The Oxford Road Boundaries Dataset

Conference item

In this paper we present The Oxford Road Boundaries Dataset, designed for training and testing machine-learning-based road-boundary detection and inference approaches. We have hand-annotated two of the 10 km-long forays from the Oxford Robotcar Dataset and generated from other forays several thousand further examples with semi-annotated road-boundary masks. To boost the number of training samples in this way, we used a vision-based localiser to project labels from the annotated datasets to other traversals at different times and weather conditions. As a result, we release 62 605 labelled samples, of which 47 639 samples are curated. Each of these samples contain both raw and classified masks for left and right lenses. Our data contains images from a diverse set of scenarios such as straight roads, parked cars, junctions, etc. Files for download and tools for manipulating the labelled data are available at: oxford-robotics-institute.github.io/road-boundaries-dataset

Authors: Suleymanov, T; Gadd, M; De Martini, D; Newman, P

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: IEEE
• Article number: WS-M119.2
• Publication date: 2022-01-10
• Acceptance date: 2021-05-31
• Event title: 32nd IEEE Intelligent Vehicles Symposium (IV21) -- Workshop on 3D-Deep Learning for Automated Driving (3D-DLAD)
• Event location: Virtual event.
• Event website: https://2021.ieee-iv.org/
• Event start date: 2021-07-11
• Event end date: 2021-07-17
• DOI: 10.1109/IVWorkshops54471.2021.9669250
• EISBN: 978-1-6654-7921-9
• ISBN: 978-1-6654-7922-6
• Language: English
• Keywords: road boundary; dataset; curb; kerb; FFR