Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ LAReferencia - Red F...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 1 versions
addClaim

Extração de rodovias utilizando SNAKES

Authors: Oliveira, Rafael Montanhini Soares de;

Extração de rodovias utilizando SNAKES

Abstract

Obtaining information from the extraction of aspects from aerial photographs and satellite images is one of the main purposes of the new technology in Digital Photogrammetry. This study proposes extracting roads and linking the segments of the extracted roads by means of other extractors of aspects, by using models of active contour, or snakes. Snakes was introduced almost two decades ago, and it consists in a parametrically represented curve, controlled by photometric and geometric injunctions: photometric injunctions, called image power, that attract the snakes curve for the aspect to be extracted (road); geometric injunctions, generated by internal powers that control the shape of the snakes curve, thus insuring its smoothness. As it is a semi-automatic extraction process, the operator shall initially describe the road roughly, using at least six seed points. From this initial position, the snakes curve evolves at each iteration, placing itself over the road edge (aspect to be extracted), where its power is minimized. The snakes method was implemented in language C and tested in the extraction and link of road segments in images of high resolution (pixels lower than 0.7m), medium resolution (pixels between 0.7m and 2.0m) and low resolution (pixels higher than 2.0m), and it turned out to be very efficient in both cases, even in the presence of obstacles that disturb the perfect road outlining. With the extraction of road edges in high and medium resolution images, one interpolated axis was generated, and it was compared to the reference axis used in the evaluation. By using visual and numerical evaluations, it was possible to prove the accuracy provided by the process of extraction and link of segments that uses the snakes method.

A obtenção de informações a partir da extração de feições em fotos aéreas e imagens de satélite é um dos principais objetivos da nova tecnologia de automação em Fotogrametria Digital. Este trabalho propõe a extração de rodovias, e a conexão de segmentos de rodovias extraidos por outros extratores de feições, utilizando modelos de contorno ativo ou snakes. Snakes foi introduzido há quase duas décadas e consiste em uma curva representada parametricamente e controlada por injunções fotométricas e geométricas: fotométricas, chamadas de força da imagem que atraem a curva snakes para a feição a ser extraída (rodovia); geométricas, geradas pelas forças internas que controlam a forma da curva snakes garantindo sua suavidade. Por ser um método de extração semi-automático, inicialmente o operador deve descrever a rodovia de maneira grosseira utilizando no mínimo seis pontos sementes. A partir desta posição inicial a curva snakes evolui a cada iteração fazendo com que a mesma se posicione sobre a borda da rodovia (feição a ser extraída) onde sua energia é minimizada. O método snakes foi implementado em linguagem C e testado na extração e conexão de segmentos de rodovia em imagens de alta (pixels menores 0.7m), média (pixels entre 0.7m e 2.0m) e baixa (pixels maiores 2.0m) resolução, mostrando-se bastante eficiente em todos os casos, mesmo na presença de obstáculos que perturbam o perfeito delineamento da rodovia. Através da extração de bordas de rodovia, em imagens de alta e média resolução, foi gerado um eixo interpolado e comparado com o eixo de referência utilizado para avaliação. Utilizando avaliações visuais e numéricas foi possível comprovar a boa acuracia do processo de extração e conexão de segmentos utilizando snakes.

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

Pós-graduação em Ciências Cartográficas - FCT

Country
Brazil
Keywords

Digital Photogrammetry, Fotogrametria digital, Rodovias, Cartografia, Extração de rodovias

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green