Optically challenging surface detection for augmented reality

Abstract

Approaches in accordance with various embodiments provide for the presentation of augmented reality (AR) content with respect to optically challenging surfaces. Such surfaces can be difficult to locate using conventional optical-based approaches that rely on visible features. Embodiments can utilize the fact that horizontal surfaces can be located relatively easily, and can determine intersections or boundaries of those horizontal surfaces that likely indicate the presence of another surface, such as a vertical wall. This boundary can be determined automatically, through user input, or using a combination of such approaches. Once such an intersection is located, a virtual plane can be determined whose relative location to a device displaying AR content can be tracked and used as a reference for displaying AR content.

What is claimed is: 
     
         1 . A computer-implemented method, comprising:
 initiating an augmented reality (AR) session on a computing device;   receiving image data representative of a scene in a physical environment;   identifying an intersection between at least a first surface and a second surface detected in the physical environment, based at least in part on a detected boundary of the first surface, the second surface being less detectable than the first surface; and   generating a virtual plane, for the AR session, corresponding to the second surface.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the first surface is a horizontal surface. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein the second surface is a vertical surface. 
     
     
         4 . The computer-implemented method of  claim 1 , wherein the first surface is identified by a visual odometry process. 
     
     
         5 . The computer-implemented method of  claim 4 , wherein the second surface is unable to be detected using the visual odometry process that identified the first surface. 
     
     
         6 . The computer-implemented method of  claim 1 , wherein the first surface is determined by identifying an object located on the first surface. 
     
     
         7 . The computer-implemented method of  claim 1 , further comprising:
 prompting a user for confirmation of the boundary if a confidence level for the boundary falls below a minimum confidence threshold.   
     
     
         8 . The computer-implemented method of  claim 1 , further comprising:
 rendering the virtual plane as an overlay over a live view of the scene for display on the computing device.   
     
     
         9 . The computer-implemented method of  claim 1 , further comprising:
 prompting a user to select the first surface from the image data.   
     
     
         10 . The computer-implemented method of  claim 1 , further comprising:
 receiving a selection, from a user, of a location corresponding to the boundary for use in the AR session.   
     
     
         11 . A computer-implemented method, comprising:
 initiating an augmented reality (AR) session on a computing device;   receiving, from a camera of the computing device, image data representative of a scene in a physical environment;   identifying an intersection between at least a first surface and a second surface detected in the physical environment, based at least in part on a boundary of the first surface; and   generating a virtual plane for the AR session, the virtual plane being locked at a position along the boundary and extending proximate to the second surface.   
     
     
         12 . The computer-implemented method of  claim 11 , wherein the first surface is a horizontal surface. 
     
     
         13 . The computer-implemented method of  claim 11 , wherein the second surface is a vertical surface. 
     
     
         14 . The computer-implemented method of  claim 11 , wherein the first surface is identified by a visual odometry process. 
     
     
         15 . The computer-implemented method of  claim 14 , wherein the second surface is unable to be detected using the visual odometry process that identified the first surface. 
     
     
         16 . The computer-implemented method of  claim 11 , further comprising:
 obtaining orientation information from the computing device; and   utilizing the orientation information in the AR session.   
     
     
         17 . A system, comprising:
 at least one processor; and   memory including instructions that, when executed by the at least one processor, cause the system to:
 initiate an augmented reality (AR) session on a computing device; 
 receive, from a camera of the computing device, image data representative of a scene in a physical environment; 
 identify an intersection between at least at least a first surface and a second surface detected in the physical environment, based at least in part on a boundary of the first surface; and 
 generate a virtual plane, for the AR session, locked at a position along the boundary and extending proximate to the second surface. 
   
     
     
         18 . The system of  claim 17 , wherein the first surface is a horizontal surface. 
     
     
         19 . The system of  claim 17 , wherein the second surface is a vertical surface. 
     
     
         20 . The system of  claim 17 , wherein the first surface is determined by a visual odometry process.