A hybrid object-based classification approach for mapping urban sprawl in periurban environment

Jacquin, Anne; Misáková, Lucie; Gay, Michel

doi:10.1016/j.landurbplan.2007.07.006

Cited by 115 publications

(55 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Outra vantagem dessa abordagem seria a possibilidade de caracterizar cada objeto não somente em suas propriedades espectrais, mas também considerando suas características espaciais, pelas regras fuzzy. Isso torna possível a reprodutibilidade do método, ainda que esse precise ser adequado, devido às especificidades da paisagem e dos dados de sensoriamento remoto utilizados em cada caso 22 . Além disso, os diferentes graus de pertinência, disponíveis na lógica fuzzy, permitem um refinamento da classificação.…”

Section: Campo Térmico Da Superfície Do Solounclassified

“…Neste estudo, além da ausência de um componente temporal e de dados sobre vetores, o que limita a interpretação dessas correlações, há ainda a pequena variação de temperatura média nos setores censitários no período analisado, indicando que as condições térmicas foram relativamente constantes na cidade. De fato, as médias (desvios-padrão) da temperatura nos setores censitários foram de 31,99 (0,96), em 1990, e de 29,1 (1,22), em 2003. Assim, a pequena variabilidade da temperatura na cidade sugere que outros fatores, como aqueles ligados a questões sociais, ambientais e do próprio indivíduo, teriam maior participação na ocorrência da doença em Teresina.…”

Section: Campo Térmico Da Superfície Do Solounclassified

See 1 more Smart Citation

Classificação orientada a objeto de imagens de sensoriamento remoto em estudos epidemiológicos sobre leishmaniose visceral em área urbana

Almeida

Werneck

Resendes³

2014

Cad. Saúde Pública

View full text Add to dashboard Cite

Neste estudo, explorou-se o uso da classificação orientada a objeto de imagens de sensoriamento remoto em estudos epidemiológicos sobre leishmaniose visceral (LV) em áreas urbanas. A classificação orientada a objeto foi aplicada a cenas Landsat 5 TM da cidade de Teresina, Piauí, Brasil, para obtenção de informações ambientais e temperatura. Para o período de 1993-1996, a taxa de incidência de LV nos setores censitários da cidade foi positivamente correlacionada com a área do setor censitário coberta por vegetação densa, rasteira e solo exposto e negativamente com a área coberta por água e áreas densamente ocupadas. No período de 2001-2006, foram encontradas correlações positivas com vegetação densa, rasteira, solo exposto e áreas densamente ocupadas e negativas com áreas urbanas com alguma vegetação. A temperatura da superfície terrestre foi negativamente associada à incidência de LV nos dois períodos. A classificação orientada a objeto pode ser útil para caracterizar paisagens associadas à ocorrência da LV em áreas urbanas e delimitar áreas de risco para definição de prioridades na implementação de intervenções.

show abstract

Section: Campo Térmico Da Superfície Do Solounclassified

Classificação orientada a objeto de imagens de sensoriamento remoto em estudos epidemiológicos sobre leishmaniose visceral em área urbana

Almeida

Werneck

Resendes³

2014

Cad. Saúde Pública

View full text Add to dashboard Cite

show abstract

“…[10]. Additionally, land cover products form a major input for further modeling and analysis, e.g., in hydrologic modeling, and trend analysis [11][12][13][14][15], biomass and energy modeling [16][17][18][19][20], population density modeling [21,22], risk and hazard analysis [23][24][25], or ecosystem assessment [26,27]. Innovative environmental planning and management tools, such as Decision Support Systems, also require high-quality land cover and land use information derived from high and very high resolution data at a regional scale [6].…”

Section: Introductionmentioning

confidence: 99%

Land Cover and Land Use Classification with TWOPAC: towards Automated Processing for Pixel- and Object-Based Image Classification

et al. 2012

View full text Add to dashboard Cite

We present a novel and innovative automated processing environment for the derivation of land cover (LC) and land use (LU) information. This processing framework named TWOPAC (TWinned Object and Pixel based Automated classification Chain) enables the standardized, independent, user-friendly, and comparable derivation of LC and LU information, with minimized manual classification labor. TWOPAC allows classification of multi-spectral and multi-temporal remote sensing imagery from different sensor types. TWOPAC enables not only pixel-based classification, but also allows classification based on object-based characteristics. Classification is based on a Decision Tree approach (DT) for which the well-known C5.0 code has been implemented, which builds decision trees based on the concept of information entropy. TWOPAC enables automatic generation of the decision tree classifier based on a C5.0-retrieved ascii-file, as well as fully automatic validation of the classification output via sample based accuracy assessment. Envisaging the automated generation of standardized land cover products, as well as area-wide classification of large amounts of data in preferably a short processing time, standardized interfaces for process control, Web Processing Services (WPS), as introduced by the Open Geospatial Consortium (OGC), are utilized. TWOPAC's functionality to process geospatial raster or vector data via web resources (server, network) enables 2531TWOPAC's usability independent of any commercial client or desktop software and allows for large scale data processing on servers. Furthermore, the components of TWOPAC were built-up using open source code components and are implemented as a plug-in for Quantum GIS software for easy handling of the classification process from the user's perspective.

show abstract

“…Mapping urban areas using remote sensing (RS) data has been widely studied but most of the applications dealing with anthropic CSs are focusing on dense urban environment and small areal coverage [19]. Manual surveying techniques are usually used for small areas but if their sizes increase, semiautomatic approaches are to be preferred because of their costeffectiveness [19], as these practices require investments and time. For this reason, it is not possible to obtain maps of the stocks with short time intervals using traditional methods.…”

Section: Introductionmentioning

confidence: 99%

Carbon Stocks in Peri-Urban Areas: A Case Study of Remote Sensing Capabilities

Villa

Malucelli²,

Scalenghe

2014

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Abstract-Peri-urban areas are the extension of cities into contiguous areas, where households and farms coexist. Carbon stocks (CSs) assessment, a concept here extended to urban features, has not yet been studied in depth over peri-urban areas due to uncertainties in such CSs quantification, level of detail required about construction materials, and the high spatial variability of those stocks. Remote sensing (RS)-based techniques have been successfully utilized in urban areas for assessing phenomena such as soil sealing, sprawl patterns, and dynamics of surface imperviousness, especially focusing on land cover classification at high to medium spatial scales. Over the floodplain study area of Emilia-Romagna region (Italy), we compared mapping products derived from Landsat multiseasonal data with different CSs, in soils and impervious surfaces, such as buildings and roads. A multiscale correlation analysis and regression assessment between CSs layers and satellite products were run at different grid cell sizes (100, 250, 500, and 1000 m). Results show that RS products from processing of midresolution satellite data can effectively perform well enough to estimate CSs in peri-urban areas, especially at 500-1000 m scale. Urban Fraction Cover method, derived through weighting urban land cover classes (including dense, sparse, and industrial urban features) can represent a good proxy of the ratio of anthropogenic over natural CSs (R 2 up to 0.75). Imperviousness Index (II) product scored high positive correlation with CSs over built-up areas (R 2 up to 0.77), and strong negative correlation with organic carbon density in soil (R 2 up to 0.73).

show abstract

A hybrid object-based classification approach for mapping urban sprawl in periurban environment

Cited by 115 publications

References 34 publications

Classificação orientada a objeto de imagens de sensoriamento remoto em estudos epidemiológicos sobre leishmaniose visceral em área urbana

Classificação orientada a objeto de imagens de sensoriamento remoto em estudos epidemiológicos sobre leishmaniose visceral em área urbana

Land Cover and Land Use Classification with TWOPAC: towards Automated Processing for Pixel- and Object-Based Image Classification

Carbon Stocks in Peri-Urban Areas: A Case Study of Remote Sensing Capabilities

Contact Info

Product

Resources

About