Abstract
The primary method for geo-localization is based on GPS which has issues of localization accuracy, power consumption, and unavailability. This paper proposes a novel approach to geo-localization in a GPS-denied environment for a mobile platform. Our approach has two principal components: public domain transport network data available in GIS databases or OpenStreetMap; and a trajectory of a mobile platform. This trajectory is estimated using visual odometry and 3D view geometry. The transport map information is abstracted as a graph data structure, where various types of roads are modelled as graph edges and typically intersections are modelled as graph nodes. A search for the trajectory in real time in the graph yields the geo-location of the mobile platform. Our approach uses a simple visual sensor and it has a low memory and computational footprint. In this paper, we demonstrate our method for trajectory estimation and provide examples of geolocalization using public-domain map data. With the rapid proliferation of visual sensors as part of automated driving technology and continuous growth in public domain map data, our approach has the potential to completely augment, or even supplant, GPS based navigation since it functions in all environments.
Highlights
Autonomous navigation is an emerging technology with a huge potential; self-driving cars are almost round the corner
Our contributions in this paper are: (i) we introduce a novel approach to geo-localization of mobile platforms in real-time that combines Geographic Information System (GIS)/OpenStreetMap data and visual sensors on-board the mobile platform
In our experiments we evaluate our visual odometry pipeline in 4.1 and demonstrate our geo-localization approach in 4.2 using maps acquired from OpenStreetMap and GIS from different urban and semi-urban regions in different parts of the world
Summary
Autonomous navigation is an emerging technology with a huge potential; self-driving cars are almost round the corner. IMU provides continuously linear accelerations and rotational velocities, which can be integrated as the relative pose displacement It is reliable in the sort time period, so we can resolve the major drawback of using monocular visual odometry: such as scale estimation, image blur due to rapid motion, and the requirement of continuously feature tracking. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume III-3, 2016 XXIII ISPRS Congress, 12–19 July 2016, Prague, Czech Republic noise and bias inherent in these measurements are multiplied and cumulative after each integration, causes the system pose drift to become significantly unbounded over time To overcome these drawbacks of the IMU drifting problem, the camera is capable of detecting feature points in the scenes and using them as a pose constraint. Proposed method improved feature tracking and camera measurement results, providing better EKF-based visual-inertial pose estimation
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
