Hierarchical and multiscale Mean Shift segmentation of population grid

Johanna Baro (1) , Etienne Come (1) , Patrice Aknin (1) , Olivier Bonin (2)

1 IFSTTAR/COSYS/GRETTIA - Génie des Réseaux de Transport Terrestres et Informatique Avancée
2 LVMT - Laboratoire Ville, Mobilité, Transport

The Mean Shift (MS) algorithm allows to identify clusters that are catchment areas of modes of a probability density function (pdf). We propose to use a multiscale and hierarchical implementation of the algorithm to process grid data of population and identify automatically urban centers and their dependant sub-centers through scales. The multiscale structure is obtained by increasing iteratively the bandwidth of the kernel used to define the pdf on which the MS algorithm works. This will induce a hierarchical structure over clusters since modes will merge together when the bandwidth parameter increases.

Mots clés: POPULATION; ALGORITHME; BASE DE DONNEES

Domaines: Sociologie

Johanna Baro, Etienne Come, Patrice Aknin, Olivier Bonin. Hierarchical and multiscale Mean Shift segmentation of population grid. 22th European Symposium on Artificial Neural Networks (ESANN 2013), Apr 2013, Belgium. 6p. ⟨hal-00863318⟩