Map-Supervised Road Detection

Ankit Laddha, Mehmet Kemal Kocamaz, Luis E. Navarro-Serment, and Martial Hebert

Abstract:

We propose an approach to detect drivable road
area in monocular images. It is a self-supervised approach
which doesn’t require any human road annotations on images
to train the road detection algorithm. Our approach reduces
human labeling effort and makes training scalable. We combine
the best of both supervised and unsupervised methods in
our approach. First, we automatically generate training road
annotations for images using OpenStreetMap
, vehicle pose
estimation sensors, and camera parameters. Next, we train
a Convolutional Neural Network (CNN) for road detection
using these annotations. We show that we are able to generate
reasonably accurate training annotations in KITTI data-set [1].
We achieve state-of-the-art performance among the methods
which do not require human annotation effort.