Find Your Own Way: Weakly-Supervised Segmentation of Path Proposals for Urban Autonomy
This addresses the need for cost-effective, scalable perception in autonomous driving by reducing reliance on manual annotation and explicit road modeling, though it is incremental as it builds on existing weakly-supervised and segmentation methods.
The paper tackles the problem of segmenting drivable paths and obstacles for autonomous driving in complex urban environments using only a monocular camera, achieving reliable segmentation across diverse conditions on KITTI and Oxford RobotCar datasets.
We present a weakly-supervised approach to segmenting proposed drivable paths in images with the goal of autonomous driving in complex urban environments. Using recorded routes from a data collection vehicle, our proposed method generates vast quantities of labelled images containing proposed paths and obstacles without requiring manual annotation, which we then use to train a deep semantic segmentation network. With the trained network we can segment proposed paths and obstacles at run-time using a vehicle equipped with only a monocular camera without relying on explicit modelling of road or lane markings. We evaluate our method on the large-scale KITTI and Oxford RobotCar datasets and demonstrate reliable path proposal and obstacle segmentation in a wide variety of environments under a range of lighting, weather and traffic conditions. We illustrate how the method can generalise to multiple path proposals at intersections and outline plans to incorporate the system into a framework for autonomous urban driving.