Road Structure Refined CNN for Road Extraction in Aerial Image

Yanan Wei, Zulin Wang, Mai XuIEEE GRSL 2017 · OpenReview

Abstract

In this letter, we propose a road structure refined convolutional neural network (RSRCNN) approach for road extraction in aerial images. In order to obtain structured output of road extraction, both deconvolutional and fusion layers are designed in the architecture of RSRCNN. For training RSRCNN, a new loss function is proposed to incorporate the geometric information of road structure in cross-entropy loss, thus called road-structure-based loss function. Experimental results demonstrate that the trained RSRCNN model is able to advance the state-of-the-art road extraction for aerial images, in terms of precision, recall, F-score, and accuracy.
BibTeX
@article{wei2017road,
  author = {Yanan Wei and Zulin Wang and Mai Xu},
  title = {{Road Structure Refined CNN for Road Extraction in Aerial Image}},
  journal = {IEEE Geosci. Remote. Sens. Lett.},
  year = {2017},
  url = {https://openreview.net/forum?id=KjCV06mLsM8-},
}

Loading related content...

Figure