Staff Publications

Staff Publications

  • external user (warningwarning)
  • Log in as
  • language uk
  • About

    'Staff publications' is the digital repository of Wageningen University & Research

    'Staff publications' contains references to publications authored by Wageningen University staff from 1976 onward.

    Publications authored by the staff of the Research Institutes are available from 1995 onwards.

    Full text documents are added when available. The database is updated daily and currently holds about 240,000 items, of which 72,000 in open access.

    We have a manual that explains all the features 

Record number 545332
Title Detecting Animals in Repeated UAV Image Acquisitions by Matching CNN Activations with Optimal Transport
Author(s) Kellenberger, Benjamin; Marcos, Diego; Courty, Nicolas; Tuia, Devis
Source In: 2018 IEEE International Geoscience & Remote Sensing Symposium Proceedings. - IEEE Xplore - ISBN 9781538671511 - p. 3643 - 3646.
Event IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, 2018-07-22/2018-07-27
DOI https://doi.org/10.1109/IGARSS.2018.8519012
Department(s) Laboratory of Geo-information Science and Remote Sensing
PE&RC
Publication type Contribution in proceedings
Publication year 2018
Abstract Repeated animal censuses are crucial for wildlife parks to ensure ecological equilibriums. They are increasingly conducted using images generated by Unmanned Aerial Vehicles (UAVs), often coupled to semi-automatic object detection methods. Such methods have shown great progress also thanks to the employment of Convolutional Neural Networks (CNNs), but even the best models trained on the data acquired in one year struggle predicting animal abundances in subsequent campaigns due to the inherent shift between the datasets. In this paper we adapt a CNN-based animal detector to a follow-up UAV dataset by employing an unsupervised domain adaptation method based on Optimal Transport. We show how to infer updated labels from the source dataset by means of an ensemble of bootstraps. Our method increases the precision compared to the unmodified CNN, while not requiring additional labels from the target set.
Comments
There are no comments yet. You can post the first one!
Post a comment
 
Please log in to use this service. Login as Wageningen University & Research user or guest user in upper right hand corner of this page.