Here Global B.v.

Henri Jaakko Julius Nurminen

Pavel Ivanov

Lauri Aarne Johannes Wirola

Marko Luomi

Petri Rauhala

Mikko Juhani Blomqvist

Veijo Ilomäki

A processor obtains an audio sample captured by an audio sensor associated with a device and/or image data captured by an image sensor associated with the device. The image data comprises a representation of one or more elevator buttons. The processor analyzes the audio sample to identify a floor name indicator in the audio sample and/or the image data to identify an activated elevator button from among the one or more elevator buttons represented by the image data; and determines a floor name based on the floor name indicator identified in the analyzed audio sample and/or a floor name indicator associated with the identified activated elevator button in accordance with the analyzed image data. The processor causes the determined floor name to be stored and/or provided for positioning purposes.

Determining floor name based on audio and/or visual samples

A network device stores a radio map comprising map data configured to enable radio-based positioning within a geographic area. The radio map is associated with a plurality of instances of quality information, with each instance of quality information corresponding to a respective location within the geographic area. The network device receives a quality information request corresponding to a geographic region within the geographic area. The quality information request is associated with an entity. Based on a determination of whether a contribution by the entity to a portion of the map data that corresponds to the geographic region satisfies one or more significance criteria, the network device either provides or withholds quality information corresponding to the geographic region.

Controlled access of radio map quality information

A computing device, method and computer program product are provided to generate fingerprint data having an obfuscated location reference, thereby maintaining the privacy of the location information provided by fingerprint data and represented by a radio map. For a computing device configured to generate fingerprint data having an obfuscated location reference, the computing device is caused to receive fingerprint data comprising a location reference and measurement(s) of one or more communications nodes. The computing device is caused to determine translation and/or rotation parameter(s) based on a respective identifier of at least one of the one or more communications nodes and to apply one or more of the parameters at least to the location reference, thereby generating an obfuscated location reference. The computing device is also caused to provide the fingerprint data including the obfuscated location reference to another computing device for generation or updating of a radio map.

Computing device and method for generating fingerprint data having an obfuscated location reference

A method, apparatus and computer program product are provided for improving localization of a device. In this regard, a coarse location of the device is determined and a neural network is utilized to determine one or more image-based vectors from the device to respective features in an image captured by an image capture device associated with the device. At one or more location points defined relative to the coarse location of the device, (a) one or more map-based vectors extending from a respective location point to respective features as defined by map data are compared to (b) the one or more image-based vectors. Based on the comparison, a refined location of the device is determined. A method, apparatus and computer program are also provided for training the neural network to determine an image-based vector from the device to a feature in an image captured by the device.

Neural network-based method and apparatus for improving localization of a device

A method, apparatus and computer program product are provided for improving localization of a device. In order to improve the localization, a coarse location of the device is determined and a feature is identified in an image captured by an image capture unit associated with the device. The feature is represented with one or more points or lines within an image plane and a projection is determined of the one or more points or lines from the image plane to a ground plane. At one or more location points defined relative to the coarse location of the device, map data is compared to the projection of the one or more points or lines representative of the feature identified in the image. Based on the comparison, a refined location of the device is determined.

Method and apparatus for improving localization of a device

Disclosed is an approach for improved radio and/or altitude data collection in the context of a positioning system. In particular, processor(s) could execute a first phase of the collection process, which may involve collection of data only in seed area(s) associated with generation of an initial map as well as setting forth guidance, via a user interface of a mobile device, to collect data only in the seed area(s). And when the processor(s) detect a trigger to end the first phase, the processor(s) could responsively execute a second phase of the process, which may involve collection of data in secondary area(s) associated with generation of an updated map as well as setting forth guidance, via the user interface, (i) to collect data in the secondary area(s) and (ii) to visit seed area(s) and/or other area(s) that are deemed to be ready.

Methods and systems for improved data collection in a positioning solution that leverages closed-loop learning (CLL)

A geometric plane defined by a building-perimeter feature in an image capture by a mobile device is identified. The building-perimeter feature is co-located with an exterior wall of a building within which the mobile device is located. An orientation and/or location of the mobile device with respect to the geometric plane and an orientation of the mobile device with respect to a defined geographical direction are determined. A building model for the building and defining perimeter portions of the building (each perimeter portion corresponding to a respective exterior wall) is obtained or accessed. Based on the orientation and/or location of the mobile device with respect to the geometric plane, the orientation of the mobile device with respect to the defined geographical direction, and/or the building model, a particular perimeter portion of the building model that corresponds to the building-perimeter feature is identified and corresponding location information is determined.

Indoor localization based on detection of building-perimeter features

The absolute altitude of multiple floors of a building are determined using a multi-mode learning process. Processor(s) execute application program code to cause an apparatus to operate in an initial floor learning mode that includes capturing outdoor altitude estimates for the apparatus and determining, based in part on the outdoor altitude estimates, instant altitude estimates for an initial floor of the building. An absolute altitude estimate for the initial floor is determined based one the instant altitude estimates. After the absolute altitude estimate for the initial floor satisfies a first threshold certainty, the apparatus operates in a subsequent floor learning mode configured for determining respective absolute altitudes for floors of the building based on the absolute altitude estimate for the initial floor and a priori floor height information for the building, a sensor-based altitude change estimate, and/or a determined floor height for the building.

Multiple mode learning of absolute altitude of floors of a building

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.

Methods and systems for using a vehicle location to geo-reference radio data collected during a time of commute

A method is provided that is performed by at least one first apparatus with the method including obtaining or causing obtaining information indicative of a variation in intensity of light emitted from at least two light sources positioned along a segment of a road; and obtaining or causing obtaining information indicative of a velocity of the at least one first apparatus based at least on the information indicative of the variation in intensity. A corresponding apparatus is also provided.

Estimation of speed of a vehicle based on light intensity measurements

Disclosed is an approach for automatic detection of entrance(s). In particular, processor(s) could have access to counter data arranged to maintain counters that each respectively represent a count of how many times GNSS service has been obtained or lost in a respective one of a plurality of sub-areas. Given this, the processor(s) could detect a GNSS state change corresponding to an instance of GNSS service being obtained or lost in a particular sub-area and could responsively increment the respective counter associated with the particular sub-area. In turn, the processor(s) could make a determination that the respective counter is representing a count that is greater than other count(s) represented by counter(s) associated with other sub-area(s). And based at least on this determination, the processor(s) could deem the particular sub-area to include an entrance, thereby resulting in detection of the entrance.

Entrance detection based on GNSS state change data

Disclosed is an approach for improving performance of a radio-based positioning system by detecting and excluding mobile radio nodes. The disclosed approach involves processors (e.g., of positioning server(s) and/or of a computing device) making a determination (i) that a speed of a computing device is at or above a threshold speed, and (ii) that at least one condition is met, the at least one condition indicating that a radio node is moving substantially along with the computing device. In response to making the determination, the processors may deem the radio node to be a mobile node. Given this, the processors may in turn exclude the radio node for positioning purposes, which may ultimately improve performance of the radio-based positioning system.

Detecting mobile nodes to improve radio-based positioning performance

A method is provided that includes obtaining one or more pieces of crowd-sourced information. A respective crowd-sourced information is at least indicative of a location at which the respective crowd-sourced information was gathered. The method determines a set of tiles at least partially based on the one or more geographical areas. For at least one tile, the method obtains one or more pieces of fingerprint information comprised by the one or more pieces of crowd-sourced information that were gathered within the respective area of the respective tile and determines an area type and/or context information indicative of a type of venue located within the respective tile and/or context the respective area of the respective tile is used for. The area type and/or context information is determined at least partially based on the one or more pieces of fingerprint information. A corresponding apparatus and computer program product are also provided.

Context information from crowd-sourced data

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.

Crowdsourcing performance indicators

A method includes obtaining piece(s) of calendar information indicative of at least one appointment taking place in a space and extracting a set of space identifiers representing space(s) of the venue. The space identifier(s) for one or more spaces are extracted based on an indoor map of the venue. The method also includes determining or triggering determining whether at least a part of the set of space identifiers or one or more spaces of the set of space identifiers match(es) the at least one space as represented by the piece(s) of calendar information; and if a match is found: determining one or more reference location estimates. A respective reference location estimate is indicative of a location of the space that was determined to be a match. A corresponding apparatus, computer program product and system are also provided.

Growing community of inventors

Tampere, Finland

Henri Jaakko Julius Nurminen