Google Patent | Method and system for navigating in panoramic images using voxel maps

Patent: Method and system for navigating in panoramic images using voxel maps

Publication Number: 10186083

Publication Date: 2019-01-22

Applicants: Google

Abstract

The present disclosure describes a system and method that includes receiving a user selection of a portion of a first image. In response to the user-selection, a first identifier of three-dimensional space associated with the user-selection is determined and a second image is selected based on a portion of the second image being associated with the first identifier. The second image may be provided to the user to be displayed. The present disclosure also provides for mapping a portion of a first image to an identifier of three-dimensional space.

Background

When viewing imagery, such as images of a geographic location, users are limited to imagery that has been previously stored in association with the viewed image. For example, if the user desires to see a different aspect of the geographical location, subsequent images may be determined based on an image-based identifier. In this regard, the subsequent images may or may not focus on the aspect the user desires to view.

Summary

The present disclosure describes interconnecting imagery using spatial identifiers. In this regard, an image may include a plurality of spatial identifiers that identify a geographic space associated with objects and features included in the image. The spatial identifiers may be used to retrieve and select additional images when a user clicks on a portion of the image associated with the geographic position identified by the spatial identifier.

One aspect of the disclosure describes a system that includes one or more computing devices and a memory. The memory stores instructions and data, such as a plurality of images. A portion of each of the plurality of images may include an object, and the portion may be associated with an identifier of a range of three-dimensional space that contains at least a portion of the surface of such object.

The one or more computing devices may be programmed to receive a user selection of a portion of a first image of the plurality of images. The one or more computing devices may then determine a first identifier of three-dimensional space associated with the user-selection and select a second image based on a portion of the second image being associated with the first identifier. The one or more computing devices may subsequently provide the second image for display to the user.

According to some examples, the user selection may include clicking on the first portion of the first image. In some examples, the first portion may be a pixel of the first image.

In some examples, the one or more computing devices may be programmed to create a scored listing of the plurality of images associated with the first identifier and select the second image from the scored listing.

In another example, the first identifier may represent a three-dimensional representation of space in a hierarchical tree of space, such as a voxel.

Another aspect of the disclosure provides a method that includes receiving a user selection of a portion of a first image, determining a first identifier of three-dimensional space associated with the user-selection, selecting a second image from a plurality of images based on a portion of the second image being associated with the first identifier, and providing the second image for display to the user. In this regard, the user selection may include clicking on the first portion of the first image. In some examples, the first portion may include a pixel or a subset of pixels.

In one example, the method may include creating a scored listing of the plurality of images associated with the first identifier and selecting the second image from the scored listing of the plurality of images.

According to other examples, the first identifier may represent a three-dimensional representation of space in a hierarchical tree of space. For example, the three-dimensional space may be a voxel.

A further aspect of the disclosure provides a system for mapping a portion of a first image to an identifier of three-dimensional space. The system may include one or more computing devices and a memory that stores instructions and data, such as a plurality of images.

The one or more computing devices may be programmed to generate a plurality of spatial identifiers. Each of the spatial identifiers may identify a range of three-dimensional space that contains the surface of an object represented by a three-dimensional model. In this regard, the one or more computing devices may be programmed to determine, for a first image captured from a first location, a first ray extending in three-dimensional space from a first location through a first portion of a first image. The one or more computing devices may then determine a first spatial identifier associated with the range of three-dimensional space that contains the intersection of the first ray with the three-dimensional model of the object and associate the first portion of the first image with the first spatial identifier.

In some examples, the one or more computing devices may be further programmed to determine, for a second image captured from a second location, a second ray extending in three-dimensional space from the second location through a second portion of a second image and determine a second spatial identifier associated with the range of three-dimensional space that contains the intersection of the second ray with the three-dimensional model of the object. The one or more computing devices may then associate the second portion of the second image with the first spatial identifier when the first spatial identifier and second spatial identifier identify the same range of three-dimensional space. According to some examples, the three-dimensional space may be a voxel.

Another aspect of the disclosure describes a method for mapping a portion of a first image to an identifier of three-dimensional space that includes generating a plurality of spatial identifiers. The method may then determine, for a first image captured from a first location, a first ray extending in three-dimensional space from the first location through a first portion of a first image and determine a first spatial identifier associated with the range of three-dimensional space that contains the intersection of the first ray with the three-dimensional model of the object. The method may then associate the first portion of the first image with the first spatial identifier. In some examples, each spatial identifier may identify a range of three-dimensional space that contains the surface of an object represented by a three-dimensional model.

The method may further include determining, for a second image captured from a second location, a second ray extending in three-dimensional space from the second location through a second portion of a second image. Accordingly, the method may determine a second spatial identifier associated with the range of three-dimensional space that contains the intersection of the second ray with the three-dimensional model of the object and associate the second portion of the second image with the first spatial identifier when the first spatial identifier and second spatial identifier identify the same range of three-dimensional space.

发表评论

电子邮件地址不会被公开。 必填项已用*标注