Semantic Annotation of Satellite Images Using Latent Dirichlet Allocation

In this letter, we are interested in the annotation of large satellite images, using semantic concepts defined by the user. This annotation task combines a step of supervised classification of patches of the large image and the integration of the spatial information between these patches. Given a tr...

Full description

Saved in:
Bibliographic Details
Published in:IEEE geoscience and remote sensing letters 2010-01, Vol.7 (1), p.28-32
Main Authors: Lienou, Marie, Maitre, Henri, Datcu, Mihai
Format: Article
Language:English
Subjects:
Allocations
Annotations
Classification
Computer Science
Data mining
Dirichlet problem
Earth
Feature extraction
Image analysis
Image representation
Indexing
Information Retrieval
Large-image annotation
latent Dirichlet allocation (LDA)
Layout
Linear discriminant analysis
Satellites
Semantics
spatial information
Spatial resolution
Tasks
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this letter, we are interested in the annotation of large satellite images, using semantic concepts defined by the user. This annotation task combines a step of supervised classification of patches of the large image and the integration of the spatial information between these patches. Given a training set of images for each concept, learning is based on the latent Dirichlet allocation (LDA) model. This hierarchical model represents each item of a collection as a random mixture of latent topics, where each topic is characterized by a distribution over words. The LDA-based image representation is obtained using simple features extracted from image words. We then exploit the capability of the LDA model to assign probabilities to unseen images, in order to classify the patches of the large image into the semantic concepts, using the maximum-likelihood method. We conduct experiments on panchromatic QuickBird images with 60-cm resolution. Taking into account the spatial information between the patches shows to improve the annotation performance.
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2009.2023536