Régis Caloz

Learn More
We propose an algorithm for very high-resolution satellite image classification that combines non-supervised segmentation with a supervised classification. Both multi-spectral data and local spatial priors are used in the Gaussian hidden Markov random field (GHMRF) model for the segmentation. Then, two classifiers, Mahalanobis distance classifier and SVM,(More)
We introduce a new method to detect signatures of natural selection in the genome based on the application of spatial analysis, with the contribution of Geographical Information Systems, environmental variables, molecular data, and multiple univariate logistic regressions. Its use allows the identification of the same genomic regions as revealed by a(More)
Forest fragmentation translates a geographical isolation process and has been shown to influence the abundance, the movements and persistence of many species. The structure of the highly fragmented forests of Monteverde, Costa Rica, may exercise a relevant influence on the species richness and individual abundance of many forestdwelling understory bird(More)
  • 1