# US 10,872,447 B2 · Topology specifying method, topology specifying apparatus and non-transitory computer-readable storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,872,447 B2 - Document ID: US10872447B2 - Status: Granted - Kind: B2 - Application number: 16/131,059 - Filed: 2018-09-14 - Published: 2019-03-28 - Granted: 2020-12-22 - Earliest claimed: 2016-03-16 - Assignees: Geocreates, Inc. - Applicants: Geocreates, Inc. - Inventors: Tsukasa Honda - Web page: https://patentgrep.com/patent/US10872447B2 ## CPC - G06T 17/05: Geographic models - G01C 21/3602: {Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera} - G01C 21/3647: {Guidance involving output of stored or live camera images or video streams} - G06T 7/536: from perspective effects, e.g. by using vanishing points - G06T 11/65: on geographic maps - G06T 19/006: {Mixed reality (object pose determination, tracking or camera calibration for mixed reality G06T7/00)} - G06V 20/20: in augmented reality scenes - G06V 40/19: Sensors therefor - G06T 2207/30184: Infrastructure - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G01C: MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY (measuring liquid level G01F; radio navigation, determining distance or velocity by use of propagation effects, e.g. Doppler effects, propagation time, of radio waves, analogous arrangements using other waves G01S) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A topology specifying method includes: acquiring object information that shows a shape of a visible object viewed by a user, and viewing position information that shows a position or movement of the user's view in a visual recognition area viewed by the user, and specifying a topology of the visible object that is associated with the user's impression of the visible object on the basis of a shape of the visible object included in the object information, and outputting information associated with the visible object and topology information that shows the specified topology in association with the each other. ## Claims ### Claim 1 A topology specifying method, comprising: acquiring a captured image including a plurality of visible objects that shows each shape of the visible objects viewed by a user and viewing position information that shows a position or movement of the user's view in a visual recognition area viewed by the user; specifying a topology of the visible objects that is associated with the user's impression of the visible objects on the basis of each shape of the visible objects included in the object information and the viewing position information; and outputting, to a display visible by the user, (i) information indicating that the user perceives composition of one-point perspective in the captured image by superimposing that information on a street where the user is, in the captured image, when the specified topology indicates that the user perceives composition of one-point perspective in the captured image, and (ii) information indicating that the user perceives composition of two-point perspective in the captured image by superimposing that information on a position of a building which is different from a position of the street where the user is, in the captured image, when the specified topology indicates that the user perceives composition of two-point perspective in the captured image. ### Claim 2 (depends on 1) The topology specifying method according to claim 1, wherein the specifying specifies the topology on the basis of (i) a type of composition specified based on the object information, and (ii) a pattern of changing a viewing position shown by the viewing position information. ### Claim 3 (depends on 2) The topology specifying method according to claim 2, wherein the specifying specifies (i) the topology showing that the user has an impression of stability when composition of one-point perspective is specified based on the object information and (ii) the topology showing that the user has an impression of openness when composition of two-point perspective is specified based on the object information. ### Claim 4 (depends on 2) The topology specifying method according to claim 2, wherein the specifying specifies the topology by detecting at least one of “paths,” “edges,” “districts,” “nodes,” and “landmarks” as an element estimated to be perceived by the user on the basis of a specified composition and a pattern of the user's eye movement. ### Claim 5 (depends on 1) The topology specifying method according to claim 1, wherein the specifying specifies the topology based on a position of an object visually perceived by the user. ### Claim 6 (depends on 1) The topology specifying method according to claim 1, wherein the specifying specifies the topology based on an angle of the user's looking around. ### Claim 7 (depends on 1) The topology specifying method according to claim 1, wherein the outputting outputs map information in which an image, showing the topology specified by the specifying, is superimposed on a map including information associated with the visible objects. ### Claim 8 (depends on 1) The topology specifying method according to claim 1, wherein the acquiring acquires, as the object information, a captured image that includes the visible objects, and the outputting outputs a guide image in which a route guidance image with an aspect corresponding to the topology is superimposed on the captured image. ### Claim 9 (depends on 8) The topology specifying method according to claim 8, wherein the outputting displays information of the topology on a screen, displaying the captured image including the visible objects. ### Claim 10 (depends on 1) The topology specifying method according to claim 1, wherein the acquiring acquires the captured image including the plurality of the visible objects, as object information, and the outputting outputs a guide image in which guide information is superimposed on the visible objects corresponding to the topology perceived by the user in the captured image. ### Claim 11 (depends on 1) The topology specifying method according to claim 1, wherein the acquiring acquires the captured image including the plurality of the visible objects, as object information, and the outputting outputs a guide image on which is superimposed guide information with an aspect that is determined on the basis of a type of the topology perceived by the user in the captured image. ### Claim 12 (depends on 11) The topology specifying method according to claim 11, wherein the outputting superimposes the guide information on the street where the user is, in the captured image, when the user perceives composition of one-point perspective in the captured image. ### Claim 13 (depends on 11) The topology specifying method according to claim 11, wherein the outputting superimposes the guide information on a position of a building where the user is not, in the captured image, when the user perceives composition of two-point perspective in the captured image. ### Claim 14 (depends on 1) The topology specifying method according to claim 1, wherein the outputting includes displaying, on the display visible to the user, (i) guide information indicating a name of the street by superimposing that guide information on the street where the user is, in the captured image, when the specified topology indicates that the user perceives composition of one-point perspective in the captured image, and (ii) guide information indicating a name of the building by superimposing that guide information on a position of the building which is different from a position of the street where the user is, in the captured image, when the specified topology indicates that the user perceives composition of two-point perspective in the captured image. ### Claim 15 A topology specifying apparatus, comprising: a processor configured to, acquire a captured image including a plurality of visible objects showing each shape of the visible objects viewed by a user and viewing position information showing a position or movement of the user's view in a visual recognition area viewed by the user; specify a topology of the visible objects, which is associated with the user's impression of the visible objects, on the basis of each shape of the visible objects included in the object information and the viewing position information; and output, to a display visible by the user, (i) information indicating that the user perceives composition of one-point perspective in the captured image by superimposing that information on a street where the user is, in the captured image, when the specified topology indicates that the user perceives composition of one-point perspective in the captured image, and (ii) information indicating that the user perceives composition of two-point perspective in the captured image by superimposing that information on a position of a building which is different from a position of the street where the user is, in the captured image, when the specified topology indicates that the user perceives composition of two-point perspective in the captured image. ### Claim 16 A non-transitory computer-readable storage medium storing a program for causing a computer to perform: acquiring a captured image including a plurality of visible objects that shows each shape of the visible objects viewed by a user and viewing position information that shows a position or movement of the user's view in a visual recognition area viewed by the user; specifying a topology of the visible objects which is associated with the user's impression of the visible objects on the basis of each shape of the visible objects included in the object information and the viewing position information; and outputting, to a display visible by the user, (i) information indicating that the user perceives composition of one-point perspective in the captured image by superimposing that information on a street where the user is, in the captured image, when the specified topology indicates that the user perceives composition of one-point perspective in the captured image, and (ii) information indicating that the user perceives composition of two-point perspective in the captured image by superimposing that information on a position of a building which is different from a position of the street where the user is, in the captured image, when the specified topology indicates that the user has perceived composition of two-point perspective in the captured image. ### Claim 17 A topology specifying method, comprising: acquiring a captured image including a plurality of visible objects that shows each shape of the visible objects viewed by a user and viewing position information that shows a position or movement of the user's view in a visual recognition area viewed by the user; specifying a topology of the visible objects that is associated with the user's impression of the visible objects on the basis of each shape of the visible objects included in the object information and the viewing position information; and turning on a lighting device provided in an aisle where the user is, in the captured image, when the specified topology indicates that the user perceives composition of one-point perspective in the captured image, and turning on a lighting device provided in a room at the end of aisle where the user is, in the captured image, when the specified topology indicates that the user has perceived composition of two-point perspective in the captured image.