Abstract : We consider the problem of tree species classification from high resolution aerial images based on radiometry, texture and a shape modeling. We use the notion of shape space proposed by Klassen et al., which provides a shape description invariant to translation, rotation and scaling. The shape features are extracted within a geodesic distance in the shape space. We then perform a classification using a SVM approach. We are able to show that the shape descriptors improve the classification performance relative to a classifier based on radiometric and textural descriptors alone. We obtain these results using high resolution Colour InfraRed (CIR) aerial images provided by the Swedish University of Agricultural Sciences. The image viewpoint is close to the nadir, i.e. the tree crowns are seen from above.
https://hal.inria.fr/inria-00465505
Contributeur : Maria Kulikova
<>
Soumis le : vendredi 19 mars 2010 - 16:26:31
Dernière modification le : lundi 5 novembre 2018 - 15:52:01
Document(s) archivé(s) le : mardi 22 juin 2010 - 10:49:17
Maria Kulikova, Meena Mani, Anuj Srivastava, Xavier Descombes, Josiane Zerubia. TREE SPECIES CLASSIFICATION USING RADIOMETRY, TEXTURE AND SHAPE BASED FEATURES. EUSIPCO, Sep 2007, Poznan, Poland. 2007. 〈inria-00465505〉
