Railway Detection: From Filtering to Segmentation Networks
Résumé
This paper deals with classification of remote sensing data to extract objects for industrial mapping. While land-cover or urban mapping have been extensively studied, industrial cartography remains a field yet to explore, in spite of tremendous needs. We present and compare here four approaches for railway detection in very high resolution images. They use various kind of filtering approaches, including the trained filters of fully convolutional networks. Moreover, they benefit from different a-priori and post-processing techniques to make them more robust. We evaluate all approaches on a challenging dataset captured on an operating station site with complex objects.
Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...