Fully Convolutional Neural Networks for Fast Road Detection

Data: 06/04/2018
Horário: 15h
Local: Auditório do CCSL

Ministrante: Dr. Caio César Teodoro Mendes (ICMC-USP)

Título: Fully Convolutional Neural Networks for Fast Road Detection

Resumo: Road detection is a crucial task in autonomous navigation
systems. It is responsible for delimiting the road area and hence the
free and valid space for maneuvers. In this paper,we consider the
visual road detection problem where, given animage, the objective is
to classify every of its pixels into road or non-road. We address this
task by proposing a convolutionalneural network architecture. We are
especially interested in a model that takes advantage of a large
contextual window while maintaining a fast inference. We achieve this
by using a Network-in-Network (NiN) architecture and by converting the
model into a fully convolutional network after training. Experiments
have been conducted to evaluate the effects of different contextual
window sizes (the amount of contextual information) and also to
evaluate the NiN aspect of the proposed architecture. Finally, we
evaluated our approach using the KITTI road detection benchmark
achieving results in line with other state-of-the-art methods while
maintaining real-time inference. The benchmark results also reveal
that the inference time of our approach is unique at this level of
accuracy, being two orders of magnitude faster than other methods with
similar performance.