Landmark Identification from Point Cloud Generated from Geographic Imagery Data

Abstract

Systems and methods for identifying prominent landmarks in a geographic area are provided. More particularly, geographic imagery data, such as panoramic images captured by a camera from a perspective at or near ground level, can be analyzed to identify landmarks depicted in the geographic imagery data. For instance, structure-from-motion techniques can be used to generate a point cloud of tracked features that are located a threshold distance away from one or more camera perspectives associated with the geographic imagery data. Landmarks that are visible from multiple camera perspectives and that are visible from greater distances relative to one or more camera perspectives can be identified as prominent landmarks in a geographic area. A geographic information system can use the prominent landmarks for a variety of purposes, such as for use in providing travel directions, for rendering landmarks in an emphasized style, and/or for constructing/displaying a three-dimensional model of the landmark.

1 - 20 . (canceled) 
     
     
         21 . A computer-implemented method, the method comprising:
 accessing, by the one or more processors, geographic imagery data captured from one or more cameras from a perspective at or near ground level;   generating, by the one or more processors, a point cloud based at least in part on the geographic imagery data, the point cloud comprising a plurality of data points, each of the plurality of data points associated with a tracked feature in the geographic imagery data;   identifying, by the one or more processors, a subset of data points in the point cloud, each data point in the subset located at least a threshold distance away from one or more camera perspectives associated with the geographic imagery data;   matching, by the one or more processors, one or more data points in the subset of data points with a landmark;   determining, by the one or more processors, a landmark ranking for the landmark based at least in part on the one or more data points; and   providing, by the one or more processors, data for rendering the landmark in a different style in a representation of a geographic area relative to other landmarks in the geographic area.   
     
     
         22 . The computer-implemented method of  claim 21 , wherein the different style is an emphasized style relative to the other landmarks. 
     
     
         23 . The computer-implemented method of  claim 21 , wherein the method comprises determining, by the one or more processors, a viewshed associated with the one or more data points in the subset of data points. 
     
     
         24 . The computer-implemented method of  claim 23 , wherein the viewshed for each of the one or more data points in the subset of data points comprises a set of camera perspectives associated with the geographic imagery data that view the data point. 
     
     
         25 . The computer-implemented method of  claim 23 , wherein the method comprises determining, by the one or more processors, a score for the landmark based at least in part on the viewshed determined for the one or more data points. 
     
     
         26 . The computer-implemented method of  claim 25 , wherein the score for the landmark is determined, by the one or more processors, based at least in part on a landmark ranking associated with the landmark in a geographic information system. 
     
     
         27 . The computer-implemented method of  claim 25 , wherein the score is used to prioritize landmarks in a geographic information system. 
     
     
         28 . The computer-implemented method of  claim 21 , wherein the point cloud is generated by the one or more processors using a structure-from-motion technique. 
     
     
         29 . The computer-implemented method of  claim 21 , wherein matching, by the one or more processors, one or more data points in the subset of data points with a landmark comprises:
 clustering, by the one or more processors, one or more data points in the subset of data points into a point cluster; and   matching, by the one or more processors, the point cluster with the landmark.   
     
     
         30 . The computer-implemented method of  claim 21 , wherein the geographic imagery data comprises street level images captured by the camera at a perspective associated with a ground level. 
     
     
         31 . A 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 geographic imagery data captured from one or more cameras from a perspective at or near ground level;   generating a point cloud based at least in part on the geographic imagery data using a structure-from-motion technique, the point cloud comprising a plurality of data points, each of the plurality of data points associated with a tracked feature in the geographic imagery data;   identifying a subset of data points in the point cloud, each data point in the subset of data points located at least a threshold distance away from one or more camera perspectives associated with the geographic imagery data;   matching one or more data points in the subset of data points with a landmark;   determining a landmark ranking for the landmark based at least in part on the one or more data points;   determining a viewshed associated with the one or more data points in the subset of data points, the viewshed for each of the one or more data points in the subset of data points comprising a set of camera perspectives associated with the geographic imagery data that view the one or more data points; and   determining a score for the landmark based at least in part on the viewshed determined for the one or more data points;   wherein the score is used to prioritize landmarks in a geographic information system.   
     
     
         32 . A tangible, non-transitory computer-readable media of claim  33 , wherein the operation of matching one or more data points in the subset of data points with a landmark comprises:
 clustering one or more data points in the subset of data points into a point cluster; and   matching the point cluster with the landmark.