Nalazite se na CroRIS probnoj okolini. Ovdje evidentirani podaci neće biti pohranjeni u Informacijskom sustavu znanosti RH. Ako je ovo greška, CroRIS produkcijskoj okolini moguće je pristupi putem poveznice www.croris.hr
izvor podataka: crosbi !

Getting The Act Together: Segmentation-Based Land Cover Classification Using RapidEye Imagery And Open Street Map Ancillary Data (CROSBI ID 639172)

Prilog sa skupa u zborniku | sažetak izlaganja sa skupa | međunarodna recenzija

Valožić, Luka Getting The Act Together: Segmentation-Based Land Cover Classification Using RapidEye Imagery And Open Street Map Ancillary Data. 2016

Podaci o odgovornosti

Valožić, Luka

engleski

Getting The Act Together: Segmentation-Based Land Cover Classification Using RapidEye Imagery And Open Street Map Ancillary Data

The research deals with land cover classification by means of object-based image analysis and geoprocessing in GIS software. The goal of the research is the overall improvement of classification results obtained from preceding rule-based land cover classification, by utilising ancillary vector data. The area of interest is the City of Zagreb in Croatia (641 sq km). The choice of suitable remote sensing data requires the settling of multiple criteria such as the quality and the quantity of data, as well as the price. This research is based on 2015 RapidEye multispectral satellite imagery. Ancillary data is often required for land cover classification but its appropriateness for such task raises similar questions. Initial examination of acquired Open Street Map shapefiles confirms the assumption that the mixture of urban, peri-urban, rural, and even protected areas, present in the administrative territory of the City of Zagreb, is sufficiently covered and interwoven with OSM data. Furthermore, such crowdsourced data is edited and updated frequently. Intent of the research is to find a solution for land cover classification of geographically heterogeneous region by reconciling the need for convenient and affordable spatial data. Preprocessing and postprocessing tasks are performed in ArcGIS 10.3.1 and they include coregistration of several datasets that originate from different sources, geographic transformations, and principle component analysis of multispectral imagery. Additionally, GIS software is used for spatial data management and visualization, including analyses previews and the cartographic representations of the final results of the research. The classification process itself is performed using eCognition Developer 9.0. Rule-based classification is executed on image segments created by the multiresolution segmentation algorithm. Careful examination of datasets leads to the threshold values for arithmetic features such as vegetation indices, and values derived from principle component analysis, as well as to conditions concerning presence of critical vector data acquired from the OSM. Classification accuracy is assessed by error matrix. Aerial and satellite images of higher spatial resolution than RapidEye’s are used as reference data for the error matrix. This research is part of CRORURIS – interdisciplinary project that is focused on the study of changes in the rural areas of Croatia and aims to develop framework for identification and geographical differentiation of predominant trends and key uncertainties as well as their projection by using statistical modelling and Delphi method, and to construct alternative future scenarios and relate them to the context of rural Europe.

OBIA; Land Cover Classification; GIS; RapidEye; Open Street Map

Izrađeno kao dio projekta Hrvatske zaklade za znanost: Primjena metode scenarija u planiranju i razvoju ruralnih područja Hrvatske (HRZZ-4513)

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

nije evidentirano

Podaci o prilogu

2016.

objavljeno

Podaci o matičnoj publikaciji

Podaci o skupu

GEOBIA 2016 "Solutions & Synergies"

predavanje

12.09.2016-16.09.2016

Enschede, Nizozemska

Povezanost rada

Geografija, Informacijske i komunikacijske znanosti

Poveznice