|
Towards Robust Semantic Segmentation using Deep Fusion
Abhinav Valada, Gabriel L. Oliveira, Thomas Brox, and Wolfram Burgard Robotics: Science and Systems (RSS 2016) Workshop, Are the Sceptics Right? Limits and Potentials of Deep Learning in Robotics 2016
valada16rssws.pdf
Notes: Robust semantic scene understanding of unstructured
environments is critical for robots operating in the real
world. Several inherent natural factors such as shadows, glare
and snow make this problem highly challenging, especially using
RGB images. In this paper, we propose the use of multispectral
and multimodal images to increase robustness of segmentation
in real-world outdoor environments. Deep Convolutional Neural
Network (DCNN) architectures define the state of the art in various
segmentation tasks. However, architectures that incorporate
fusion have not been sufficiently explored. We introduce early
and late fusion architectures for dense pixel-wise segmentation
from RGB, Near-InfraRed (NIR) channels, and depth data. We
identify data augmentation strategies that enable training of very
deep fusion models using small datasets. We qualitatively and
quantitatively evaluate our approach and show it exceeds several
other state-of-the-art architectures. In addition, we present
experimental results for segmentation under challenging realworld
conditions. The dataset and demos are publicly available
at http://deepscene.cs.uni-freiburg.de.
BibTeX:
@inproceedings{valada16rssws,
author = {Abhinav Valada and Gabriel Oliveira and Thomas Brox and Wolfram Burgard},
title = {Towards Robust Semantic Segmentation using Deep Fusion},
booktitle = {Robotics: Science and Systems (RSS 2016) Workshop, Are the Sceptics Right? Limits and Potentials of Deep Learning in Robotics},
year = 2016,
month = jun,
url = {http://ais.informatik.uni-freiburg.de/publications/papers/valada16rssws.pdf},
address = {Ann Arbor, USA}
}
|
|