Rating is available when the video has been rented.
This feature is not available right now. Please try again later.
Published on Oct 3, 2014
taken into account in the vehicle’s current motion plan and speed. Also labeling of parking spots, could be crucial in other V-Charge tasks as efficient assignment of parking spaces and local planning. Because many of these useful semantic cues are fixed in place, it makes sense to build up reusable semantic maps of the areas in which we want our autonomous cars to operate. Usually these maps are created manually but offers guarantees that are currently not available when using unsupervised machine learning classifiers. We describe the pipeline of UOXF.DF to create semantic maps automatically using active learning for road mark (e.g parking spot) classification.
Collaborators: Oxford University Hugo Grimmett, Lina Paz, Pedro Pinies, Chi Tong Ingmar Posner, Paul Newman