Indoor corner landmark matching and identification method based on crowdsourcing trajectories

Abstract

The invention discloses an indoor corner landmark matching and identification method based on crowdsourcing trajectories. The method comprises the steps that landmark two-dimensional coordinate information of an indoor layout map is obtained; N signal sources are arranged in a target zone so that a user terminal can acquire signals of at least one signal source; marked and non-marked trajectories are acquired and are divided into trajectory windows; targeted characteristics are extracted from the marked trajectory windows, and a posture group identification classifier and a corner identification classifier are trained; the trained classifiers are utilized to identify corner landmarks of the non-marked trajectories, and RSS data of positive windows in the windows is extracted; a multidimensional scale analysis algorithm is utilized to reduce dimensionality so as to reach multiple dimensions, and clustering and matching are performed respectively; a voting algorithm is adopted to make effective sampling values correspond to certain corners according to clustering and matching results under multiple dimensions, and invalid sampling values are filtered; corner landmark fingerprints are generated according to the matching results. Compared with existing corner landmark identification method, the identification performance is improved.

Description

technical field [0001] The invention belongs to the technical field of communication and wireless network, and more specifically, relates to a method for matching and identifying indoor corner landmarks based on crowdsourcing trajectories. Background technique [0002] With the development of mobile networks, the demand for location-based information services continues to grow; the Global Positioning System (GPS) can provide reliable positioning services in outdoor environments, but the line-of-sight propagation of satellite signals in complex indoor environments leads to poor performance . The existing indoor positioning technology RSS positioning technology includes ranging-based positioning and fingerprint-based positioning; the former uses RSS to calculate the distance from the target to the signal source according to the propagation model to achieve positioning, and this method has poor performance in complex indoor environments; the latter Use the RSS vectors measured...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the above defects or improvement needs of the prior art, the present invention provides a method for matching and identifying indoor corner landmarks based on crowdsourcing trajectories. The problem of poor recognition performance caused by pedestrian multi-pose and false corner problems

Images