Affordable Access

Indexing of satellite images using structural information

Authors
  • Bhattacharya, Avik
Publication Date
Dec 14, 2007
Source
HAL-SHS
Keywords
Language
English
License
Unknown
External links

Abstract

The properties of road networks vary considerably from one geographical environment to another. The networks pertaining in a satellite image can therefore be used to classify and retrieve such environments. In this work, we propose to classy geographical environment using geometrical and topological features computed from the road networks. The limitations of road extraction methods in dense urban areas was circumvented by segmenting the urban regions and computing a second set of geometrical and topological features from them. The small images forming our database were extracted from images of the SPOT5 satellite with 5m resolution (each image of size 512x512 pixels). The set of geometrical and topological features computed from the road networks and urban regions are used to classify the pre-defined geographical classes. In order to avoid the burden of feature dimensionality and reduce the classification performance, feature selection was performed using Fisher Linear Discriminant (FLD) analysis and an one-vs-rest linear Support Vector Machine (SVM) classification was performed on the selected feature set. The impact of spatial resolution and size of images on the feature set have been explored. Tests were performed on a database with images of 10m resolution and on a database with 5m resolution images each of size 256x256 pixels. This approach allows also to classify large SPOT5 images with patches of size 512x512. In this case, a one-vs-rest Gaussian kernel SVM classification method was used to classify this large image. The classification labels the image patches with the one having the maximum geographical coverage of the area associated in the large image.

Report this publication

Statistics

Seen <100 times