolution test image is used as a running example and as a proof of concept of the potential of this approach.

International audience; The Texture Fragmentation and Reconstruction (TFR) algorithm has been recently introduced to address the problem of image segmentation by textural properties, based on a suitable image description tool known as the Hierarchical Multiple Markov Chain (H-MMC) model. TFR provides a hierarchical set of nested segmentation maps by first identifying the elementary image patterns, and then merging them sequentially to identify complete textures at different scales of observation. In this work, we propose a major modification to the TFR by resorting to a graph based description of the image content and a graph clustering technique for the enhancement and extraction of image patterns. A procedure based on mathematical morphology will be introduced that allows for the construction of a color-wise image representation by means of multiple graph structures, along with a simple clustering technique aimed at cutting the graphs and correspondingly segment groups of connected components with a similar spatial context. The performance assessment, realized both on synthetic compositions of real-world textures and images from the remote sensing domain, confirm the effectiveness and potential of the proposed method.

The Texture Fragmentation and Reconstruction (TFR) algorithm, recently proposed for the segmentation of textured images, has been applied with promising results to highresolution remote-sensing images. The algorithm provides a sequence of nested segmentation maps which allow the analysis at various scales of observation. However, the performance which is very good at large scales, with complex semantic areas retrieved with remarkable accuracy, becomes less satisfactory at finer scales. In this paper we propose to use the TFR in a recursive fashion, segmenting the image in just two regions, initially, with each region further segmented only if relevant subre-gions emerge. The recursive TFR allows one to better adapt to local statistics and to extract significant textures also at finer scales. Early experimental results validate the effectiveness of the new algorithm.

Segmentation of very high resolution remote-sensing images cannot rely only on spectral information, quite limited here for technological reasons, but must take into account also the rich textural information available. To this end, we proposed recently the Texture Fragmentation and Reconstruction (TFR) algorithm, based on a split-and-merge paradigm, which provides a sequence of nested segmentation maps, at various scales of observation. Early experiments on several high-resolution test images confirm the potential of TFR, but there is room for further improvements under various points of view. In this paper we describe the TFR algorithm and, starting from the analysis of some critical results propose two new version that address and solve some of its weak points.

International audience; In this work, we present a novel multiscale texture model, and a related algorithm for the unsupervised segmentation of color images. Elementary textures are characterized by their spatial interactions with neighboring regions along selected directions. Such interactions are modeled in turn by means of a set of Markov chains, one for each direction, whose parameters are collected in a feature vector that synthetically describes the texture. Based on the feature vectors, the texture are then recursively merged, giving rise to larger and more complex textures, which appear at different scales of observation: accordingly, the model is named Hierarchical Multiple Markov Chain (H-MMC). The Texture Fragmentation and Reconstruction (TFR) algorithm, addresses the unsupervised segmen- tation problem based on the H-MMC model. The “fragmentation” step allows one to find the elementary textures of the model, while the “reconstruction” step defines the hierarchical image segmentation based on a probabilistic measure (texture score) which takes into account both region scale and inter-region interactions. The performance of the proposed method was assessed through the Prague segmentation benchmark, based on mosaics of real natural textures, and also tested on real-world natural and remote sensing images.

Multispectral and synthetic aperture radar (SAR) images are known to exhibit complementary properties: unlike optical sensors, SAR provides information about the soil roughness and moisture, and acquires useful data despite clouds and Sun-illumination conditions. However, the analysis of the resulting images turns out to be more difficult, as compared to the use of optical imagery, due to the noise-like speckle phenomenon. In order to exploit this complementarity for classification purposes, a criticality relies in the definition of accurate joint optical-SAR statistical models, due to the different physical natures of these two data typologies and to the corresponding differences in the related parametric models. In this paper, a region-based semiparametric classification technique is proposed for multisensor optical-SAR images. The method combines the tree-structured Markov random field approach to segmentation with the dependence tree approach to probability density estimation and with case-specific bivariate models for the distributions of optical and SAR data. A Bayesian decision rule is formulated at the segment level in order to incorporate spatial-contextual information and to gain robustness against noise.

We propose here a new algorithm for the unsupervised segmentation of multiresolution remote-sensing images. After a first segmentation step on the high-resolution panchromatic data, the image is converted in a set of disjoint regions, which are then clustered and merged progressively, based on multispectral, spatial and textural properties, producing a sequence of nested segmentation maps which provide a thorough and multi-scale description of the image. The algorithm is fast, since it works mainly at a region level, and preserves fine details thanks to the initial step at the high-resolution level. Experimental results on IKONOS data confirm the algorithm potential and point out to a few problems to address in future research.

The region-based description of multispectral images enables important high-level tasks such as data mining and retrieval, and region-of-interest selection. In order to obtain an efficient representation of such images we resort to adaptive transform coding techniques. Such techniques, however, require a considerable information overhead, which must be carefully managed to obtain a satisfactory rate-distortion performance. In this work we develop several region based coding schemes and compare them with conventional (non-adaptive) and class-based schemes, so as to single out the rate-distortion gains/losses of this approach.