Automatic Discovery and Geotagging of Objects from Street View Imagery

TL;DR

This paper presents an automated method for detecting objects and determining their precise GPS locations from street view images using neural networks and a novel triangulation approach, enhancing urban mapping accuracy.

Contribution

It introduces a new pipeline combining monocular depth estimation and triangulation with a custom Markov Random Field for accurate object geolocation from street imagery.

Findings

High object recall rates achieved

GPS accuracy within 2 meters

Effective for multiple object classes like traffic lights and telegraph poles

Abstract

Many applications such as autonomous navigation, urban planning and asset monitoring, rely on the availability of accurate information about objects and their geolocations. In this paper we propose to automatically detect and compute the GPS coordinates of recurring stationary objects of interest using street view imagery. Our processing pipeline relies on two fully convolutional neural networks: the first segments objects in the images while the second estimates their distance from the camera. To geolocate all the detected objects coherently we propose a novel custom Markov Random Field model to perform objects triangulation. The novelty of the resulting pipeline is the combined use of monocular depth estimation and triangulation to enable automatic mapping of complex scenes with multiple visually similar objects of interest. We validate experimentally the effectiveness of our approach on two object classes: traffic lights and telegraph poles. The experiments report high object recall rates and GPS accuracy within 2 meters, which is comparable with the precision of single-frequency GPS receivers.