Multi-Scale Fusion Localization Based on Magnetic Trajectory Sequence
Open Access
Abstract
Magnetic fingerprint has a multitude of advantages in the application of indoor positioning, but as a weak magnetic field, the dynamic range of the data is limited, which exerts direct influence on the positioning accuracy. Aiming at resolving the problem wherein the indoor magnetic positioning results tremendously rest with the magnetic characteristics, this paper puts forward a method based on deep learning to fuse the temporal and spatial characteristics of magnetic fingerprints, to fully explore the magnetic characteristics and to obtain stable and trustworthy positioning results. First and foremost, the trajectory of the acquisition area is extracted by adopting the ameliorated random waypoint model, and the simulation of pedestrian trajectory is completed. Then, the magnetic sequence is obtained by mapping the magnetic data. Aside from that, considering the scale characteristics of the sequence, a scale transformation unit is designed to obtain multi-scale features. At length, the neural network self-attention mechanism is adopted to fuse multiple features and output the positioning results. By probing into the positioning results of dissimilar indoor scenes, this method can adapt to diverse scenes. The average positioning error in a corridor, open area and complex area reaches 0.65 m, 0.93 m and 1.38 m respectively. The addition of multi-scale features has certain reference value for ameliorating the positioning performance.Keywords
Funding Information
- National Natural Science Foundation (NNSF) of China (BS 11975044)
This publication has 28 references indexed in Scilit:
- WiMag: Multimode Fusion Localization System based on Magnetic/WiFi/PDR2016
- An improved RSSI of geomagnetic field-based indoor positioning method involving efficient database generation by building materials2016
- UJIIndoorLoc-Mag: A new database for magnetic field-based localization problems2015
- Using Wi-Fi/magnetometers for indoor location and personal navigation2015
- Indoor positioning based on foot-mounted IMUBulletin Of The Polish Academy Of Sciences-Technical Sciences, 2015
- Dynamic gesture recognition based on improved DTW algorithm2015
- Magicol: Indoor Localization Using Pervasive Magnetic Field and Opportunistic WiFi SensingIEEE Journal on Selected Areas in Communications, 2015
- Performance evaluation of bluetooth low energy in indoor positioning systemsTransactions on Emerging Telecommunications Technologies, 2014
- LocateMeACM Transactions on Intelligent Systems and Technology, 2013
- An enhanced dynamic time warping model for improved estimation of DTW parametersIEEE Transactions on Speech and Audio Processing, 2003