Feature selection for image based location determination

Patent metadata

Field	Value
Publication number	US-9288636-B2
Application number	US-201314075621-A
Country	US
Kind code	B2
Filing date	Nov 8, 2013
Priority date	Nov 8, 2013
Publication date	Mar 15, 2016
Grant date	Mar 15, 2016

Abstract

Feature selection is provided for geometry data in an image-based based location determination. For example, one or more computing devices may receive information collected for a particular area. The one or more computing devices may identify one or more features and associated location from the received information. Given ones of the identified one or more features are selected based on a characteristic of a user. The selected ones of the one or more features and the associated locations are used to generate a set of geometry data for the particular area.

First claim

The invention claimed is:

1. A computer-implemented method comprising:
receiving, by one or more computing devices, information collected at a particular area;
identifying, by the one or more computing devices, various objects as well as the shapes of the various objects and associated locations of the various objects from the received information;
generating, by the one or more computing devices, three-dimensional geometry data for the particular area using the identified one or more features, wherein the geometry data includes a plurality of points and vectors defining the associated locations and shapes of the various objects within the particular area;
filtering, by the one or more computing devices, the three-dimensional geometry data to remove points and vectors of the three-dimensional geometry data that define at least one object of the various objects based on a characteristic identifying a first type of user in order to generate a subset of the three-dimensional geometry data for the particular area and for the first type user;
storing, by the one or more computing devices, the subset of three-dimensional geometry data for the particular area for the first type of user;
receiving, by the one or more computing devices, from a client computing device associated with a first user, user input identifying a type of the first user;
when the client computing device enters the particular area, receiving, by the one or more computing devices from the client computing device, a request for information for determining the location of the client device;
determining, by the one or more computing devices, the type of the first user as the first type of user;
retrieving, by the one or more computing devices, the stored subset of three-dimensional geometry data for the particular area and for the first type of user based on the determination; and
providing in response to the request and based on the determination, by the one or more computing devices, the retrieved subset of the three-dimensional geometry data for the particular area and for the first type of user to the client computing device, wherein the three-dimensional geometry data is configured to allow the client computing device to determine a location in the particular area from an image captured by the client computing device.

2. The method of claim 1 , wherein the filtering further includes removing three-dimensional geometry data corresponding to objects in locations where that user is not likely to be at the particular area.

3. The method of claim 1 , wherein the filtering further includes removing three-dimensional geometry data corresponding to objects in locations where that user is likely to be lost at the particular area.

4. The method of claim 1 , wherein the filtering is further based on a type of activity performed by users.

5. The method of claim 1 , wherein the filtering is further based on a storage attribute of a mobile computing device.

6. The method of claim 1 , wherein the filtering is further based on a processing power attribute of a mobile computing device.

7. A system comprising one or more computing devices, each of the one or more computing devices having one or more processors, the one or more computing devices being configured to:
receive information collected at an particular area;
identify various objects as well as the shapes of the various objects and associated locations of the various objects from the received information;
generate three-dimensional geometry data for the particular area using the identified one or more features, wherein the geometry data includes a plurality of points and vectors defining the associated locations and shapes of the various objects within the particular area;
filtering the three-dimensional geometry data to remove points and vectors of the three-dimensional geometry data that define at least one object of the various objects based on a characteristic identifying a first type of user in order to generate a subset of the three-dimensional geometry data for the particular area and for the first type of user;
store, by the one or more computing devices, the subset of three-dimensional geometry data for the particular area for the first type of user;
receive, by the one or more computing devices, from a client computing device associated with a first user, user input identifying a type of the first user;
when the client computing device enters the particular area, receive, from the client computing device, a request for information for determining the location of the client device;
determine the type of the first user as the first type of user;
retrieve the stored subset of three-dimensional geometry data for the particular area and for the first type of user based on the determination; and
providing in response to the request and based on the determination, the retrieved subset of the three-dimensional geometry data for the particular area and for the first type of user to the client computing device, wherein the three-dimensional geometry data is configured to allow the client computing device to determine a location in the particular area from an image captured by the client computing device.

8. The system of claim 7 , wherein the filtering further includes removing three-dimensional geometry data corresponding to objects in locations where that user is not likely to be at the particular area.

9. The system of claim 7 , wherein the filtering further includes removing three-dimensional geometry data corresponding to objects in locations where that user is likely to be lost at the particular area.

10. The system of claim 7 , wherein the filtering is further based on a type of activity performed by users.

11. The system of claim 7 , wherein the filtering is further based on a storage attribute of a mobile computing device.

12. The system of claim 7 , wherein the filtering is further based on a processing power attribute of a mobile computing device.

13. A non-transitory, computer-readable storage device on which computer readable instructions of a program are stored, the instructions, when executed by one or more processors, cause the one or more processors to perform a method, the method comprising:
receiving information collected at a particular area;
identifying various objects as well as the shapes of the various objects and associated locations of the various objects from the received information;
generating three-dimensional geometry data for the particular area using the identified one or more features, wherein the geometry data includes a plurality of points and vectors defining the associated locations and shapes of the various objects within the particular area;
filtering the three-dimensional geometry data to remove points and vectors of the three-dimensional geometry data that define at least one object of the various objects based on a characteristic identifying a first type of user in order to generate a subset of the three-dimensional geometry data for the particular area and for the first type user;
storing the subset of three-dimensional geometry data for the particular area for the first type of user;
receiving, from a client computing device associated with a first user, user input identifying a type of the first user;
when the client computing device enters the particular area, receiving from the client computing device, a request for information for determining the location of the client device;
determining, the type of the first user as the first type of user;
retrieving, the stored subset of three-dimensional geometry data for the particular area and for the first type of user based on the dete

Assignees

• Google Inc

Inventors

• Mcclendon Brian

Classifications

• G06K9/00664

  Physics · mapped topic

• G06F17/30247

  Physics · mapped topic

• H04W4/043 Primary

  Electricity · mapped topic

• G06F17/30241

  Physics · mapped topic

• G06V20/10 Primary

  Terrestrial scenes (scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59) · CPC title