# US 10,762,364 B2 · Method, apparatus, and system for traffic sign learning > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,762,364 B2 - Document ID: US10762364B2 - Status: Granted - Kind: B2 - Application number: 15/957,518 - Filed: 2018-04-19 - Published: 2019-10-24 - Granted: 2020-09-01 - Earliest claimed: 2018-04-19 - Assignees: HERE Global B.V. - Applicants: Here Global B.V. - Inventors: Leon Stenneth; Sebastian Zaba; Zhenhua Zhang; Lakshmi Nookala; Prashant Chauhan; Pradeepa Kavindapadi Nagarajan; Yu Yang Bai - Web page: https://patentgrep.com/patent/US10762364B2 ## CPC - G08G 1/0112: {from the vehicle, e.g. floating car data [FCD]} - G06F 16/29: Geographical information databases - G06F 16/35: Clustering; Classification - G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques} - G06F 18/22: Matching criteria, e.g. proximity measures - G06F 18/23: Clustering techniques - G06V 10/75: Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries - G06V 10/762: using clustering, e.g. of similar faces in social networks - G06V 10/774: Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting - G06V 20/582: {of traffic signs} - G06V 30/422: Technical drawings; Geographical maps - G08G 1/0129: {for creating historical data or processing based on historical data} - G08G 1/0141: {for traffic information dissemination} - G08G 1/09623: {Systems involving the acquisition of information from passive traffic signs by means mounted on the vehicle (G08G1/0967 takes precedence)} - B60R 2300/302: combining image information with GPS information or vehicle data, e.g. vehicle speed, gyro, steering angle data - G08G: TRAFFIC CONTROL SYSTEMS (guiding railway traffic, ensuring the safety of railway traffic B61L; arrangement of road signs or traffic signals E01F9/00; radar or analogous systems, sonar systems, lidar systems specially adapted for traffic control G01S13/91, G01S15/88, G01S17/88; {radar or analogous systems, sonar systems, lidar systems specially adapted for anti-collision purposes G01S13/93, G01S15/93, G01S17/93}) - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - B60R: VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR ## Abstract An approach is provided for traffic sign learning. The approach involves, for example, receiving a plurality of traffic sign observations generated using sensor data collected from a plurality of vehicles. Each of the plurality of traffic sign observations includes location data and sign property data for an observed traffic sign corresponding to said each of the plurality of traffic sign observations. The approach also involves clustering the plurality of traffic speed sign observations into at least one cluster based on the location data and the sign property data. The approach further involves determining a learned sign for the at least one cluster, and determining a learned sign value indicated by the learned sign based on the location data, the sign property data, or a combination of the plurality of traffic sign observations aggregated in the at least one cluster. ## Claims ### Claim 1 A computer-implemented method for traffic sign learning comprising: receiving a plurality of traffic sign observations generated using sensor data collected from a plurality of vehicles, wherein each of the plurality of traffic sign observations includes location data and sign property data for an observed traffic sign corresponding to said each of the plurality of traffic sign observations; determining whether a number of the plurality of traffic sign observations satisfies a pre-determined threshold; clustering, according to the determination, the plurality of traffic sign observations into at least one cluster based on the location data and the sign property data; determining a learned sign for the at least one cluster; and determining a learned sign value indicated by the learned sign based on the location data, the sign property data, or a combination of the plurality of traffic sign observations aggregated in the at least one cluster. ### Claim 2 (depends on 1) The method of claim 1, wherein the observed traffic sign is a traffic speed sign, and wherein the learned sign value is a traffic speed indicated by the learned sign for a road segment corresponding to a learned sign location. ### Claim 3 (depends on 2) The method of claim 2, wherein the learned sign location is determined based on a mean of the location data for the plurality of traffic sign observations aggregated in the at least one cluster. ### Claim 4 (depends on 1) The method of claim 1, wherein the sign property data includes a sign value, a sign type, a side of a road on which the observed traffic sign is detected, a time stamp, or a combination thereof; and wherein the location data includes a location, a heading, a speed, or a combination thereof of a reporting vehicle when the observed traffic sign is detected. ### Claim 5 (depends on 4) The method of claim 4, further comprising: map matching the location, the heading, or a combination thereof of the reporting vehicle to one or more records of a geographic database, wherein the location data is based on the map matching. ### Claim 6 (depends on 1) The method of claim 1, further comprising: determining a confidence value, an accuracy level, or a combination thereof for the learned sign, the learned sign value, or a combination thereof; and selecting between (1) providing the learned sign, the learned sign value, or a combination thereof, and (2) providing traffic sign data from an alternate data source based on the confidence value, the accuracy level, or a combination thereof. ### Claim 7 (depends on 1) The method of claim 1, further comprising: associating the learned sign value with a road link record of a geographic database. ### Claim 8 (depends on 1) The method of claim 1, further comprising: providing the learned sign value for presenting a mapping user interface on a device, operating an autonomous vehicle, or a combination thereof. ### Claim 9 (depends on 1) The method of claim 1, further comprising: updating a road link record of a geographic database based on the learned sign value. ### Claim 10 An apparatus for road sign learning comprising: at least one processor; and at least one memory including computer program code for one or more programs, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following, select road sign data from either learned road sign data or alternate road sign data based on one or more rules, wherein the learned road sign data is determined based on clustering, according to a determination that a number of a plurality of road sign observations satisfies a pre-determined threshold, the plurality of road sign observations according to location data and sign property data generated using sensor data collected from a plurality of vehicles; and provide the selected road sign data for presenting a mapping user interface on a device, operating an autonomous vehicle, or a combination thereof. ### Claim 11 (depends on 10) The apparatus of claim 10, wherein the one or more rules for determining the selected road sign data for a road link of interest are stored in a filter layer of a geographic database. ### Claim 12 (depends on 11) The apparatus of claim 11, wherein the alternate road sign data is a road sign attribute stored for the road link in the geographic database, and wherein the one or more rules select the stored road sign attribute when the learned road sign data is not available for the road link. ### Claim 13 (depends on 11) The apparatus of claim 11, wherein the one or more rules select the learned road sign data over the alternate road sign data when the learned road sign data is available for the road link. ### Claim 14 (depends on 11) The apparatus of claim 11, wherein the alternate road sign data is available from an alternate road sign service, and wherein the one or more rules are used to select from among the alternate road sign data, the learned road sign data, and a road sign attribute stored for the road link in the geographic database. ### Claim 15 (depends on 14) The apparatus of claim 14, wherein the selecting of the road sign data is based on a historic and/or real-time confidence level, a historic and/or real-time accuracy level, or a combination thereof of the alternate road sign data, the learned road sign data, the road sign attribute, the geographic database, the alternate road sign service, or a combination thereof. ### Claim 16 A non-transitory computer-readable storage medium for traffic sign learning, carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to perform: clustering, according to a determination that a number of a plurality of traffic sign observations satisfies a pre-determined threshold, the plurality of traffic sign observations into one or more clusters, wherein the plurality of traffic sign observations relate to at least one traffic speed sign detected from sensor data of a plurality of vehicles, and wherein the plurality of traffic sign observations includes data indicating a sign speed value, a sign type, a location of a reporting vehicle when a respective traffic sign observation is made, a side of a road on which the respective traffic sign observation is made, a time stamp, or a combination thereof; determining a learned sign speed value based on the one or more sign clusters; and updating a speed attribute of a road link record of a geographic database based on the learned sign value. ### Claim 17 (depends on 16) The non-transitory computer-readable storage medium of claim 16, wherein the clustering uses density-based clustering to aggregate the plurality of traffic sign observations into the one or more clusters based on a similarity with respect to the sign speed value, the sign type, the location of the reporting vehicle, the side of the road, the time stamp, or a combination thereof. ### Claim 18 (depends on 16) The non-transitory computer-readable storage medium of claim 16, wherein the clustering is further based on a distance threshold applied to the location of the reporting vehicle. ### Claim 19 (depends on 16) The non-transitory computer-readable storage medium of claim 16, wherein the apparatus is further caused to perform: merging at least two clusters of the one or more clusters based on determining the at least two clusters are within a threshold distance. ### Claim 20 (depends on 16) The non-transitory computer-readable storage medium of claim 16, wherein a learned sign location is determined based on a mean of the location of the reporting vehicle for the plurality of traffic sign observations clustered into a respective cluster of the one or more clusters.