Crowdsourced localization using geo-spatial big data has become an effective approach for constructing smart-city-based location services with the fast growing number of Internet of Things terminals. This paper presents a self-calibrated multi-floor indoor positioning framework using a combination of Wi-Fi ranging, crowdsourced fingerprinting and low-cost sensors (SM-WRFS). The localization parameters, such as heading and altitude biases, step-length scale factor, and Wi-Fi ranging bias are autonomously calibrated to provide a more accurate forward 3D localization performance. In addition, the backward smoothing algorithm and a novel deep-learning model are applied in order to construct an autonomous and efficient crowdsourced Wi-Fi fingerprinting database using the detected quick response (QR) code-based landmarks. Finally, the adaptive extended Kalman filter is adopted to combine the corresponding location sources using different integration models to provide a precise multi-source fusion based multi-floor indoor localization performance. The real-world experiments demonstrate that the presented SM-WRFS is proven to realize precise 3D indoor positioning under different environments, and the meter-level positioning accuracy can be acquired in Wi-Fi ranging supported indoor areas.

Crowd-sensing-based localization is regarded as an effective method for providing indoor location-based services in large-scale urban areas. The performance of the crowd-sensing approach is subject to the poor accuracy of collected daily-life trajectories and the efficient combination of different location sources and indoor maps. This paper proposes a robust map-assisted 3D Indoor localization framework using crowd-sensing-based trajectory data and error ellipse-enhanced fusion (ML-CTEF). In the off-line phase, novel inertial odometry which contains the combination of 1D-convolutional neural networks (1D-CNN) and Bi-directional Long Short-Term Memory (Bi-LSTM)-based walking speed estimator is proposed for accurate crowd-sensing trajectories data pre-processing under different handheld modes. The Bi-LSTM network is further applied for floor identification, and the indoor network matching algorithm is adopted for the generation of fingerprinting database without pain. In the online phase, an error ellipse-assisted particle filter is proposed for the intelligent integration of inertial odometry, crowdsourced Wi-Fi fingerprinting, and indoor map information. The experimental results prove that the proposed ML-CTEF realizes autonomous and precise 3D indoor localization performance under complex and large-scale indoor environments; the estimated average positioning error is within 1.01 m in a multi-floor contained indoor building.

No abstract