Deep-Geometric 6 DoF Localization from a Single Image in Topo-metric Maps

TL;DR

This paper introduces a hybrid Deep-Geometric Localizer that estimates full 6 DoF camera pose from a single image in a known environment by combining deep learning for topological localization with geometric PnP algorithms.

Contribution

It presents a novel approach that separates mapping and localization, enabling accurate 6 DoF pose estimation with a single camera in previously mapped environments.

Findings

Outperforms fully deep learning pose regressors in accuracy.

Works effectively with monocular images in real and simulated environments.

Compatible with mobile and drone applications for real-time localization.

Abstract

We describe a Deep-Geometric Localizer that is able to estimate the full 6 Degree of Freedom (DoF) global pose of the camera from a single image in a previously mapped environment. Our map is a topo-metric one, with discrete topological nodes whose 6 DoF poses are known. Each topo-node in our map also comprises of a set of points, whose 2D features and 3D locations are stored as part of the mapping process. For the mapping phase, we utilise a stereo camera and a regular stereo visual SLAM pipeline. During the localization phase, we take a single camera image, localize it to a topological node using Deep Learning, and use a geometric algorithm (PnP) on the matched 2D features (and their 3D positions in the topo map) to determine the full 6 DoF globally consistent pose of the camera. Our method divorces the mapping and the localization algorithms and sensors (stereo and mono), and allows accurate 6 DoF pose estimation in a previously mapped environment using a single camera. With potential VR/AR and localization applications in single camera devices such as mobile phones and drones, our hybrid algorithm compares favourably with the fully Deep-Learning based Pose-Net that regresses pose from a single image in simulated as well as real environments.