0 views collected around this technical thread.
Wuhan University and Amap clinched first place in IPIN 2021’s Smartphone‑Based Indoor Positioning track by fusing machine‑learning‑driven pedestrian dead‑reckoning with magnetic, Bluetooth and Wi‑Fi matching, achieving real‑time, high‑frequency indoor navigation using only a phone’s built‑in sensors.
This article provides a detailed overview of indoor positioning technologies—including GPS, cellular base‑station, Wi‑Fi, RFID, Bluetooth, UWB, infrared, visible light, geomagnetic, and visual methods—explaining their principles, advantages, limitations, and the specific challenges of achieving accurate, reliable, and cost‑effective indoor location services.
The Wuhan‑Amap team won IPIN2020’s vehicle‑navigation track by using big‑data mining and neural‑network‑enhanced Vehicle‑Dead Reckoning to fuse smartphone GNSS, IMU, and barometer data, overcoming GPS outages and sensor limitations, and demonstrating that machine‑learning‑driven inertial navigation can achieve vehicle‑grade accuracy on consumer phones.
DiDi's AR indoor navigation system addresses GPS unreliability in large indoor venues by using SfM-based 3D reconstruction, robust visual localization with magnetometer/GNSS priors, and sensor fusion with pedestrian dead‑reckoning and deep‑learning heading estimation, cutting passenger pick‑up time by up to 25 % across dozens of airports and malls.