In one embodiment, a method includes receiving from one or more magnetic-measurement devices one or more trajectories comprising magnetic measurements in an area collected by the magnetic-measurement devices over a period of time. The method also includes performing one or more correlation analyses on at least some of the trajectories to determine similarities in the trajectories. The method also includes storing portions of the trajectories that have determined similarities below predetermined thresholds for incorporation into a master geomagnetic map.

[Object] To accurately estimate a user's position on the basis of sensor data by preparing absolute criteria in advance.

[Solution] Provided is an information processing apparatus including: a feature extractor configured to extract a feature of first sensor data provided by a sensor carried or worn by a user; a matching unit configured to match the feature of the first sensor data and a feature of second sensor data corresponding to the first sensor data, the feature of the second sensor data being associated with given position information; and a position estimation unit configured to estimate a position of the user on the basis of a result of the matching.

A technique for detecting the occurrence of an event, and for estimating other event-related information, by analyzing the barometric pressure in the vicinity of one or more wireless terminals. The disclosed detection technique is based on the recognition that the barometric sensor on various wireless terminals, such as smartphones, is capable of measuring very subtle changes in the atmospheric pressure. The disclosed detection technique is also based on the additional recognition of how some of the changes in the atmospheric pressure, as measured by a wireless terminal, correlate to various events that occur within a building or other defined area. For example, the disclosed technique can detect an entry door opening or closing by analyzing a resultant pressure wave having a particular transient that is perceptible by one or more wireless terminals in the area and analyzed by a detection engine.

Techniques describe tagging visual data (e.g., image and/or video data) with wireless and sensor measurement information by a mobile device. Tagged visual data may be sent to a server, such as a crowdsourcing server. Techniques further describe receiving visual data from a device, wherein the visual data is tagged with information comprising source identifying information associated with an at least one signal emitting device, identifying at least one visual feature from the visual data, determining a coordinate on a map at which the visual data was acquired based on identifying the at least one visual feature from the visual data, and associating the coordinate on the map with the information associated with the at least one signal emitting device.

Methods, program products, and systems for building a location fingerprint database for a transit system are described. The transit system can be a subway system including underground train stations and routes where location determination using GPS signals is difficult or impossible. A sampling device can measure signals, e.g., radio frequency (RF) signals detected at the stations or on the routes. A location server can construct a location fingerprint for each of the stations and the routes. Each location fingerprint can represent expected signal measurements by a user device if the user device is located at the respective station or route. The location server can provide the location fingerprint to a user device for the user device to determine a location of the user device within the station or on the route.

Embodiments of present disclosure disclose a method for updating geomagnetic information performed at a computing device, which belong to the field of electronic technologies. The method includes: receiving target geomagnetic information and target location assistance information that are transmitted by a terminal during positioning; determining a target geographical location corresponding to the target location assistance information in a case that geomagnetic information corresponding to a current geographical location of the terminal is invalid; and updating geomagnetic information corresponding to the target geographical location according to the target geomagnetic information in a prestored correspondence between a geographical location and geomagnetic information. According to the embodiments of the present disclosure, efficiency of updating geomagnetic information can be improved.

A method of training a predictor to predict a location of a computing device in an indoor environment incudes: receiving training data including strength of signals received from wireless access points at positions of an indoor environment, where the training data includes: a subset of labeled data including signal strength values and location labels; and a subset of unlabeled data including signal strength values and not including labels indicative of locations; training a variational autoencoder to minimize a reconstruction loss of the signal strength values of the training data, where the variational autoencoder includes encoder neural networks and decoder neural networks; and training a classification neural network to minimize a prediction loss on the labeled data, where the classification neural network generates a predicted location based on the latent variable, and where the encoder neural networks and the classification neural network form the predictor.

Disclosed is an approach to enable radio map download for Global Navigation Satellite System (GNSS)-denied areas. In particular, processor(s) (e.g., of positioning server(s)) could identify GNSS-denied area(s) in an initial radio map, the GNSS-denied area(s) being (i) one or more areas in which at least one GNSS signal is or was unavailable and (ii) a subset of a plurality of areas represented by the initial radio map. Subsequently, the processor(s) could generate a partial radio map representing radio data only for the GNSS-denied area(s) identified in the initial radio map, and could then transmit the partial radio map to a mobile device for storage at the mobile device. In this way, the mobile device could optimize resource usage and perform radio-based position estimations at least in the GNSS-denied area(s) that were identified.

A location engine uses the empirical measurements made by a scouting wireless terminal (i) to discover the existence of a reference radio within a geographic region; (ii) to generate an estimate of the location of the newly-discovered reference radio, and (iii) to generate an estimate of the transmission power of the downlink control channel radio signal transmitted by the newly-discovered reference radio. The location engine then uses: (i) the estimate of the location of the newly-discovered reference radio, and (ii) the estimate of the transmission power of the downlink control channel radio signal transmitted by the newly-discovered reference radio, and (iii) measurements, made by a user wireless terminal, of the power of each of the downlink control channel radio signals transmitted by each of the reference radios to generate an estimate of the location of the user wireless terminal.

It is inter-alia disclosed a method comprises: obtaining or holding available radio signal observation data of a tracking device representing one or more sets of radio signal observation results captured by a radio interface of the tracking device when present on a site, wherein a respective set of radio signal observation results is captured at a corresponding observation position on said site; obtaining or holding available setting information; associating at least one training set of radio signal observation results with identification information of an area of interest on said site, if at least one of the one or more sets of radio signal observation results is indicated as the at least one training set of radio signal observation results by the setting information.