Hierarchical image content analysis with an embedded marked point process framework

In this paper we introduce a probabilistic approach for extracting complex hierarchical object structures from digital images. The proposed framework extends conventional Marked Point Process models by (i) admitting object-subobject ensembles in parent-child relationships and (ii) allowing corresponding objects to form coherent object groups. The proposed method is demonstrated in three application areas: optical circuit inspection, built in area analysis in aerial images, and traffic monitoring on airborne Lidar data.