Semantic Image Based Geolocation Given a Map

TL;DR

This paper introduces a novel approach for urban geolocation that uses a map and sparse geo-tagged views to identify buildings and determine camera position, improving robustness to viewpoint and appearance changes.

Contribution

The work presents a new method for geo-locating images by detecting building facades and leveraging map geometry, reducing dependency on dense reference databases.

Findings

Effective building identification in challenging urban environments

Accurate camera localization using landmark detection and map geometry

Robust performance despite appearance and viewpoint variations

Abstract

The problem visual place recognition is commonly used strategy for localization. Most successful appearance based methods typically rely on a large database of views endowed with local or global image descriptors and strive to retrieve the views of the same location. The quality of the results is often affected by the density of the reference views and the robustness of the image representation with respect to viewpoint variations, clutter and seasonal changes. In this work we present an approach for geo-locating a novel view and determining camera location and orientation using a map and a sparse set of geo-tagged reference views. We propose a novel technique for detection and identification of building facades from geo-tagged reference view using the map and geometry of the building facades. We compute the likelihood of camera location and orientation of the query images using the detected landmark (building) identities from reference views, 2D map of the environment, and geometry of building facades. We evaluate our approach for building identification and geo-localization on a new challenging outdoors urban dataset exhibiting large variations in appearance and viewpoint.