Georeferenced road extraction and formulation of hypotheses for new road segments

The acquisition and update of Geographic Information System (GIS) data are typically carried out using aerial or satellite imagery. Since new roads are usually linked to georeferenced pre-existing road network, the extraction of pre-existing road segments may provide good hypotheses for the updating process. This paper addresses the problem of extracting georeferenced roads from images and formulating hypotheses for the presence of new road segments. Our approach proceeds in three steps. First, salient points are identified and measured along roads from a map or GIS database by an operator or an automatic tool. These salient points are then projected onto the image-space and errors inherent in this process are calculated. In the second step, the georeferenced roads are extracted from the image using a dynamic programming (DP) algorithm. The projected salient points and corresponding error estimates are used as input for this extraction process. Finally, the road center axes extracted in the previous step are analyzed to identify potential new segments attached to the extracted, pre-existing one. This analysis is performed using a combination of edge-based and correlation-based algorithms. In this paper we present our approach and early implementation results.

Adaptative techniques for the human faces detection

This paper presents results from an efficient approach to an automatic detection and extraction of human faces from images with any color, texture or objects in background, that consist in find isosceles triangles formed by the eyes and mouth.

Caracterização das falhas de transferência na porção norte da Bacia de Santos a partir da integração de dados geológicos e geofísicos

Structures transverse/sub-transverse to the shoreline have been identified and characterized on the precambrian basement outcrop on the continent adjacent to the northern Santos Basin. These structures were analyzed from images of digital elevation model SRTM 90m by extracting NW-SE lineaments that intersect the NE-SW foliation. The lineaments were selected, classified into 48 segments that extend toward offshore, and correlated with basin structures. In the basin 25 2D seismic sections, 12 well logs and data from potential methods were interpreted, identifying the key stratigraphic levels and the major structures. Structural maps of each horizon were generated. Six transfer faults (FTs) were recognized and named FT-1 to FT-6, whose extensions correspond to continental lineaments named FC1 to FC6. The FTs are related to the basin deformation and evolution. In seismic sections, these faults have lateral slip in flower structures, displacement inversions from normal at the top to reverse at the base, abrupt changes in thickness or even disappearance of the seismic reflectors. The structural map of the Basement and Top of the Rift shows control of some depocenters by faults and displacements in some areas. The maps of potential methods indicate that there are pronounced anomaly shifts in some areas, associated with FTs. Some seismic sections indicate reactivation of FTs when they intersect horizons from the basement until the most recent layers. The 3D integration of data facilitated the observation of the FT extensions in the continent discontinuity.

Environment mapping for mobile robots navigation using hierarchical neural network and omnivision

Autonomous robots must be able to learn and maintain models of their environments. In this context, the present work considers techniques for the classification and extraction of features from images in joined with artificial neural networks in order to use them in the system of mapping and localization of the mobile robot of Laboratory of Automation and Evolutive Computer (LACE). To do this, the robot uses a sensorial system composed for ultrasound sensors and a catadioptric vision system formed by a camera and a conical mirror. The mapping system is composed by three modules. Two of them will be presented in this paper: the classifier and the characterizer module. The first module uses a hierarchical neural network to do the classification; the second uses techiniques of extraction of attributes of images and recognition of invariant patterns extracted from the places images set. The neural network of the classifier module is structured in two layers, reason and intuition, and is trained to classify each place explored for the robot amongst four predefine classes. The final result of the exploration is the construction of a topological map of the explored environment. Results gotten through the simulation of the both modules of the mapping system will be presented in this paper. © 2008 IEEE.

Grafias não-convencionais da coda silábica nasal em dados de escrita de jovens e adultos em processo de alfabetização

Pós-graduação em Estudos Linguísticos - IBILCE

Luz e sombra, mostrar e esconder: os efeitos de sentido e as estratégias da imagem fotográfica em magnum in motion

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Desenvolvimento de um programa computacional para classificação do uso da terra em imagens CBERS 2

Pós-graduação em Agronomia (Energia na Agricultura) - FCA

Materialografia quantitativa de micro estruturas complexas baseada na segmentação por texturas

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Identificação de doenças em folhas vegetais da cultura de algodão

Pós-graduação em Ciência da Computação - IBILCE

Classificação de cobertura do solo utilizando árvores de decisão e sensoriamento remoto

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

A coluna “Reflexões” de Hipólito da Costa no Correio Brasiliense (1808-1822): uma voz pela liberdade de imprensa, união do Brasil com Portugal e contra governos despóticos

Pós-graduação em Letras - FCLAS

Proposta de um modelo matemático para apoio às decisões táticas da gestão da produção

Pós-graduação em Engenharia Mecânica - FEG

Reconhecimento da tectônica mezozóica-cenozóica na borda leste da Bacia do Paraná através da aplicação de traços de fissão em apatitas no Domo de Pitanga (Sudoeste de Rio Claro, SP)

A tectônica Mesozóica-Cenozóica na borda leste da Bacia do Paraná foi interpretada com base no estudo geocronológico de uma importante feição estrutural conhecida como Domo de Pitanga (sudoeste de Rio Claro, SP), que, como outras estruturas do mesmo tipo presentes na borda da bacia, coincide com grandes alinhamentos estruturais formados pela reativação de estruturas preexistentes no seu embasamento. O método utilizado foi o de datação por análise de traços de fissão em apatitas, o qual permite a modelagem térmica entre 120oC e a temperatura ambiente. Utilizando apatitas de rochas sedimentares, foi possível a modelagem da história térmica da área, graças à homogeneidade dos dados que cada amostra apresentou em função do aquecimento no Eocretáceo pelo magmatismo Serra Geral. Além do resfriamento posterior ao magmatismo marcado pelas idades (Eocretáceo), foram detectadas as principais épocas de resfriamento na área de estudo, sendo elas do Neocretáceo, Paleoceno e, com menor importância, do Mioceno. Estes períodos remontam a importantes eventos tectônicos ocorridos no Sudeste brasileiro, bem descritos no embasamento cristalino. Fica clara a influência desta tectônica de caráter ascensional do embasamento adjacente no interior da bacia, atuando na formação de estruturas, como é o caso do Domo de Pitanga.

An alternative approach for quasi-truth

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Acurácia da mosaicagem gerada por veículo aéreo não tripulado utilizado na agricultura de precisão

The need for unmanned aerial vehicle (UAV) is a Brazilian reality in the worlds agricultural, once they have models penetrating the market with agrictural purpose. After processing, the images collected by a UAV can generate a mosaic of the study area. For making and georeferencing the mosaic, can be deployed or not ground control points. Thus, the study aimed to compare a mosaic with ground control points and without ground control points generated from images collected by a UAV used primarily for agricultural purposes. The results showed that the quality in the determination of areas and perimeters no presented significant difference with or without the use of ground control points. The mosaic generated without ground control points obtained an average error of 23.7% of the pixel size; with ground control points, the average error was 10.6%, providing an improvement of approximately 50%. Planimetric and altimetric errors, with respect to the ground control points, for the controlled mosaic, reached the order of decimeters, with planimetric accuracy of 12.8 cm, a result considered satisfactory taking into account mainly the purpose of assessed UAV