Abstract
Vision-based semantic segmentation in urban scenarios is a key functionality for autonomous driving. Recent revolutionary results of deep convolutional neural networks (CNNs) foreshadow the advent of reliable classifiers to perform such visual tasks. However, CNNs require learning of many parameters from raw images; thus, having a sufficient amount of diverse images with class annotations is needed. These annotations are obtained via cumbersome, human labor which is particularly challenging for semantic segmentation since pixel-level annotations are required. In this chapter, we propose to use a combination of a virtual world to automatically generate realistic synthetic images with pixel-level annotations, and domain adaptation to transfer the models learned to correctly operate in real scenarios. We address the question of how useful synthetic data can be for semantic segmentation—in particular, when using a CNN paradigm. In order to answer this question we have generated a synthetic collection of diverse urban images, named SYNTHIA, with automatically generated class annotations and object identifiers. We use SYNTHIA in combination with publicly available real-world urban images with manually provided annotations. Then, we conduct experiments with CNNs that show that combining SYNTHIA with simple domain adaptation techniques in the training stage significantly improves performance on semantic segmentation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
SYNTHIA is available at http://synthia-dataset.net.
- 2.
Here we refer to the new SYNTHIA-RAND subset, extended after the CVPR version.
Acknowledgements
Authors want to thank Andrew Bagdanov for his help and proofreading and the next funding bodies: the Spanish MEC Project TRA2014-57088-C2-1-R, the Spanish DGT Project SPIP2014-01352, the People Programme (Marie Curie Actions) FP7/2007-2013 REA grant agreement no. 600388, and by the Agency of Competitiveness for Companies of the Government of Catalonia, ACCIO, the Generalitat de Catalunya Project 2014-SGR-1506, and to all the members of the SYNTHIA team.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this chapter
Cite this chapter
Ros, G. et al. (2017). Semantic Segmentation of Urban Scenes via Domain Adaptation of SYNTHIA. In: Csurka, G. (eds) Domain Adaptation in Computer Vision Applications. Advances in Computer Vision and Pattern Recognition. Springer, Cham. https://doi.org/10.1007/978-3-319-58347-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-58347-1_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-58346-4
Online ISBN: 978-3-319-58347-1
eBook Packages: Computer ScienceComputer Science (R0)