A Multi-User Personal Indoor Localization System Employing Graph-Based Optimization

Abstract

Personal indoor localization with smartphones is a well-researched area, with a number of approaches solving the problem separately for individual users. Most commonly, a particle filter is used to fuse information from dead reckoning and WiFi or Bluetooth adapters to provide an accurate location of the person holding a smartphone. Unfortunately, the existing solutions largely ignore the gains that emerge when a single localization system estimates locations of multiple users in the same environment. Approaches based on filtration maintain only estimates of the current poses of the users, marginalizing the historical data. Therefore, it is difficult to fuse data from multiple individual trajectories that are usually not perfectly synchronized in time. We propose a system that fuses the information from WiFi and dead reckoning employing the graph-based optimization, which is widely applied in robotics. The presented system can be used for localization of a single user, but the improvement is especially visible when this approach is extended to a multi-user scenario. The article presents a number of experiments performed with a smartphone inside an office building. These experiments demonstrate that graph-based optimization can be used as an efficient fusion mechanism to obtain accurate trajectory estimates both in the case of a single user and in a multi-user indoor localization system. The code of our system together with recorded dataset will be made available when the paper gets published.

Collaborative Smartphone-Based User Positioning in a Multiple-User Context Using Wireless Technologies

“…Therefore, the proposed Social-Loc is more suitable for improving the Dead Reckoning tracking than the Wi-Fi fingerprinting tracking. In [30], a graph-based optimization process is used to combine different trajectories from multiple users. The graph is built by using the Personal Dead Reckoning data from the phone as moving constraints.…”

Leveraging Visual Place Recognition to Improve Indoor Positioning with Limited Availability of WiFi Scans

“…An alternative solution, which does not need to assume any propagation model is crowdsourcing—updating the WiFi map with data collected by many users while they use the positioning service. This approach was investigated and shown feasible in our recent work [4], and can be adopted also and can also be adopted to the solution proposed in this article. However, our aim in this research is not to improve the efficiency of the off-line preparation phase, but to find a solution that can compensate for the problem with WiFi signal availability during the localization phase that emerged due to the security policy changes in the recent generation of smartphones.…”

“…This approach gained popularity in robotics [5] due to the efficient solvers, like g2o [36], that make it possible to simultaneously optimize hundreds of parameters with thousands of constraints in real time. The graph-based approach to indoor positioning was introduced in our previous research concerning the localization of single [37] and multiple users [4]. In these papers, we focused on the positioning accuracy of a system based on metric measurements—WiFi and inertial.…”

“…Nevertheless, the recent changes in Android WiFi scanning policy () will require modifications to those approaches since the WiFi scanning rate is reduced to four scans per two minutes in the latest Android devices. This is a significantly lower value than the scanning frequency typically used to obtain a reasonably dense positioning with WiFi-based fingerprinting [4].…”

“…The concept of localization constraints stemming from qualitative observations of the environment or information entered directly by the user was introduced in our conference paper [6]. However, this journal article significantly extends the preliminary approach from [6], building upon our more recent graph-based positioning system utilizing WiFi fingerprinting [4]. This paper introduced an efficient opportunistic WiFi sensing framework that does not require laborious surveying of the site, which is also adopted in the research presented here.…”