A neural nets urban land cover classification: a case study of Brno (Czechia)

Abstract

Accurate and updated land cover maps provide crucial basic information in a number of important enterprises, with sustainable development and regional planning far from the least of them. Remote sensing is probably the most efficient approach to obtaining a land cover map. However, certain intrinsic limitations limit the accuracy of automatic approaches to image classification. Classifications within highly heterogeneous urban areas are especially challenging. This study makes a presentation of multilayer perceptron (MLP), an artificial neural network (ANN), as an applicable approach to image classification. Optimal MLP architecture parameters were established by means of a training set. The resulting network was used to classify a sub-scene within ASTER imagery. The results were evaluated against a test dataset. The overall accuracy of classification was 94.8%. This is comparable to classification results from a maximum likelihood classifier (MLC) used for the same image. In built-up areas, MLP did not exaggerate built-up areas at the expense of other classes to the same extent as MLC.

Utilização Do Infravermelho Termal Na Análise Espaço Temporal Da Temperatura De Superfície E Ilhas De Calor Urbanas

“…No entanto, Small (2002) alerta para a difi culdade de trabalhar com áreas urbanas utilizando imagens de média resolução espacial, isto se deve a heterogeneidade das superfícies urbanas (concreto, asfalto, árvores, telhas, metal, dentre outros). Para tanto, diversas técnicas e estudos foram desenvolvidos para melhorar a precisão na caracterização dos tipos de cobertura da terra no espaço urbano, como por exemplo classifi cação híbrida (ALBERT et al, 2004), análise de pixel mistura (SMALL, 2002;MICHISHITA, 2012), redes neurais artifi ciais (KÍNOVÁ, 2015), e índices radiométricos para áreas construídas (ZHA, 2003;XU, 2007).…”