City-scale continuous visual localization

Visual or image-based self-localization refers to the recovery of a camera's position and orientation in the world based on the images it records. In this paper, we deal with the problem of self-localization using a sequence of images. This application is of interest in settings where GPS-based systems are unavailable or imprecise, such as indoors or in dense cities. Unlike typical approaches, we do not restrict the problem to that of sequence-to-sequence or sequence-to-graph localization. Instead, the image sequences are localized in an image database consisting on images taken at known locations, but with no explicit ordering. We build upon the Gaussian Process Particle Filter framework, proposing two improvements that enable localization when using databases covering large areas: 1) an approximation to Gaussian Process regression is applied, allowing execution on large databases. 2) we introduce appearance-based particle sampling as a way to combat particle deprivation and bad initialization of the particle filter. Extensive experimental validation is performed using two new datasets which are made available as part of this publication.