Neural network geomagnetic positioning method based on multi-feature driving and computer equipment
The invention is suitable for the field of indoor positioning, and provides a neural network geomagnetic positioning method based on multi-feature driving, a computer readable storage medium and computer equipment. The method comprises the following steps: receiving geomagnetic signals and sensor in...
Saved in:
Main Authors | , , , , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
19.01.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | The invention is suitable for the field of indoor positioning, and provides a neural network geomagnetic positioning method based on multi-feature driving, a computer readable storage medium and computer equipment. The method comprises the following steps: receiving geomagnetic signals and sensor information collected by a mobile terminal, and creating a multi-dimensional data set for geomagnetic positioning and step length estimation; geomagnetic positioning estimation is carried out based on the ResNet-GRU-LSTM neural network model, and a predicted geomagnetic positioning result is obtained; obtaining a step length, a step frequency and a direction angle for predicting and obtaining pedestrian dead reckoning (PDR) positioning by using a hierarchical GRU neural network model; and according to the step length, the step frequency, the direction angle and the geomagnetic positioning result, performing geomagnetic auxiliary multi-feature driven PDR positioning through particle filtering to obtain the final posit |
---|---|
Bibliography: | Application Number: CN202311353762 |