[time]
2020-09-01T10:18:17+02:00

[team_name]
TJU

[team_institution]
Tianjin University

[logolink]


[system_name]


[website]


[track]
3

[reference_person]
Zhang Liqiang

[email]
zhangliqiang@tju.edu.cn

[description]
A smartphone integrates rich sensors, including inertial sensor, magnetic sensor, light sensor, sound sensor and proximity sensor, etc. Therefore, it provides a possibility to localize pedestrians, which is valuable and challenging. Especially, with the spread of the COVID-19, social distancing becomes a trend. Therefore, precision and low-cost localization solutions are attracting the interests of researchers. Step-length and heading system (SHS) is a mainstream solution using a smartphone. To our best knowledge, step-length computing is accurate when a pedestrian moves straightly on a level ground. However, when a pedestrian moves on a slope or with specific gaits (such as walking backwards or sideways, etc.). To address the problem, we propose a scheme based on inertial navigation system (INS). In our system, a learning-based error model is leveraged to estimate the errors from the INS. Simultaneously, global navigation satellite system (GNSS), Wi-Fi fingerprint and magnetic fingerprint are leveraged to correct the position errors.

[references]