A NEURAL NETS URBAN LAND COVER CLASSIFICATION: A CASE STUDY OF BRNO (CZECHIA).

KÝNOVÁ, Andrea and Petr DOBROVOLNÝ. A NEURAL NETS URBAN LAND COVER CLASSIFICATION: A CASE STUDY OF BRNO (CZECHIA). Online. Acta Universitatis Carolinae Geographica. 2015, vol. 50, No 2, p. 153-163. ISSN 0300-5402. Available from: https://dx.doi.org/10.14712/23361980.2015.94. [citováno 2024-04-23]

Basic information

• Original name: A NEURAL NETS URBAN LAND COVER CLASSIFICATION: A CASE STUDY OF BRNO (CZECHIA).
• Authors: KÝNOVÁ, Andrea (203 Czech Republic, belonging to the institution) and Petr DOBROVOLNÝ (203 Czech Republic, belonging to the institution)
• Edition: Acta Universitatis Carolinae Geographica, 2015, 0300-5402.

Other information

• Original language: English
• Type of outcome: Article in a journal
• Field of Study: Earth magnetism, geodesy, geography
• Country of publisher: Czech Republic
• Confidentiality degree: is not subject to a state or trade secret
• WWW: URL
• RIV identification code: RIV/00216224:14310/15:00085925
• Organization unit: Faculty of Science
• Doi: http://dx.doi.org/10.14712/23361980.2015.94
• Keywords in English: image classification; multilayer perceptron; urban land cover; ASTER
• Tags: AKR, rivok
• Tags: Reviewed

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.

Links

• MUNI/A/0952/2013, interní kód MU: Name: Analýza, hodnocení a vizualizace globálních environmentálních změn v krajinné sféře Země (Acronym: AVIGLEZ)

Investor: Masaryk University, Category A