Authors:
Clemens-Alexander Brust
;
Sven Sickert
;
Marcel Simon
;
Erik Rodner
and
Joachim Denzler
Affiliation:
Friedrich Schiller University of Jena, Germany
Keyword(s):
Convolutional Neural Networks, Patch Classification, Road Detection, Semantic Segmentation, Scene Understanding.
Related
Ontology
Subjects/Areas/Topics:
Computer Vision, Visualization and Computer Graphics
;
Image and Video Analysis
;
Segmentation and Grouping
Abstract:
Classifying single image patches is important in many different applications, such as road detection or scene understanding. In this paper, we present convolutional patch networks, which are convolutional networks learned to distinguish different image patches and which can be used for pixel-wise labeling. We also show how to incorporate spatial information of the patch as an input to the network, which allows for learning spatial priors for certain categories jointly with an appearance model. In particular, we focus on road detection and urban scene understanding, two application areas where we are able to achieve state-of-the-art results on the KITTI as well as on the LabelMeFacade dataset.
Furthermore, our paper offers a guideline for people working in the area and desperately wandering through all the painstaking details that render training CNs on image patches extremely difficult.