Causal Markov mesh hierarchical modeling for the contextual classification of multiresolution satellite images

Alessandro Montaldo (1) , Luca Fronda (1) , Ihsen Hedhli (2, 3) , Gabriele Moser (1) , Sebastiano B. Serpico (1) , Josiane Zerubia (3, 4)

1 UniGe - Università degli studi di Genova = University of Genoa
2 ULaval - Université Laval [Québec]
3 CRISAM - Inria Sophia Antipolis - Méditerranée
4 AYIN - Models of spatio-temporal structure for high-resolution image processing

In this paper, we address the problem of the joint classifica-tion of multiple images acquired on the same scene at different spatial resolutions. From an application viewpoint, thisproblem is of importance in several contexts, including, mostremarkably, satellite and aerial imagery. From a methodolog-ical perspective, we use a probabilistic graphical approachand adopt a hierarchical Markov mesh framework that we have recently developed and models the spatial-contextual classification of multiresolution and possibly multisensor images. Here, we focus on the methodological properties of this framework. First, we prove the causality of the model, a highly desirable property with respect to the computationa lcost of the inference. Then, we prove the expression of the marginal posterior mode criterion for this model and discuss the related assumptions. Experimental results with multi-spectral and panchromatic satellite images are also presented.

Mots clés: Markov mesh random field; Semantic image segmentation; Multiresolution images; Hierarchical Markov random fields; Causality

Domaines: Traitement du signal et de l'image [eess.SP]; Sciences de l'ingénieur [physics]; Mathématiques [math]; Statistiques [math.ST]

Alessandro Montaldo, Luca Fronda, Ihsen Hedhli, Gabriele Moser, Sebastiano B. Serpico, et al.. Causal Markov mesh hierarchical modeling for the contextual classification of multiresolution satellite images. ICIP 2019 - IEEE International Conference on Image Processing, Sep 2019, Taipei, Taiwan. ⟨hal-02157081⟩