HidroSIG: un sistema de información geográfica para la gestión de recursos naturales y modelación del medio ambiente

This paper describes HidroGIS, a GIS platform developed by Water Resources Program at Universidad Nacional de Colombia at Medellín. HidroSIG is a tool for hydrological variables visualization and analysis, using a set of modules that make this software a powerful tool for hydrological modeling. HidroSIG has tools for digital terrain models processing, water supply estimation using long term water balance in watersheds, a rainfall-runoff model, a model for landslide susceptibility estimation, an one-dimensional pollutant transport model, tools for homogeneity analysis in time series and tools for satellite images classification. The tools in development status are also described

Análise temporal do uso do solo e comparação entre os índices de vegetação ndvi e savi no município de Santa Cruz do Rio Pardo - SP usando imagens landsat-5

This work aims to analyze the land use evolution in the city of Santa Cruz do Rio Pardo - SP through supervised classification of Landsat-5 TM satellite images according to the maximum likelihood (Maxlike), as well as verifying the mapping accuracy through Kappa index, comparing NDVI and SAVI vegetation indexes in different adjustment factors for the canopy substrate and determining the vegetal coverage percentage in all methods used on 2007, May 26 th; 2009, January 7 th and 2009, April 29 th. The Maxlike classification showed several spatial changes in land use over the study period. The most appropriated vegetation indexes were NDVI and SAVI - 0,25 factor, which showed similar values of vegetal coverage percentage, but discrepant from the inferred value for Maxlike classification.

Métodos para extração de informações a partir de imagens multiespectrais de escalas grandes

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Comparação de métodos de classificação de imagens, visando o gerenciamento de áreas citrícolas

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Identificação da dinâmica espaço-temporal para estimar área cultivada de soja a partir de imagens MODIS no Rio Grande do Sul

The objective of this study was to define a method for estimating soybean crop area in the Northern Rio Grande do Sul state (Brazil). Overall, six different remote sensing methods were proposed based on spectral-temporal profile and minimum and maximum values of NDVI/MODIS related to the stages of sowing, maximum development and harvesting of soybean areas. The resulting estimates were compared to official crop area data provided by the Brazilian government, using statistical analysis and the fuzzy similarity method. The performance of each method depended on information such as crop size, type of crop management, and sowing/harvesting dates. Regression coefficients of determination and fuzzy agreement values were above 0.8 and 0.45, respectively, for all methods. For operational monitoring of soybean crop area, the empirical threshold applied to the image difference with inclusion of harvest image method was the most effective, producing estimates that matched closely the official data. For spatial analysis the application of multitemporal images classification method is recommended that generated a map of better quality. The efficiency of these methods should be evaluated in the areas of soybean expansion in the state.

Forming classes by stimulus frequency: Behavior and theory

Visual classification is the way we relate to different images in our environment as if they were the same, while relating differently to other collections of stimuli (e.g., human vs. animal faces). It is still not clear, however, how the brain forms such classes, especially when introduced with new or changing environments. To isolate a perception-based mechanism underlying class representation, we studied unsupervised classification of an incoming stream of simple images. Classification patterns were clearly affected by stimulus frequency distribution, although subjects were unaware of this distribution. There was a common bias to locate class centers near the most frequent stimuli and their boundaries near the least frequent stimuli. Responses were also faster for more frequent stimuli. Using a minimal, biologically based neural-network model, we demonstrate that a simple, self-organizing representation mechanism based on overlapping tuning curves and slow Hebbian learning suffices to ensure classification. Combined behavioral and theoretical results predict large tuning overlap, implicating posterior infero-temporal cortex as a possible site of classification.

Advancing Bag-of-visual-words Representations For Lesion Classification In Retinal Images.

Diabetic Retinopathy (DR) is a complication of diabetes that can lead to blindness if not readily discovered. Automated screening algorithms have the potential to improve identification of patients who need further medical attention. However, the identification of lesions must be accurate to be useful for clinical application. The bag-of-visual-words (BoVW) algorithm employs a maximum-margin classifier in a flexible framework that is able to detect the most common DR-related lesions such as microaneurysms, cotton-wool spots and hard exudates. BoVW allows to bypass the need for pre- and post-processing of the retinographic images, as well as the need of specific ad hoc techniques for identification of each type of lesion. An extensive evaluation of the BoVW model, using three large retinograph datasets (DR1, DR2 and Messidor) with different resolution and collected by different healthcare personnel, was performed. The results demonstrate that the BoVW classification approach can identify different lesions within an image without having to utilize different algorithms for each lesion reducing processing time and providing a more flexible diagnostic system. Our BoVW scheme is based on sparse low-level feature detection with a Speeded-Up Robust Features (SURF) local descriptor, and mid-level features based on semi-soft coding with max pooling. The best BoVW representation for retinal image classification was an area under the receiver operating characteristic curve (AUC-ROC) of 97.8% (exudates) and 93.5% (red lesions), applying a cross-dataset validation protocol. To assess the accuracy for detecting cases that require referral within one year, the sparse extraction technique associated with semi-soft coding and max pooling obtained an AUC of 94.2 ± 2.0%, outperforming current methods. Those results indicate that, for retinal image classification tasks in clinical practice, BoVW is equal and, in some instances, surpasses results obtained using dense detection (widely believed to be the best choice in many vision problems) for the low-level descriptors.

Towards an efficient and robust foot classification from pedobarographic images

O documento em anexo encontra-se na versão post-print (versão corrigida pelo editor).

The contribution of multitemporal information from multispectral satellite images for automatic land cover classification at the national scale

Thesis submitted to the Instituto Superior de Estatística e Gestão de Informação da Universidade Nova de Lisboa in partial fulfillment of the requirements for the Degree of Doctor of Philosophy in Information Management – Geographic Information Systems

Unsupervised classification of remote sensing images combining Self Organizing Maps and segmentation techniques

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Analysis of classification algorithms for crop detection using LANDSAT 8 images

Remote sensing - the acquisition of information about an object or phenomenon without making physical contact with the object - is applied in a multitude of different areas, ranging from agriculture, forestry, cartography, hydrology, geology, meteorology, aerial traffic control, among many others. Regarding agriculture, an example of application of this information is regarding crop detection, to monitor existing crops easily and help in the region’s strategic planning. In any of these areas, there is always an ongoing search for better methods that allow us to obtain better results. For over forty years, the Landsat program has utilized satellites to collect spectral information from Earth’s surface, creating a historical archive unmatched in quality, detail, coverage, and length. The most recent one was launched on February 11, 2013, having a number of improvements regarding its predecessors. This project aims to compare classification methods in Portugal’s Ribatejo region, specifically regarding crop detection. The state of the art algorithms will be used in this region and their performance will be analyzed.

Cluster kernels for semisupervised classification of VHR urban images

In this paper, we present and apply a semisupervised support vector machine based on cluster kernels for the problem of very high resolution image classification. In the proposed setting, a base kernel working with labeled samples only is deformed by a likelihood kernel encoding similarities between unlabeled examples. The resulting kernel is used to train a standard support vector machine (SVM) classifier. Experiments carried out on very high resolution (VHR) multispectral and hyperspectral images using very few labeled examples show the relevancy of the method in the context of urban image classification. Its simplicity and the small number of parameters involved make it versatile and workable by unexperimented users.

Validation of tissue modelization and classification techniques in T1-weighted MR brain images

We propose a deep study on tissue modelization andclassification Techniques on T1-weighted MR images. Threeapproaches have been taken into account to perform thisvalidation study. Two of them are based on FiniteGaussian Mixture (FGM) model. The first one consists onlyin pure gaussian distributions (FGM-EM). The second oneuses a different model for partial volume (PV) (FGM-GA).The third one is based on a Hidden Markov Random Field(HMRF) model. All methods have been tested on a DigitalBrain Phantom image considered as the ground truth. Noiseand intensity non-uniformities have been added tosimulate real image conditions. Also the effect of ananisotropic filter is considered. Results demonstratethat methods relying in both intensity and spatialinformation are in general more robust to noise andinhomogeneities. However, in some cases there is nosignificant differences between all presented methods.

Comparison and validation of tissue modelization and statistical classification methods in T1-weighted MR brain images.

This paper presents a validation study on statistical nonsupervised brain tissue classification techniques in magnetic resonance (MR) images. Several image models assuming different hypotheses regarding the intensity distribution model, the spatial model and the number of classes are assessed. The methods are tested on simulated data for which the classification ground truth is known. Different noise and intensity nonuniformities are added to simulate real imaging conditions. No enhancement of the image quality is considered either before or during the classification process. This way, the accuracy of the methods and their robustness against image artifacts are tested. Classification is also performed on real data where a quantitative validation compares the methods' results with an estimated ground truth from manual segmentations by experts. Validity of the various classification methods in the labeling of the image as well as in the tissue volume is estimated with different local and global measures. Results demonstrate that methods relying on both intensity and spatial information are more robust to noise and field inhomogeneities. We also demonstrate that partial volume is not perfectly modeled, even though methods that account for mixture classes outperform methods that only consider pure Gaussian classes. Finally, we show that simulated data results can also be extended to real data.

Mixed spectral-structural classification of very high resolution images with summation kernels

In this paper, mixed spectral-structural kernel machines are proposed for the classification of very-high resolution images. The simultaneous use of multispectral and structural features (computed using morphological filters) allows a significant increase in classification accuracy of remote sensing images. Subsequently, weighted summation kernel support vector machines are proposed and applied in order to take into account the multiscale nature of the scene considered. Such classifiers use the Mercer property of kernel matrices to compute a new kernel matrix accounting simultaneously for two scale parameters. Tests on a Zurich QuickBird image show the relevance of the proposed method : using the mixed spectral-structural features, the classification accuracy increases of about 5%, achieving a Kappa index of 0.97. The multikernel approach proposed provide an overall accuracy of 98.90% with related Kappa index of 0.985.