R E S U M O<\/strong><\/p>\n\n\n\nAs paisagens como conhecemos e vemos est\u00e3o em constante mudan\u00e7a devido a processos naturais e antr\u00f3picos de diferentes magnitudes espaciais e temporais. Para entendermos essas mudan\u00e7as, elas necessariamente devem ser observ\u00e1veis ou mensur\u00e1veis. Atualmente se coloca o Sensoriamento Remoto como uma das mais modernas formas de monitoramento da paisagem devido a m\u00e9todos aplic\u00e1veis aos seus produtos que permitem an\u00e1lises qualitativas e quantitativas das altera\u00e7\u00f5es na paisagem, ocasionadas pelos complexos padr\u00f5es de uso e ocupa\u00e7\u00e3o da terra ao longo do tempo. Dentre os muitos m\u00e9todos de detec\u00e7\u00e3o de mudan\u00e7as h\u00e1 o de detec\u00e7\u00f5es autom\u00e1ticas a partir de algoritmos, que simplificam os processamentos e capturam as transforma\u00e7\u00f5es de forma r\u00e1pida e sistem\u00e1tica. Assim, o objetivo desse trabalho \u00e9 entender como se comporta os algoritmos de detec\u00e7\u00e3o de mudan\u00e7as em uma classifica\u00e7\u00e3o h\u00edbrida integrada. Essa classifica\u00e7\u00e3o ser\u00e1 testada usando imagens de mesoresolu\u00e7\u00e3o como as dos sat\u00e9lites LANDSAT num contexto temporal de 35 anos em 8 datas e espacial que encobre todo o estado do Rio de Janeiro e suas complexidades de cobertura. O trabalho est\u00e1 constru\u00eddo pensando em resolver os problemas metodol\u00f3gicos da constru\u00e7\u00e3o desses algoritmos, na classifica\u00e7\u00e3o das mudan\u00e7as e na explora\u00e7\u00e3o desses algoritmos para entender suas vantagens e limita\u00e7\u00f5es. Ao fim tem-se que para o estado do rio de Janeiro os descritores do NDBI, SWIR 1 e SWIR 2 s\u00e3o o que melhor nos atendem para a identifica\u00e7\u00e3o r\u00e1pida de mudan\u00e7as de diferentes tipologias na \u00e1rea, onde o melhor estatisticamente e visualmente foi o NDBI.<\/p>\n\n\n\n
Palavras-Chaves<\/strong>: Mudan\u00e7as da Paisagem, Descritores Espectrais, Algoritmos de Mudan\u00e7a, Sensoriamento Remoto.<\/p>\n\n\n\nDynamic spectral descriptors and Classification by hybrid approach for Change Detection studies<\/p>\n\n\n\n
A B S T R A C T<\/strong><\/p>\n\n\n\nThe landscapes as we know and see them are constantly changing due to natural and anthropic processes of different spatial and temporal magnitudes. To understand these changes, they must necessarily be observable or measurable. Currently Remote Sensing is considered one of the most modern ways of monitoring the landscape due to methods applicable to its products that allow qualitative and quantitative analysis of changes in the landscape, caused by the complex patterns of land use and occupation over time. Among the many methods of detecting changes, there is automatic detection using algorithms, which simplify processing and capture transformations quickly and systematically. Thus, the objective of this work is to understand how the change detection algorithms behave in an integrated hybrid classification. This classification will be tested using mesoresolution images such as those of the LANDSAT satellites in a 35-year temporal context over 8 dates and a spatial one that covers the entire state of Rio de Janeiro and its coverage complexities. The work is built thinking about solving the methodological problems of the construction of these algorithms, in the classification of changes and in the exploration of these algorithms to understand their advantages and limitations. In the end we have that for the state of Rio de Janeiro the descriptors of NDBI, SWIR 1 and SWIR 2 are the ones that best serve us for the quick identification of changes of different types in the area, where the best statistically and visually was the NDBI.<\/p>\n\n\n\n
Keywords:\u00a0<\/strong>Landscape Changes, Spectral Descriptors, Landscape Change Algorithms, Remote Sensing.<\/object>38-207-1-PB<\/a> Download<\/a><\/div>\n\n\n\n<\/p>\n","protected":false},"excerpt":{"rendered":"
Resumo R E S U M O As paisagens como conhecemos e vemos est\u00e3o em constante mudan\u00e7a devido a processos<\/p>\n","protected":false},"author":2,"featured_media":2038,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0},"categories":[6,33,22,53,30],"tags":[],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/reativarambiental.com.br\/index.php?rest_route=\/wp\/v2\/posts\/2036"}],"collection":[{"href":"https:\/\/reativarambiental.com.br\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/reativarambiental.com.br\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/reativarambiental.com.br\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/reativarambiental.com.br\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=2036"}],"version-history":[{"count":1,"href":"https:\/\/reativarambiental.com.br\/index.php?rest_route=\/wp\/v2\/posts\/2036\/revisions"}],"predecessor-version":[{"id":2039,"href":"https:\/\/reativarambiental.com.br\/index.php?rest_route=\/wp\/v2\/posts\/2036\/revisions\/2039"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/reativarambiental.com.br\/index.php?rest_route=\/wp\/v2\/media\/2038"}],"wp:attachment":[{"href":"https:\/\/reativarambiental.com.br\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=2036"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/reativarambiental.com.br\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=2036"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/reativarambiental.com.br\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=2036"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}