Monocular Urban Localization using Street View

Li Yu (1, 2) , Cyril Joly (1) , Guillaume Bresson (2) , Fabien Moutarde (1)

1 CAOR - Centre de Robotique
2 VeDeCom - VEhicule DEcarboné et COmmuniquant et sa Mobilité

This paper presents a metric global localization in the urban environment only with a monocular camera and the Google Street View database. We fully leverage the abundant sources from the Street View and benefits from its topo-metric structure to build a coarse-to-fine positioning, namely a topolog-ical place recognition process and then a metric pose estimation by local bundle adjustment. Our method is tested on a 3 km urban environment and demonstrates both sub-meter accuracy and robustness to viewpoint changes, illumination and occlusion. To our knowledge, this is the first work that studies the global urban localization simply with a single camera and Street View.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Li Yu, Cyril Joly, Guillaume Bresson, Fabien Moutarde. Monocular Urban Localization using Street View. 14th International Conference on Control, Automation, Robotics and Vision (ICARCV'2016), Nov 2016, Phuket, Thailand. ⟨hal-01425639⟩