Classification of urban environments using feature extraction and random forest

Multisource remote sensing data provide information of high relevance for classification and climate studies in urban areas and are of particular interest for regional and global climate science. To classify the urban environment using predefined Local Climate Zones we propose a method using feature...

Full description

Saved in:
Bibliographic Details
Main Authors: Souza dos Anjos, Camila, Goncalves Lacerda, Marielcio, do Livramento Andrade, Leidiane, Neves Salles, Roberto
Format: Conference Proceeding
Language:English
Subjects:
Data Fusion
Earth
Feature extraction
Image segmentation
Land Use Classification
Local Climate Zone
Meteorology
Radio frequency
Random Forest
Remote sensing
Urban areas
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Multisource remote sensing data provide information of high relevance for classification and climate studies in urban areas and are of particular interest for regional and global climate science. To classify the urban environment using predefined Local Climate Zones we propose a method using feature extraction, image segmentation and decision trees. The method extracts features and segments from the multisource data. Later objects are selected to create decision trees using the random forest algorithm. Finally the images are classified by the earlier generated trees. The multispectral images were from Landsat 8 and Sentinel 2 resampled to 100m. Visual analysis and quantitative testing of results show the effectiveness of our method.
ISSN:2153-7003
DOI:10.1109/IGARSS.2017.8127174