Abstract
Visual localization is an accurate and low-cost indoor localization solution. A bottleneck for visual localization is the computation efficiency of continuous image searching and matching. In this paper, an indoor visual localization method is proposed to realize continuous and accurate indoor localization based on image matching. This method uses smartphones to collect multi-sensor data, including video frames and inertial readings. To improve the computation efficiency of the proposed visual localization method, a spatial model is developed to optimize the spatial organization of geo-tagged images in a dataset. Several spatial constraint-based image searching strategies are also designed to further reduce the computation time. Based on the spatial model and spatial constraint-based strategies, a visual localization algorithm is proposed. The experimental results show that the localization errors of the image querying, continuous offline localization and online localization of this method are approximately 0.4 m, 0.7 m and 0.9 m, respectively. This method can achieve an accuracy of 1.3 m, even under a random camera opening condition. The average computation time (i.e.. the average time needed to provide a location estimation result) is approximately 0.59 s. The results indicate that the proposed method can realize efficient and continuous indoor localization with high localization accuracy.
Highlights
The localization of people in large indoor environments, such as shopping malls, office buildings or large parking garages, has become a common issue for many industry and commercial applications
EVALUATION we evaluate the performance of the proposed visual localization method employing sensor data and video frames collected by smartphones
The experimental results showed that the matching of geo-tagged images can continuously correct the accumulative error of pedestrian dead reckoning (PDR)
Summary
The localization of people in large indoor environments, such as shopping malls, office buildings or large parking garages, has become a common issue for many industry and commercial applications. Due to the shielding effect caused by obstacles (e.g., buildings), it is difficult to obtain accurate localization results from GPS in indoor spaces. Technologies, for example, UWB or Bluetooth, can achieve good localization performance in indoor spaces. Among various indoor localization technologies, visual localization is an accurate and low-cost indoor localization solution. It uses a camera (e.g., from a smartphone) to collect video frames from the environment. The collected video frames can either be used to achieve a relative localization based on an SFM (structure from motion) scheme [7] or be compared with geo-tagged data in a database to find the best matching result [8]. Visual localization systems can be deployed in various indoor or outdoor environments and do not rely on extra infrastructures or devices
Sign-in/Register to view highlights & summary 
Published Version (
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