Case Study on Vector Spatial Analysis - Open Source Geospatial Tools: Applications in Earth Observation - page 276

Chapter 16
Case Study on Vector Spatial Analysis
This case study will demonstrate the creation of a vector based training dataset for
a study area based in Houston, Texas. This task fits within the context of the IEEE
GRSS Data Fusion Contest. The data created can be used as a training dataset for
supervised image classification. In short, a training dataset consists of labeled pixels
that are used by the rules of the image classification algorithm to classify unlabeled
pixels. The objective of the case study is to digitize vector spatial data in Google
Earth and then pre-process them using GDAL/OGR to create a dataset that is ready
to be used within an image classification workflow. We have decided to introduce
Google Earth as it provides a rich time-series of satellite imagery both, high and
very high resolution satellite data for the entire globe. It also includes contextual
information regarding place names and landmarks.
In addition, Google Earth's interface is easy-to-use for the creation of simple
vectorial data. We note that Google Earth is not an open source application, but we
feel that it is a reliable tool that readily provides access to geo-referenced satellite
imagery in a consistent manner for the entire globe. We equally acknowledge that
the OpenLayers plugin for QGIS provides direct access to Google, OpenStreetMap
and Bing data via Web services. However, we have not used this approach in this
case study as it is covered in Chap. 17 and other topics on QGIS.
The principal steps that will be carried out in this case study are to:
1. Use Google Earth to create polygon datasets;
2. Preprocess polygons using OGR;
3. Reproject and export the dataset to the required format.
16.1 Digitizing in Google Earth
To begin, it is necessary to launch Google Earth (and in doing so, we assume that
you have a working Internet connection as it is necessary to retrieve the satellite
imagery, Fig. 16.1 ). You can either navigate to Google Earth within your Window