Multi-scale data fusion using Dempster-Shafer evidence theory

Authors:
S. Le Hé/garat-Mascle;D. Richard;C. Ottlé/
Affiliations:
CETP/CNRS, 10-12 av. de l'Europe, 78140 Vé/lizy, France. Tel.: +33 1 3925 49 34/ Fax: +33 1 39 25 49 22/ E-mail: sylvie.mascle@cetp.ipsl.fr;CETP/CNRS, 10-12 av. de l'Europe, 78140 Vé/lizy, France. Tel.: +33 1 3925 49 34/ Fax: +33 1 39 25 49 22/ E-mail: sylvie.mascle@cetp.ipsl.fr;CETP/CNRS, 10-12 av. de l'Europe, 78140 Vé/lizy, France. Tel.: +33 1 3925 49 34/ Fax: +33 1 39 25 49 22/ E-mail: sylvie.mascle@cetp.ipsl.fr
Venue:
Integrated Computer-Aided Engineering
Year:
2003

Citing 0
Cited 7

Fault diagnosis of machines based on D-S evidence theory. Part 1: D-S evidence theory and its improvement

Pattern Recognition Letters
Using Dempster---Shafer to incorporate knowledge into satellite image classification

Artificial Intelligence Review
Decision-based fuzzy image restoration for noise reduction based on evidence theory

Expert Systems with Applications: An International Journal
Fusion of elevation data into satellite image classification using refined production rules

ICIAR'11 Proceedings of the 8th international conference on Image analysis and recognition - Volume Part I
Autonomous and deterministic clustering for evidence-theoretic classifier

ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
Using dempster-shafer theory in MCF systems to reject samples

MCS'05 Proceedings of the 6th international conference on Multiple Classifier Systems
Multi-objective optimization of problems with epistemic uncertainty

EMO'05 Proceedings of the Third international conference on Evolutionary Multi-Criterion Optimization

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the remote sensing domain, the combination of multi-scale satellite data appears as a new challenge for the signal processing community. This approach will lead to strong advances in Earth monitoring and continental land cover classifications by use of the complementary of the data presenting either high spatial resolution or high time repetitiveness. For the modelling of the mixed feature of the low spatial resolution pixels, and those of the partial ignorance (class confusion) when time information is not sufficient, we propose an algorithm based on the Dempster-Shafer evidence theory, which allows to model both ignorance and imprecision, and to consider compound hypotheses such as unions of classes. It has been applied on simulated data and actual data (SPOT/HRV image and NOAA/AVHRR series), and in both cases, the results show unambiguously the major improvement brought by such a data fusion, and the performance of the proposed method.