Transportation where people leave: An introduction
Franklin, Rachel S. ; Leeuwen, Eveline S. van; Paez, Antonio - \ 2018
In: Advances in Transport Policy and Planning / Franklin, Rachel S., Van Leeuwen, Eveline S., Paez, Antonio, Elsevier B.V. (Advances in Transport Policy and Planning ) - ISBN 9780128154540 - p. 1 - 14.
Cities - Demographic aging - Exurbia - Population loss - Rural - Suburbia - Transportation
Transportation means access: to jobs, information, communities, and services. When depopulation occurs a number of questions arise around the central query: what was and will be the role of transportation? This volume engages with several aspects of the depopulation-transportation topic and at multiple geographic scales—from the national and regional to the city- and neighborhood-level. In this chapter, we provide an overview of the challenges associated with population loss and how various aspects of transportation research intersect with these issues. We then summarize the chapters included in this volume, showing how they connect to larger emerging research themes, as well as to each other.
Multitemporal classification without new labels : A solution with optimal transport
Tuia, Devis ; Flamary, Rémi ; Rakotomamonjy, Alain ; Courty, Nicolas - \ 2015
In: 2015 8th International Workshop on the Analysis of Multitemporal Remote Sensing Images, Multi-Temp 2015. - Institute of Electrical and Electronics Engineers Inc. (2015 8th International Workshop on the Analysis of Multitemporal Remote Sensing Images, Multi-Temp 2015 ) - ISBN 9781467371193
Adaptation models - Buildings - Couplings - Estimation - Predictive models - Remote sensing - Transportation
Re-using models trained on a specific image acquisition to classify landcover in another image is no easy task. Illumination effects, specific angular configurations, abrupt and simple seasonal changes make that the spectra observed, even though representing the same kind of surface, drift in a way that prevents a non-adapted model to perform well. In this paper we propose a relative normalization technique to perform domain adaptation, i.e. to make the data distribution in the images more similar before classification. We study optimal transport as a way to match the image-specific distributions and propose two regularization schemes, one unsupervised and one semi-supervised, to obtain more robust and semantic matchings. Code is available at http://remi.flamary.com/soft/soft-transp.html. Experiments on a challenging triplet of WorldView2 images, comparing three neighborhoods of the city of Zurich at different time instants, confirm the effectiveness of the proposed method that can perform adaptation in these non-coregistered and very different urban case studies.