Research on indoor positioning algorithm based on location fingerprint and PDR

To improve the indoor positioning accuracy, the methods of position fingerprint and pedestriandeadreckoning(PDR)areusedtostudytheindoorpositioningalgorithm.Forpositionfingerprintalgorithm,thefingerprintdatabaseisoptimizedthroughtheofflinedatatrainingphase,andthe optimizationofthenearestneighboralgorithmiscarriedoutbylimitingtheregionweightedvalue K throughtheonlinereal-timematchingphase.ForPDRalgorithm,theself-adaptationpeakdetectionalgorithmusedforstepfrequencydetectionisproposed.Theimprovednonlinearmodelisusedforstep sizeestimation.Moreover,Thegyroscope’sinformationarefusedtomagnetometer’sinformationinthe heading estimation.Finally, the unscented Kalman filter is used to fuse the position fingerprint algorithmandPDRmethod,whichimprovesthepositioningaccuracyandthepracticabilityofthefusion algorithmisverifiedbythepositioningsystem.