# US 2021/0240762 A1 · Finding Locally Prominent Semantic Features for Navigation and Geocoding > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0240762 A1 - Document ID: US20210240762A1 - Status: Published application - Kind: A1 - Application number: 16/977,777 - Filed: 2018-10-22 - Published: 2021-08-05 - Earliest claimed: 2018-10-22 - Assignees: Google Inc. - Applicants: Google LLC - Inventors: Yan Mayster; Brian Brewington; Matthew Strosnick - Web page: https://patentgrep.com/patent/US20210240762A1 ## CPC - G01C 21/3644: {Landmark guidance, e.g. using POIs or conspicuous other objects} - G06F 16/587: using geographical or spatial information, e.g. location - G06F 16/29: Geographical information databases - G06F 16/583: using metadata automatically derived from the content - G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle - 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) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Provided are methods, systems, devices, apparatuses, and tangible non-transitory computer readable media for navigation and geocoding. The disclosed technology can perform operations including accessing semantic tags associated with images. Each of the semantic tags can be associated with features depicted by one of the images. Further, each of the features can be associated with a geographic location. Based on the semantic tags, landmarks that include the features that satisfy entropic criteria can be identified. The entropic criteria can measure a localized prominence of each of the one or more features. A landmark for use in navigation at the location can be selected based on context data associated with a location on a path that includes a plurality of locations. Furthermore, at least one navigational instruction that references the landmark can be generated. ## Claims ### Claim 1 A computer-implemented method of providing navigational instructions that reference landmarks, the method comprising: accessing, by a computing system comprising one or more processors, a plurality of semantic tags associated with a plurality of images, wherein each of the plurality of semantic tags is associated with one or more features depicted by one of the plurality of images, and wherein each of the one or more features is associated with a geographic location; identifying, by the computing system, based at least in part on the plurality of semantic tags, one or more landmarks that comprise the one or more features that satisfy one or more entropic criteria that measure a localized prominence of each of the one or more features; selecting, by the computing system, based at least in part on context data associated with a location on a path comprising a plurality of locations, at least one landmark for use in navigation at the location; and generating, by the computing system, at least one navigational instruction that references the at least one landmark. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein identifying, by the computing system, based at least in part on the plurality of semantic tags, one or more landmarks that comprise the one or more features that satisfy one or more entropic criteria that measure a localized prominence of each of the one or more features comprises: determining, by the computing system, based at least in part on the plurality of semantic tags, a rate at which each of the one or more features occurs within a predetermined area; and determining, by the computing system, that the one or more landmarks comprise the one or more features that occur the least frequently or that occur at a rate below a threshold rate. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein identifying, by the computing system, based at least in part on the plurality of semantic tags, one or more landmarks that comprise the one or more features that satisfy one or more entropic criteria that measure a localized prominence of each of the one or more features comprises: determining, by the computing system, a confidence score for each of the one or more features based at least in part on a number of times that each respective feature of the one or more features has been associated with a semantic tag of the plurality of semantic tags; and identifying as a landmark, by the computing system, the one or more features with a confidence score that satisfy one or more confidence score criteria. ### Claim 4 (depends on 3) The computer-implemented method of claim 3, wherein the confidence score is based at least in part on a number of different perspectives from which each of the one or more features associated with a semantic tag has been viewed, or a recency with which the one or more features have been associated with a semantic tag. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein identifying, by the computing system, based at least in part on the plurality of semantic tags, one or more landmarks that comprise the one or more features that satisfy one or more entropic criteria that measure a localized prominence of each of the one or more features comprises: determining, by the computing system, one or more clusters of the one or more features that satisfy the one or more entropic criteria, wherein each of the one or more clusters includes the one or more features that have a common semantic type. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein the context data comprises a vantage point associated with the location, and wherein selecting, by the computing system, based at least in part on context data associated with a location on a path comprising a plurality of locations, at least one landmark for use in navigation at the location comprises: determining, by the computing system, a visibility of each of the one or more landmarks from the vantage point associated with the location. ### Claim 7 (depends on 6) The computer-implemented method of claim 6, wherein the visibility is based at least in part on a distance from which each of the one or more landmarks is visible from the vantage point, an amount of light that is cast on each of the one or more landmarks, any obstructions between the vantage point and the one or more landmarks, or physical dimensions of each of the one or more landmarks. ### Claim 8 (depends on 6) The computer-implemented method of claim 6, wherein determining, by the computing system, a visibility of each of the one or more landmarks from the vantage point associated with the location comprises: determining, by the computing system, a direction of travel along the path at the vantage point; and determining, by the computing system, the one or more landmarks that face the direction of travel. ### Claim 9 (depends on 6) The computer-implemented method of claim 6, wherein determining, by the computing system, a visibility of each of the one or more landmarks from the vantage point associated with the location comprises: determining, by the computing system, the visibility based at least in part on a mode of transportation associated with the vantage point. ### Claim 10 (depends on 1) The computer-implemented method of claim 1, wherein selecting, by the computing system, based at least in part on context data associated with the location on the path comprising the plurality of locations, at least one landmark for use in navigation at the location comprises: determining, by the computing system, a reaction time based at least in part on a velocity at the location and a distance to a closest landmark of the one or more landmarks; and determining, by the computing system, the one or more landmarks that satisfy one or more reaction time criteria associated with a minimum reaction time. ### Claim 11 (depends on 10) The computer-implemented method of claim 10, wherein the reaction time is based at least in part on a mode of transportation associated with the location, and wherein the mode of transportation comprises a motor vehicle, a bicycle, or foot travel. ### Claim 12 (depends on 1) The computer-implemented method of claim 1, wherein selecting, by the computing system, based at least in part on context data associated with the location on the path comprising the plurality of locations, at least one landmark for use in navigation at the location comprises: selecting, by the computing system, the at least one landmark based at least in part on a level of familiarity with the one or more landmarks, wherein the level of familiarity is based at least in part on the user's previous association with the location or the one or more features of the one or more landmarks. ### Claim 13 (depends on 12) The computer-implemented method of claim 12, wherein generating, by the computing system, the at least one navigational instruction that references the at least one landmark comprises: adjusting, by the computing system, the at least one navigational instruction based at least in part on the level of familiarity. ### Claim 14 (depends on 1) The computer-implemented method of claim 1, further comprising: generating, by the computing system, a navigational instruction utility query associated with a utility of the at least one navigational instruction; receiving, by the computing system, one or more responses to the navigational instruction utility query; and adjusting, by the computing system, the one or more entropic criteria based at least in part on the one or more responses to the navigational instruction utility query. ### Claim 15 One or more tangible, non-transitory computer-readable media storing computer-readable instructions that when executed by one or more processors cause the one or more processors to perform operations, the operations comprising: accessing image data comprising a plurality of images associated with one or more semantic tags, wherein each of the one or more semantic tags is associated with one or more features of the plurality of images, and wherein each of the one or more features is associated with a geographic location; determining one or more landmarks comprising the one or more features that satisfy one or more entropic criteria associated with a localized prominence of each of the one or more features; determining, based at least in part on context data associated with a location of a vantage point on a path comprising a plurality of locations, the one or more landmarks associated with the vantage point; and generating navigational data comprising one or more indications associated with the one or more landmarks. ### Claim 16 (depends on 15) The one or more tangible, non-transitory computer-readable media of claim 15, wherein each of the one or more features is associated with a time of day, a season, a visual constancy, or one or more locations from which each of the one or more features is visible. ### Claim 17 (depends on 15) The one or more tangible, non-transitory computer-readable media of claim 15, wherein the one or more entropic criteria comprise a frequency of occurrence of each of the one or more features within a predetermined area not exceeding a predetermined threshold frequency, a temporal persistence of each of the one or more features at a location exceeding a predetermined threshold duration, or a size of each of the one or more features exceeding a threshold size. ### Claim 18 A computing system comprising: one or more processors; one or more non-transitory computer-readable media storing instructions that when executed by the one or more processors cause the one or more processors to perform operations comprising: accessing image data comprising a plurality of images associated with one or more semantic tags, wherein each of the one or more semantic tags is associated with one or more features of the plurality of images, and wherein each of the one or more features is associated with a geographic location; determining one or more landmarks comprising the one or more features that satisfy one or more entropic criteria associated with a localized prominence of each of the one or more features; determining, based at least in part on context data associated with a location of a vantage point on a path comprising a plurality of locations, the one or more landmarks associated with the vantage point; and generating navigational data comprising one or more indications associated with the one or more landmarks. ### Claim 19 (depends on 18) The computing system of claim 18, wherein the one or more indications comprise one or more visual indications associated with a relative location of the one or more landmarks on the path with respect to the vantage point, or one or more audible indications associated with the relative location of the one or more landmarks on the path with respect to the vantage point. ### Claim 20 (depends on 18) The computing system of claim 18, wherein determining one or more landmarks comprising the one or more features that satisfy one or more entropic criteria associated with a localized prominence of each of the one or more features comprises: determining a mode of travel associated with the vantage point; and determining, based at least in part on a direction of travel and velocity along the path, the one or more landmarks that will be visible from the vantage point within a predetermined time period associated with the mode of travel.