Automatic dense visual semantic mapping from street-level imagery

This paper describes a method for producing a semantic map from multi-view street-level imagery. We define a semantic map as an overhead, or bird's eye view of a region with associated semantic object labels, such as car, road and pavement. We formulate the problem using two conditional random...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй
Үндсэн зохиолчид: Sengupta, S, Sturgess, P, Ladický, L, Torr, PHS
Формат: Conference item
Хэл сонгох:English
Хэвлэсэн: IEEE 2012