Find Your Own Way WeaklySupervised Segmentation of Path Proposals for Urban Autonomy
>> YOUR LINK HERE: ___ http://youtube.com/watch?v=rbZ8ck_1nZk
Autonomous vehicles should reliably detect obstacles and plan paths without always relying on extensive manually labelled datasets or expensive sensors. In this video we present our work towards segmenting path proposals and obstacles using a driver to implicitly label valid paths at train time, then only using monocular camera at run time. Details of the approach can be found at: https://arxiv.org/abs/1610.01238 • D. Barnes, W. Maddern and I. Posner: Find Your Own Way: Weakly-Supervised Segmentation of Path Proposals for Urban Autonomy, IEEE International Conference on Robotics and Automation (ICRA), 2017.
#############################
