Impact of contextual information integration on pixel fusion

Abstract

Pixel fusion is used to elaborate a classification method at pixel level. It needs to take into account the as accurate as possible information and take advantage of the statistical learning of the previous measurements acquired by sensors. The classical probabilistic fusion methods lack performance when the previous learning is not representative of the real measurements provided by sensors. The Dempster-Shafer theory is then introduced to face this disadvantage by integrating further information which is the context of the sensor acquisitions. In this paper, we propose a formalism of modeling of the sensor reliability in the context that leads to two methods of integration: the first one amounts to integrate this further information in the fusion rule as degrees of trust and the second models the sensor reliability directly as mass function. These two methods are compared in the case where the sensor reliability depends on an atmospheric disturbance: the water vapor.