Back to articles
Volume: 29 | Article ID: art00010
Free-Space Detection with Self-Supervised and Online Trained Fully Convolutional Networks
  DOI :  10.2352/ISSN.2470-1173.2017.19.AVM-021  Published OnlineJanuary 2017

Recently, vision-based Advanced Driver Assist Systems have gained broad interest. In this work, we investigate free-space detection, for which we propose to employ a Fully Convolutional Network (FCN). We show that this FCN can be trained in a selfsupervised manner and achieve similar results compared to training on manually annotated data, thereby reducing the need for large manually annotated training sets. To this end, our selfsupervised training relies on a stereo-vision disparity system, to automatically generate (weak) training labels for the color-based FCN. Additionally, our self-supervised training facilitates online training of the FCN instead of offline. Consequently, given that the applied FCN is relatively small, the free-space analysis becomes highly adaptive to any traffic scene that the vehicle encounters. We have validated our algorithm using publicly available data and on a new challenging benchmark dataset that is released with this paper. Experiments show that the online training boosts performance with 5% when compared to offline training, both for Fmax and AP.

Subject Areas :
Views 62
Downloads 2
 articleview.views 62
 articleview.downloads 2
  Cite this article 

Willem P. Sanberg, Gijs Dubbleman, Peter H.N. de With, "Free-Space Detection with Self-Supervised and Online Trained Fully Convolutional Networksin Proc. IS&T Int’l. Symp. on Electronic Imaging: Autonomous Vehicles and Machines,  2017,  pp 54 - 61,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2017
Electronic Imaging
Society for Imaging Science and Technology