Supervised learning on graphs of spatio-temporal similarity in satellite image sequences

TL;DR

This paper introduces a supervised learning approach for recognizing and retrieving similar spatio-temporal patterns in satellite image sequences by attaching semantics to graph representations of physical phenomena.

Contribution

It presents a novel supervised learning methodology that links user-specific semantics to graph-based models of satellite image sequences using Bayesian inference.

Findings

Effective recognition of similar spatio-temporal phenomena demonstrated.

Probabilistic retrieval based on user-defined semantics achieved.

Method applied successfully on multi-spectral SPOT images.

Abstract

High resolution satellite image sequences are multidimensional signals composed of spatio-temporal patterns associated to numerous and various phenomena. Bayesian methods have been previously proposed in (Heas and Datcu, 2005) to code the information contained in satellite image sequences in a graph representation using Bayesian methods. Based on such a representation, this paper further presents a supervised learning methodology of semantics associated to spatio-temporal patterns occurring in satellite image sequences. It enables the recognition and the probabilistic retrieval of similar events. Indeed, graphs are attached to statistical models for spatio-temporal processes, which at their turn describe physical changes in the observed scene. Therefore, we adjust a parametric model evaluating similarity types between graph patterns in order to represent user-specific semantics attached to spatio-temporal phenomena. The learning step is performed by the incremental definition of similarity types via user-provided spatio-temporal pattern examples attached to positive or/and negative semantics. From these examples, probabilities are inferred using a Bayesian network and a Dirichlet model. This enables to links user interest to a specific similarity model between graph patterns. According to the current state of learning, semantic posterior probabilities are updated for all possible graph patterns so that similar spatio-temporal phenomena can be recognized and retrieved from the image sequence. Few experiments performed on a multi-spectral SPOT image sequence illustrate the proposed spatio-temporal recognition method.