Abstract
Ubiquitous positioning is considered to be a highly demanding application for today's Location-Based Services (LBS). While satellite-based navigation has achieved great advances in the past few decades, positioning and navigation in indoor scenarios and deep urban areas has remained a challenging topic of substantial research interest. Various strategies have been adopted to fill this gap, within which vision-based methods have attracted growing attention due to the widespread use of cameras on mobile devices. However, current vision-based methods using image processing have yet to revealed their full potential for navigation applications and are insufficient in many aspects. Therefore in this paper, we present a hybrid image-based positioning system that is intended to provide seamless position solution in six degrees of freedom (6DoF) for location-based services in both outdoor and indoor environments. It mainly uses visual sensor input to match with geo-referenced images for image-based positioning resolution, and also takes advantage of multiple onboard sensors, including the built-in GPS receiver and digital compass to assist visual methods. Experiments demonstrate that such a system can greatly improve the position accuracy for areas where the GPS signal is negatively affected (such as in urban canyons), and it also provides excellent position accuracy for indoor environments.
Highlights
Ubiquitous positioning is considered to be the main goal for today’s Location-Based Services (LBS)
We propose a multi-step solution: firstly we use GPS data to narrow down the search space; a voting strategy is used to find reference images corresponding to the query view among the localized image space; a hybrid technique is proposed that uses the measurements from GPS, digital compass and visual sensor onboard to calculate the final positioning result in 6DoF for outdoor environments
We have presented a comprehensive system that adopts a hybrid image-based method with combined use of onboard sensors (GPS, camera and digital compass) to achieve a seamless positioning solution for both indoor and outdoor environments
Summary
Ubiquitous positioning is considered to be the main goal for today’s Location-Based Services (LBS). Images associated with vision sensors have been researched for positioning and navigation purposes since early in the last century They are superior to many other techniques because they can operate both indoors and outdoors. From the perspective of vision-based navigation, the major difference between these two approaches lies in that the former uses a stereo camera to directly extract depth information, while the second is based on a single camera and query image matching. Following these two main streams, many vision-related navigation solutions designed for GPS-degraded environment can be found (e.g., [11,12,13,14,15]). The paper is structured as follows: the methodology of the system is described; outdoor positioning and indoor positioning will be discussed, respectively, in greater detail; we present the experiment results in Section 5, while in the last section the concluding remarks are presented
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
