Lubia Vinhas

Lubia Vinhas
National Institute for Space Research, Brazil | inpe · Divisão de Processamento de Imagens (DPI)

Doctor - Applied Computing

About

77
Publications
32,731
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
478
Citations
Additional affiliations
December 1998 - present
National Institute for Space Research, Brazil
Position
  • Researcher

Publications

Publications (77)
Method
Full-text available
http://urlib.net/rep/8JMKD3MGP3W34R/443GTAS O Programa de Monitoramento da Amazônia e Demais Biomas (PAMZ+) é um programa desenvolvido na Divisão de Observação da Terra e Geoinformática (DIOTG) e na Coordenação Espacial da Amazônia (COEAM)do Instituto Nacional de Pesquisas Espaciais (INPE). O PAMZ+ executa três projetos operacionais de monitor...
Method
Full-text available
http://urlib.net/rep/8JMKD3MGP3W34R/443H3RE The Monitoring Program for the Amazon and Other Biomes (PAMZ +) is a program developed by the Earth Observation and Geoinformatics Division (DIOTG) and by the Spatial Coordination of the Amazon (COEAM), in the National Institute for Space Research (INPE). PAMZ+ executes three operational projects for lan...
Article
Full-text available
Monitoring the conversion of native vegetation has challenged Brazilian government and scientists since the 1980s. In the case of the Amazonian forests, the Amazon Gross Deforestation Monitoring Project - PRODES has developed an effective methodology that provides consistent annual data on deforestation areas on a scale of 1:250,000, since 1988. In...
Article
Full-text available
Many of the world’s agricultural frontiers are located in the tropics. Crop and cattle expansionin these regions has a strong environmental impact. This paper examines land use and land covertransformations in Brazil, where large swaths of natural vegetation are being removed to make way foragricultural production. In Brazil, the land use dynamics...
Article
Full-text available
Recently, remote sensing image time series analysis has being widely used to investigate the dynamics of environments over time. Many studies have combined image time series analysis with machine learning methods to improve land use and cover change mapping. In order to support image time series analysis, analysis-ready data (ARD) image collections...
Conference Paper
Full-text available
Remotely sensed Earth Observation (EO) data have exceeded a large scale and are increasingly available for different communities and thematic applications. In this matter, EO Data Cubes (EODC) are a promising solution to efficiently manage big EO data, enabling its access, processing and analysis. As final products, EODC provides analysis-ready dat...
Article
Full-text available
The Brazilian National Institute for Space Research (INPE) produces official information about deforestation as well as land use and cover in the country, based on remote sensing images. The current open data policy adopted by many space agencies and governments worldwide provided access to petabytes of remote sensing images. To properly deal with...
Article
Full-text available
The physical phenomena derived from an analysis of remotely sensed imagery provide a clearer understanding of the spectral variations of a large number of land use and cover (LUC) classes. The creation of LUC maps have corroborated this view by enabling the scientific community to estimate the parameter heterogeneity of the Earth’s surface. Along w...
Conference Paper
Full-text available
DETER and PRODES projects have been pioneerers at monitoring large deforestation mapping areas in Brazil. They have proved with quality-assured data their commitment to bridge the gap between society and better management of resources. Such environmental programs complexity, however, requires the designing, implementation and deployment of a spatia...
Article
Full-text available
Earth observation images are a powerful source of data about changes in our planet. Given the magnitude of global environmental changes taking place, it is important that Earth Science researchers have access to spatiotemporal reasoning tools. One area of particular interest is land-use change. Using data obtained from images, researchers would lik...
Conference Paper
Full-text available
The effective monitoring of land-use and land-cover changes (LULCC) is a basic requirement for understanding socio-enviromental processes of local to global scales. Remote sensing data and methods have long been established as the most effective approach for monitoring LULCC. The potential for further increasing the effectiveness of this approach i...
Conference Paper
Full-text available
This work presents an architecture for big Earth Observation data analytics. It uses array databases to support storage and management of large volumes of satellite image time series. The analysis methods are developed in R and enable using the full depth of satellite image time series with advanced statistical learning algorithms. New kinds of web...
Conference Paper
Full-text available
In this work, we evaluated the agreement between land cover maps generated by TerraClass and MapBiomas projects for Pará state and, more specifically: (1) describe the legends based on an international classification system, (2) analyze the differences among classes and (3) test PostGIS Raster from PostgreSQL database to work with classification pr...
Conference Paper
Full-text available
The answers to current our planet’s problems could be hidden in gi- gabytes of satellite imagery of the last 40 years, but scientists lack the means for processing such amount of data. To answer this challenge, we are build- ing a scientific platform for handling big Earth observation data. We organized decades of satellite images into data cubes i...
Conference Paper
Full-text available
The monitoring of land use and cover changes is essential for un- derstanding several environmental and socio-economic processes in the World. This monitoring requires novel software tools able to process big spatiotempo- ral data sets generated from Earth observation satellites efficiently. To generate land use and cover maps, researchers from dif...
Article
Full-text available
Geographic Information Systems users without appropriate programming skills perform repetitive tasks through Graphical User Interfaces when manipulating large datasets, such as remote sensing imagery. Scripting languages, such as Lua, make the process easier for those users, due to their higher abstraction and simplicity, than the more complex prog...
Article
Full-text available
Governmental agencies provide a large and open set of satellite imagery that can be used to track changes in geographic features over time. The current available analysis methods are complex and they are very demanding in terms of computing capabilities. Hence, scientist cannot reproduce analytic results because of lack of computing infrastructure....
Conference Paper
Full-text available
One of the main applications in remote sensing is the analysis and classification of land cover and land use Sensors, such as MODIS, are have been largely used for monitoring land cover change due to its high temporal resolution. Although several studies perform time series classification by features extracting or similarities measures to verify an...
Conference Paper
Full-text available
Recent advances in devices that collect geospatial information have produced massive spatiotemporal data sets. Earth observation and GPS satellites, sensor networks and mobile gadgets are examples of technologies that have created large data sets with better spatial and temporal resolution than ever. This scenario brings a challenge for Geoinformat...
Conference Paper
Full-text available
The aim of geospatial web services is to enable users to share and process geospatial data on the Web, no matter what platform or protocol is used. In this paper, we investigate what are the design decisions needed to implement web services for big Earth observation (EO) data. The focus of the work is discussing what is unique about big EO data and...
Conference Paper
Full-text available
O potencial observado em diversas aplicações e o avanço das tecnologias de aquisição de nuvem de pontos tem aumentado a disponibilidade desse tipo de dado geoespacial. Com o aumento do volume, novos desafios surgem quanto ao gerenciamento eficiente dessas informações. Recentemente, o Sistema Gerenciador de Banco de Dados PostgreSQL tem gerenciado e...
Conference Paper
Full-text available
In this work, we propose the development of a system for thunderstorms cell tracking, based on a spatial database. We also introduce a that performs spatio-temporal clustering operations of lightning data using the DBS-CAN algorithm. The spatial database query language were used to define the time window, in order to characterize cells associated w...
Conference Paper
Full-text available
The temporal dimension of spatial data has been the subject of discussion in the literature for a long time. While there are numerous Database Management System (DBMS) solutions only for spatial dimension, we did not observe the same situation for spatiotemporal data. Considering this gap, our purpose is to design and implement an extension to the...
Article
Full-text available
Species distribution models (SDMs) are tools to obtain habitat suitability maps based on historical species occurrences and environmental variables. Those maps can be used to restrict fishing grounds or to assist in planning and reserve selection. This is especially important for species at risk of extinction. We developed SDMs for five endangered...
Conference Paper
Full-text available
Earth observation satellites produce petabytes of geospatial data. To manage large data sets, researchers need stable and efficient solutions that support their analytical tasks. Since the technology for big data handling is evolving rapidly, researchers find it hard to keep up with the new developments. To lower this burden, we argue that research...
Article
Full-text available
After a thorough review of the past editions of the Brazilian Symposium on GeoInformatics (GEOINFO), from 1999 to 2015, which included more than 300 articles, we have identified some topics pointing to trends in the area of GeoInformatics for the next years of research. As expected, the topics Data/Information, Geographic Information System (GIS),...
Article
Full-text available
A cobertura da terra encontra-se em constante transformação devido aos diferentes fatores que influenciam a sua utilização e destinação. Essas alterações observadas ao longo do tempo definem o que chamamos de Trajetórias de Mudança de Cobertura da Terra. Tais trajetórias, uma vez caracterizadas, podem fornecer informações valiosas acerca de diferen...
Conference Paper
Full-text available
This paper shows how to implement zonal operations from Tomlin's Map Algebra in a multidimensional matricial database management system. The database consist of a set of remote sensing images stored in a SciDB instance. The zonal operator was used to compute spatial and temporal statistics over discrete regions of a vector map. Resumo. Este artigo...
Conference Paper
Full-text available
Mobile devices, such as smartphones and tablets, are useful tools for in situ collecting information about spatial locations. In this paper, we describe the architecture of a mobile application for geographical data gathering and validation in fieldwork. This application is being developed based on well-established standards in order to assure spat...
Conference Paper
Full-text available
The recent technological advances in geospatial data collection, such as mobile phones, Earth observation and GPS (Global Positioning System) satellites, have created bigger spatiotemporal data sets than ever. This novel scenario has motivated new infrastructures and technologies to efficiently store, process, analyze and disseminate large data set...
Conference Paper
Full-text available
This paper presents a lightweight web service named Web Time Series Service (WTSS) for handling remote sensing imagery as time series. The proposed web service bridges the gap between remote sensing applications and their data access pattern requirements through a simple and effective representation for time series data. Our main goal is to bring t...
Conference Paper
Full-text available
Remote sensing images are largely used for monitoring and combat deforestation at Brazil. One example of environmental monitoring project, based in remote sensing images is the PRODES Project that detects the deforestations and performs the processing necessary for that deforestation data can be used in different studies, for example, study about l...
Conference Paper
Full-text available
Remote sensing data are useful in different areas of research and application, among them agriculture, which can be used for monitoring crops and even of the support the productivity prediction of certain crops. For this, one of the most desired features is the ability to separate, or classify, in remote sensing images, the different crops observed...
Conference Paper
Full-text available
Mobile devices, such as smartphones and tablets, are useful tools for in situ gathering information about spatial locations. Specialists need mobile geographical data acquisition and validation systems to be used in fieldwork and in places where there is limited or any network connectivity available. This paper presents an ongoing work on designing...
Conference Paper
Full-text available
This paper defines the Field data type for big spatial data. Most big spatial data sets provide information about properties of real-ity in continuous way, which leads to their representation as fields. We develop a generic data type for fields that can represent di↵erent types of spatiotemporal data, such as trajectories, time series, remote sensi...
Article
Full-text available
Moving object is a well-established concept in geographic information system (GIS) science. It is an entity whose spatial position or extent changes continuously over time. Some examples are cars, animals and deforested regions. Nowadays, there is a growing demand for GIS tools that are able to handle and analyze moving objects. Most exiting spatia...
Conference Paper
Full-text available
Although KML files can be used to describe journeys, there is not a standard way to represent them as moving object trajectories for further analysis. In the KML schema, there is not a predefined element to describe a moving object trajectory. Each software or mobile device that generates KML files with trajectories uses its own structure for repre...
Data
Full-text available
Geosciences studies frequently require to conduct field works. When a huge amount information is collected during such surveys, it's manipulation, organization and interpretation is, generally, an arduous task. A tool resulting from advances in Geotechnology are GPS cameras. They are capable to record the geographical position of the locations phot...
Article
Full-text available
This article describes a graphic tool implementation to upload and visualize raster data stored in a PostgreSQL database with PostGIS extension. The implementation was done as a Quantum GIS plugin called WktRaster, re-leased as an open source software. The plugin is one of the earliest efforts to explore raster data storage, visualization and proce...
Conference Paper
Full-text available
This paper examines the constraints that limit the large-scale adoption of open source GIS. Although the open source GIS community has already achieved relevant results, their products have a small market share. There is equivalent to Linux and Apache in the open source GIS scene. We try to explain why this happens, by considering some factors that...
Conference Paper
Full-text available
The use of remote sensing imagery to obtain land cover and land use maps is a common task in GIS applications. Segmentation techniques identify closed regions in images, producing vector datasets composed by polygons. Since segmentation is a bottom-up technique, the resulting vector datasets are often too detailed. Thus, we need to use generalizati...
Conference Paper
Full-text available
Abstract. Abstract. This paper proposes an automated approach for describing how geospatial objects evolve. We consider geospatial objects whose boundaries and properties change in the time, and refer to them as evolving objects . Our approach is to provide a set of rules that describe how objects change, referred to as rule-based evolution . We co...
Chapter
Full-text available
This paper discusses the challenges facing GIS designers in the 21st century. We argue that GI engineers lack a sound theoretical basis that would allow them to make best use of new technologies that handle geospatial data. Considering three important topics for the new generations of GIS (change, semantics, and cognition) we show that GIS theory i...
Chapter
Full-text available
This chapter describes TerraLib, an open source GIS software library. The design goal for TerraLib is to support large-scale applications using socio-economic and environmental data. TerraLib supports coding of geographical applications using spatial databases, and stores data in different database management systems including MySQL and PostgreSQL....
Conference Paper
Full-text available
This paper describes a model for spatiotemporal objects whose location is fixed, but its boundaries and properties change. We refer to these as evolving objects. We consider cases where the evolution of an object is dependent of its type and propose a rule-based approach for description of spatiotemporal object's evolution. By developing semantics...
Chapter
Full-text available
Esse capítulo descreve a biblioteca TerraLib em seus