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 533105
Title Optimising Realism of Synthetic Agricultural Images using Cycle Generative Adversarial Networks
Author(s) Barth, R.; IJsselmuiden, J.M.M.; Hemming, J.; Henten, E.J. van
Source In: Proceedings of the IEEE IROS workshop on Agricultural Robotics / Kounalakis, Tsampikos, van Evert, Frits, Ball, David Michael, Kootstra, Gert, Nalpantidis, Lazaros, Wageningen : Wageningen University & Research - p. 18 - 22.
Department(s) WUR GTB Tuinbouw Technologie
Farm Technology Group
WUR GTB Teelt & Gewasfysiologie
Publication type Contribution in proceedings
Publication year 2017
Abstract A bottleneck of state-of-the-art machine learning methods, e.g. deep learning, for plant part image segmentation in agricultural robotics is the requirement of large manually annotated datasets. As a solution, large synthetic datasets including ground truth can be rendered that realistically reflect the empirical situation. However, a dissimilarity gap can remain between synthetic and empirical data by incomplete manual modelling. This paper contributes to closing this gap by optimising the realism of synthetic agricultural images using unsupervised cycle generative adversarial networks, enabling unpaired image-to-image translation from the synthetic to empirical domain and vice versa. For this purpose, the Capsicum annuum (sweet- or bell pepper) dataset was used, containing 10,500 synthetic and 50 empirical annotated images. Additionally, 225 unlabelled empirical images were used. We hypothesised that the similarity of the synthetic images with the empirical images increases qualitatively and quantitively when translated to the empirical domain and investigated the effect of the translation on the factors color, local texture and morphology. Results showed an increased mean class color distribution correlation with the empirical dataset from 0.62 prior and 0.90 post translation of the synthetic dataset. Qualitatively, synthetic images translate very well in local features such as color,
illumination scattering and texture. However, global features like plant morphology appeared not to be translatable.
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.