# US 2021/0271900 A1 · Lane count estimation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0271900 A1 - Document ID: US20210271900A1 - Status: Published application - Kind: A1 - Application number: 17/322,310 - Filed: 2021-05-17 - Published: 2021-09-02 - Earliest claimed: 2019-01-02 - Assignees: HERE Global B.V. - Applicants: HERE Global B.V. - Inventors: Abhilshit Soni; Akshay Pachaar - Web page: https://patentgrep.com/patent/US20210271900A1 ## CPC - G06V 10/763: {Non-hierarchical techniques, e.g. based on statistics of modelling distributions} - G06V 20/56: exterior to a vehicle by using sensors mounted on the vehicle - G06V 20/588: {Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A method for assigning a number of lanes and a direction of travel on a path includes receiving location data including a plurality of location points, projecting the plurality of location points on to an aggregation axis perpendicular to a centerline of the vehicle path, grouping the plurality of location points as projected onto the aggregation axis into one or more clusters, and determining the number of vehicle lanes of the vehicle path based on a count of the one or more clusters. ## Claims ### Claim 1 A method for assigning a number of vehicle lanes to a vehicle path, the method comprising: receiving, via a processor, a plurality of location points including locations of a plurality of vehicles; projecting, via the processor, the plurality of location points on to an aggregation axis; grouping, by the processor, the plurality of location points as projected onto the aggregation axis into one or more clusters; and determining, by the processor, the number of vehicle lanes based on a count of the one or more clusters. ### Claim 2 (depends on 1) The method of claim 1, further comprising: determining, by the processor, a standard deviation of linear positions of the plurality of location points as projected onto the aggregation axis; and removing, by the processor, an outlier subset of location points of the plurality of location points based on the standard deviation to define a remainder, wherein the remainder is grouped into the one or more clusters. ### Claim 3 (depends on 2) The method of claim 2, further comprising: determining, by the processor, a mean of the linear positions of the plurality of location points as projected onto the aggregation axis; and determining, by the processor, a linear range on the aggregation axis based on the mean and the standard deviation, wherein the outlier subset of location points includes location points located outside of the linear range. ### Claim 4 (depends on 1) The method of claim 1, further comprising: fitting, via the processor, one or more linear path segments to the vehicle path; and matching, by the processor, a subset of the plurality of location points to each of the one or more linear path segments. ### Claim 5 (depends on 4) The method of claim 4, wherein the number of vehicle lanes of the vehicle path is determined based on a number of lanes of a majority of the one or more linear path segments. ### Claim 6 (depends on 1) The method of claim 1, further comprising: selecting, by the processor, a representative location point from a subset of vehicle-common location points of the plurality of location points; and removing, by the processor, the subset of location points other than the representative location point from the plurality of location points. ### Claim 7 (depends on 6) The method of claim 6, further comprising: determining, by the processor, a centroid of the subset of vehicle-common location points, wherein the representative location point is selected based on the centroid. ### Claim 8 (depends on 6) The method of claim 6, further comprising: projecting, by the processor, the subset of vehicle-common location points onto a line perpendicular to a centerline of the vehicle path; determining, by the processor, a mean of the subset of vehicle-common location points as projected onto the line, wherein the representative location point is selected based on the mean. ### Claim 9 (depends on 1) The method of claim 1, further comprising: determining, by the processor, a density of the plurality of location points along the aggregation axis; and removing, by the processor, a subset of location points of the plurality of location points having a density below a threshold density. ### Claim 10 (depends on 1) The method of claim 1, wherein the grouping is performed based on a plurality of cluster criteria, and wherein the method further comprises: determining, by the processor, a degree of overlap between the one or more clusters for each grouping performed based the plurality of cluster criteria; and selecting, by the processor, the one or more clusters grouped according to a first cluster criterion of the plurality of cluster criteria with a least degree of overlap between the one or more clusters. ### Claim 11 (depends on 10) The method of claim 10, further comprising: determining, by the processor, a silhouette coefficient for the plurality of location points, the silhouette coefficient indicating a similarity between the plurality of location points for each grouping performed based the plurality of cluster criteria, wherein the one or more clusters is selected based on a second cluster criterion of the plurality of cluster criteria that maximizes a total silhouette coefficient of the plurality of location points. ### Claim 12 An apparatus for assigning a number of vehicle lanes to a vehicle path, the apparatus comprising: a controller comprising a memory and a processor, the memory storing instructions that, when executed by the processor, are operable to: receive a plurality of location points including locations of a plurality of vehicles; project the plurality of location points on to an aggregation axis group the plurality of location points as projected onto the aggregation axis into one or more clusters; and determine the number of vehicle lanes of the vehicle path based on a count of the one or more clusters. ### Claim 13 (depends on 12) The apparatus of claim 12, wherein the memory stores instructions that, when executed by the processor, are further operable to: determine one or more mathematical quantities based on the plurality of location points; and remove a portion of the plurality of location points. ### Claim 14 (depends on 13) The apparatus of claim 13, wherein the one or more mathematical quantities includes a standard deviation of linear positions of the plurality of location points as projected onto the aggregation axis, wherein the portion of the plurality of location points is an outlier subset of the plurality of location points based on the standard deviation, and wherein the memory stores instructions that, when executed by the processor, are further operable to group location points of the plurality of location points not included in the outlier subset into the one or more clusters. ### Claim 15 (depends on 14) The apparatus of claim 14, wherein the one or more mathematical quantities includes a mean of the linear positions of the plurality of location points as projected onto the aggregation axis and a linear range on the aggregation axis based on the mean and the standard deviation, and wherein the outlier subset includes location points located outside of the linear range. ### Claim 16 (depends on 13) The apparatus of claim 13, wherein the plurality of location points are recorded by a vehicle of the plurality of vehicles, wherein the one or more mathematical quantities includes a centroid of the plurality of location points recorded by the vehicle, and wherein the portion of the plurality of location points includes a plurality of location points recorded by the vehicle other than a representative location point, the representative location point being based on the centroid. ### Claim 17 (depends on 13) The apparatus of claim 13, wherein the one or more mathematical quantities includes a density of the plurality of location points along the aggregation axis, and wherein the portion of the plurality of location points includes a subset of location points of the plurality of location points having a density below a threshold density. ### Claim 18 (depends on 13) The apparatus of claim 13, wherein the memory stores instructions that, when executed by the processor, are further operable to: repeat grouping the plurality of location points as projected onto the aggregation axis into one or more clusters for each of a plurality of cluster criteria, wherein the one or more mathematical quantities includes a degree of overlap between the one or more clusters for each grouping according to the plurality of criteria; and select a grouping according to a cluster criterion of the cluster criteria which resulted in a least degree of overlap between the one or more clusters. ### Claim 19 (depends on 12) The apparatus of claim 12, wherein the memory stores instructions that, when executed by the processor, are further operable to: fit one or more linear path segments to the vehicle path and match one or more subsets of the plurality of location points to each linear path segment of the one or more linear path segments; project the plurality of location points and group location points of the plurality of location points into the one or more clusters for each linear path segment of the one or more linear path segments and for the one or more subsets matched to each respective path segment; and determine a number of vehicle lanes for each linear path segment of the one or more linear path segments based on the count of the one or more clusters associated with each linear path segment. ### Claim 20 A non-transitory computer-readable medium including instructions that when executed are operable to: receive a plurality of location points representing a plurality of mobile devices traversing a path in a travel direction; project the plurality of location points on to an aggregation axis of the path; group the plurality of location points travel into one or more clusters based on the location points as projected onto the aggregation axis; and determine a number of traffic lanes and a direction of the path based on a count of the one or more clusters and the travel direction.