The demand for indoor localization is increasing with ubiquitous computing and the Internet of Things (IoT) emergence. Location awareness is crucial to intelligent systems in large-scale indoor environments, such as smart airports, train stations, hospitals, malls, and smart cities. Hence, indoor localization has been researched for the last decades. However, most site survey based WiFi fingerprint based indoor localization methods involve independent or one by one online localization methods, that are costly, and inefficient regarding computation time, memory, and energy consumption to implement in large-scale indoor environments. We propose an Online Batch Localization (OBLoc) for large-scale indoor environments scheme to address these challenges. The basic idea of OBLoc is that the indoor localization users close to each other have similar WiFi fingerprinting and can be clustered to form batches. Every batch's search space could be reduced using a batch representative. We propose a search space-slicing algorithm that slices part of the large-scale database using the appointed representative to minimize searching overhead. Furthermore, we designed a neighborhood consistency algorithm to identify erroneous location annotations in the sliced search space. We conduct experiments on three field-measured datasets to evaluate the performance of the proposed method. The experiment results show the improvement over the peer schemes of 21.34%, 17.38%, and 27.24% localization accuracy in the three datasets.
Pedestrian dead reckoning (PDR) is the critical component in indoor pedestrian tracking and navigation services. While most of the recent PDR solutions exploit in-built inertial sensors in smartphones for next step estimation, due to measurement errors and sensing drift, the accuracy of walking direction, step detection, and step length estimation cannot be guaranteed, leading to large accumulative tracking errors. In this paper, we propose a radar-assisted PDR scheme, called RadarPDR, which integrates a frequency-modulation continuous-wave (FMCW) radar to assist the inertial sensors-based PDR. We first establish a segmented wall distance calibration model to deal with the radar ranging noise caused by irregular indoor building layouts and fuse wall distance estimation with acceleration and azimuth signals measured by the inertial sensors of a smartphone. We also propose a hierarchical particle filter(PF) together with an extended Kalman filter for position and trajectory adjustment. Experiments have been conducted in practical indoor scenarios. Results demonstrate that the proposed RadarPDR is efficient and stable and outperforms the widely used inertial sensors-based PDR scheme.