Interactive geo-positioning of imagery

Abstract

An interactive user-friendly incremental calibration technique that provides immediate feedback to the user when aligning a point on a 3D model to a point on a 2D image. A can drag-and-drop points on a 3D model to points on a 2D image. As the user drags the correspondences, the application updates current estimates of where the camera would need to be to match the correspondences. The 2D and 3D images can be overlayed on each other and are sufficiently transparent for visual alignment. The user can fade between the 2D/3D views providing immediate feedback as to the improvements in alignment. The user can begin with a rough estimate of camera orientation and then progress to more granular parameters such as estimates for focal length, etc., to arrive at the desired alignment. While one parameter is adjustable, other parameters are fixed allowing for user adjustment of one parameter at a time.

What is claimed is: 
     
         1 . A computer-implemented image calibration method, comprising:
 selecting a 3D map that approximates a scene in an image for calibration;   rendering a virtual view as a semi-transparent overlay on the image based on positioning of a camera in the 3D map and defining a view direction of the camera in the 3D map relative to a perspective of a scene in the image;   dragging-and-dropping a virtual point in the virtual view to a corresponding image point in the image;   dynamically rendering changes in perspective of the virtual view based on drag-and-drop of the virtual point; and   registering the virtual view to the image based on the virtual point.   
     
     
         2 . The method of  claim 1 , wherein, in the registering, a starting point is received as a location of a camera and a view direction relative to the camera. 
     
     
         3 . The method of  claim 2 , wherein the starting point further considers elevation of the camera, average height of a user at the camera location, and focal length of the camera. 
     
     
         4 . The method of  claim 1 , wherein the rendering includes presenting the image and the virtual view side-by-side for a drag-and-drop operation. 
     
     
         5 . The method of  claim 1 , further comprising fading in or fading out at least one of the image and the semi-transparent overly. 
     
     
         6 . The method of  claim 1 , wherein the virtual point is a first virtual point, and the method further comprises:
 receiving a selection of a second point in the virtual view; and   registering the virtual view to the image based on the virtual point and the second virtual point.   
     
     
         7 . A system for calibrating an image, the system comprising:
 at least one processor; and   a memory storing instructions that, when executed by the at least one processor, causes the at least one processor to perform a method including:
 selecting a 3D map that approximates a scene in an image for calibration; 
 rendering a virtual view as a semi-transparent overlay on the image based on positioning of a camera in the 3D map and defining a view direction of the camera in the 3D map relative to a perspective of a scene in the image; 
 dragging-and-dropping a virtual point in the virtual view to a corresponding image point in the image; 
 dynamically rendering changes in perspective of the virtual view based on drag-and-drop of the virtual point; and 
 registering the virtual view to the image based on the virtual point. 
   
     
     
         8 . The system of  claim 7 , wherein, in the registering, a starting point is received as a location of a camera and a view direction relative to the camera. 
     
     
         9 . The system of  claim 8 , wherein the starting point further considers elevation of the camera, average height of a user at the camera location, and focal length of the camera. 
     
     
         10 . The system of  claim 7 , wherein the rendering includes presenting the image and the virtual view side-by-side for a drag-and-drop operation. 
     
     
         11 . The method of  claim 7 , further comprising fading in or fading out at least one of the semi-transparent overlay and the image. 
     
     
         12 . The system of  claim 7 , further comprising a 3D datasource from which the 3D map is retrieved and ground control points and lines are defined, based on the image. 
     
     
         13 . The system of  claim 7 , wherein the virtual point is a first virtual point, and the instructions further comprise instructions for:
 receiving a selection of a second point in the virtual view; and   registering the virtual view to the image based on the virtual point and the second virtual point.   
     
     
         14 . A computer-implemented calibration system, comprising:
 at least one processor; and   a memory storing instructions that, when executed by the at least one processor, causes the execution of a method that includes:
 selecting a 3D map that approximates a scene in an image for calibration; 
 rendering a virtual view as a semi-transparent overlay on the image based on positioning of a camera in the 3D map and defining a view direction of the camera in the 3D map relative to a perspective of a scene in the image; 
 dragging-and-dropping a virtual point in the virtual view to a corresponding image point in the image; 
 dynamically rendering changes in perspective of the virtual view based on drag-and-drop of the virtual point; and 
 registering the virtual view to the image based on the virtual point. 
   
     
     
         15 . The system of  claim 14 , further comprising a 3D datasource from which the 3D map is retrieved and ground control points and lines are defined, based on the image. 
     
     
         16 . The system of  claim 14 , wherein the instructions include receiving a starting point of the registration process as a location of a camera and a view direction relative to the camera. 
     
     
         17 . The system of  claim 16 , wherein the starting point further considers elevation of the camera, average height of a user at the camera location, focal length of the camera. 
     
     
         18 . The system of  claim 17 , wherein parameters of the camera are locked after registration. 
     
     
         19 . The system of  claim 14 , wherein the virtual point is a first virtual point, and wherein the instructions further comprise:
 instructions to receive a selection of a second point in the virtual view; and   instructions to register the virtual view to the image based on the virtual point and the second virtual point.