Techniques are described herein for developing a fingerprint map that may be used for 3D indoor localization. In one example, a network server may leverage a building footprint from an open source database with signal measurements taken by probing user devices from signal sources such as access point (AP) devices. The network server may use the signal measurements to remotely calculate corresponding 3D positions of the AP devices in a particular building. Further, the network server may use the building footprint and the calculated 3D positions of the AP devices as references for developing the fingerprint map for 3D indoor localization.

A method for generating a wireless signal fingerprint database includes: obtaining an initial atmospheric pressure value, in which the initial atmospheric pressure value is an atmospheric pressure value collected when a terminal enters indoors; obtaining periodically a current wireless signal fingerprint and a current atmospheric pressure value collected by the terminal; and determining a floor corresponding to the current wireless signal fingerprint based on the initial atmospheric pressure value and the current atmospheric pressure value, to obtain the wireless signal fingerprint database.

Techniques are described herein for developing a fingerprint map that may be used for 3D indoor localization. In one example, a network server may leverage a building footprint from an open source database with signal measurements taken by probing user devices from signal sources such as access point (AP) devices. The network server may use the signal measurements to remotely calculate corresponding 3D positions of the AP devices in a particular building. Further, the network server may use the building footprint and the calculated 3D positions of the AP devices as references for developing the fingerprint map for 3D indoor localization.

Disclosed is an approach to improve data collection for a radio-based positioning system. The disclosed approach may involve processor(s) (e.g., of positioning server(s) and/or of a mobile device) obtaining radio data associated with the mobile device, where the radio data is collected while the mobile device is located within a particular vehicle during a time of commute. The processor(s) may determine a particular location of the particular vehicle representing where the particular vehicle is or was located during the time of commute. And the processor(s) may then use the particular location of the particular vehicle to geo-reference the radio data collected while the mobile device is located within the particular vehicle during the time of commute.

A method is provided that includes obtaining or holding available radio positioning support map information and geographic map information. An overlapping geographic area is covered by the radio positioning support map and the geographic map, which is dividable into a plurality of subareas. The method also includes determining, for each subarea of the plurality of subareas, a respective observed radio positioning support device density at least partially based on the radio positioning support map and a respective expected radio positioning support device density at least partially based on the geographic map. The method further includes evaluating, for each subarea of the plurality of subareas, a respective radio positioning performance in a respective subarea at least partially based on the respective observed radio positioning support device density and the respective expected radio positioning support device density. A corresponding apparatus and computer readable storage medium are also provided.

It is disclosed to obtain a frequency transformed radiomap data set by applying a discrete frequency transform to an original radiomap data set. It is also disclosed to obtain a reconstructed radiomap data set by applying an inverse discrete frequency transform to a frequency transformed radiomap data set.

In various embodiments, techniques are provided for determining and associating multiple locations with beacons, and estimating a location of an electronic device based on beacons having multiple associated locations. To determine multiple locations of a beacon, observations are grouped into observation clusters, a probability is calculated that each observation cluster accurately describes the beacon, multiple observation clusters are selected as representative of the beacon based on the calculated probabilities, characteristics are derived for the beacon (including multiple locations) based on the selected multiple observation clusters, and at least the multiple locations for the beacon are stored in a reference database. To estimate a location of an electronic device, a list of detected beacons is created, one or more locations are accessed from a reference database for each of the beacons on the list of detected beacons with at least one of the beacons having multiple locations, the locations are grouped into location clusters, a probability each location cluster represents a location of the electronic device is calculated, an location cluster is selected to represent the location of the beacon based on the calculated probabilities, and a location of the electronic device is estimated based on the selected location cluster.

A ranging-type positioning system and a ranging-type positioning method based on crowdsourced calibration are provided. In a crowdsourcing stage, pedestrian dead reckoning (PDR) is performed based on readings of inertial measurement units on a mobile device, a particle filter (PF) is executed to reconstruct a path of the mobile device with map information of the target field, and FTM data records are collected. Then, a ranging model based on a neural network can be used to calibrate and inversely infer approximate locations of unknown base stations. The optimized ranging model can estimate estimated distances and standard deviations based on the FTM data records obtained in the crowdsourcing stage. In a positioning stage, a position of a to-be-positioned mobile device can be positioned by having the ranging model operated in cooperation with the PDR and the PF.

A method is disclosed that includes gathering one or more pieces of crowdsourcing information indicative of one or more positions at which the at least one mobile device is located during the gathering. The method also includes collecting one or more performance indicators indicative of measurable information associated with the gathering of the one or more pieces of crowdsourcing information. The one or more performance indicators enable an evaluation of the gathering of the one or more pieces of crowdsourcing information. The method further includes providing the collected one or more performance indicators. An according apparatus, computer program and system are also disclosed.

It is inter-alia disclosed a method comprises: obtaining or holding available at least one training set of radio signal observation results, wherein a respective training set of radio signal observation results is held available in association with identification information of a corresponding area of interest on a site, wherein a respective training set of radio signal observation results is captured at a corresponding observation position within a corresponding area of interest on said site; obtaining or holding available area of interest information indicating whether at least one tracking device has been determined to have entered and/or to have been located within a corresponding area of interest on the site; obtaining or holding available current radio signal observation data of a current tracking device representing one or more current sets of radio signal observation results captured by a radio interface of the current tracking device when present on said site, wherein a respective current set of radio signal observation results is captured at a corresponding observation position on said site; determining whether the current tracking device has entered or is located within an area of interest, identification information of which is associated with the at least one training set of radio signal observation results, based on at least one current set of radio signal observation results, based on at least one training set of radio signal observation results associated with the identification information of the area of interest, and based on the area of interest information.