Identification of dynamic objects based on depth data

Patent metadata

Field	Value
Publication number	US-9230366-B1
Application number	US-201314136647-A
Country	US
Kind code	B1
Filing date	Dec 20, 2013
Priority date	Dec 20, 2013
Publication date	Jan 5, 2016
Grant date	Jan 5, 2016

Abstract

A system and method is provided that identifies dynamic objects within a set of photographic images. The objects may be identified as dynamic based on depth data associated with the images. The depth data may also be used to determine the potential states of the dynamic objects within the set of images. A three-dimensional model be created in which the dynamic objects are displayed in accordance with one of the potential states.

First claim

The invention claimed is:

1. A method for identifying dynamic objects, the method comprising:
accessing, by one or more computing devices, a plurality of images, each having therewith associated depth data;
determining, by the one or more computing devices, based at least in part on the depth data for each image in the plurality of images, that a first object, visible within at least one of the plurality of images, is dynamic;
identifying, by the one or more computing devices and based on the depth data, a set of potential states of the first object;
selecting, by the one or more computing devices, a state, from the set of potential states, in which the first object is to be displayed; and
providing, by the one or more computing devices, a user with directions in connection with navigating a pathway within a map, wherein the directions provided to the user are based at least in part on the selected state of the first object.

2. The method of claim 1 , further comprising:
generating, by the one or more computing devices, a model of objects shown in the plurality of images, including the first object;
receiving a request of a user to view the model; and
providing a rendering of the model for display to the user.

3. The method of claim 2 , wherein the rendering of the model displays the objects relative to a first point in time, and wherein the selected state of the first object is based on the first point in time.

4. The method of claim 1 , wherein chronological data is associated with the plurality of images, and wherein selecting the state in which the first object is to be displayed is based at least in part on the chronological data.

5. The method of claim 1 , further comprising:
determining, by the one or more computing devices, based on the depth data, that a second object within at least one of the plurality of images is dynamic;
identifying, by the one or more computing devices and based on the depth data, a set of potential states of the second object;
determining, by the one or more computing devices, that a relationship exists between the set of potential states of the first object and the set of potential states of the second object; and
selecting, by the one or more computing devices, a state in which the second object is to be displayed within the model based on the determined relationship between the set of potential states of the first object and the set of potential states of the second object.

6. The method of claim 1 , further comprising:
displaying, by the one or more computing devices, the first object in the selected state;
receiving, by the one or more computing devices, device input from a user in connection with the displaying of the first object; and
in response to the device received input, altering the displaying of the first object from a first state to a second state in the identified set of potential states of the first object.

7. A system comprising one or more processors configured:
access a plurality of images, each having therewith associated depth data;
determine, based at least in part on the depth data for each image in the plurality of images, that a first object, within at least one of the plurality of images, is dynamic;
identify a set of potential states of the first object; and
select a state, from the set of potential states, in which the first object is to be displayed; and
provide a user with directions in connection with navigating a pathway within a map, wherein the directions provided to the user are based at least in part on the selected state of the first object.

8. The system of claim 7 , wherein the one or more processors are further configured to:
generate a model of objects shown in the plurality of images, including the first object;
receive a request of a user to view the model; and
provide a rendering of the model for display to the user.

9. The system of claim 8 , wherein the rendering of the model displays the objects relative to a first point in time, and wherein the selected state of the first object is based on the first point in time.

10. The system of claim 7 , wherein chronological data is associated with the plurality of images, and wherein selecting the state in which the first object is to be displayed is based at least in part on the chronological data.

11. The system of claim 7 , wherein the one or more processors are further configured to:
determine that a second object within at least one of the plurality of images is dynamic;
identify a set of potential states of the second object;
determine that a relationship exists between the set of potential states of the first object and the set of potential states of the second object; and
select a state in which the second object is to be displayed within the model based on the determined relationship between the set of potential states of the first object and the set of potential states of the second object.

12. The system of claim 7 , wherein the one or more processors are further configured to:
display the first object in the selected state;
receive device input from a user in connection with the display of the first object; and
in response to the device input, alter the display of the first object from a first state to a second state in the identified set of potential states of the first object.

13. A method for identifying dynamic objects, the method comprising:
accessing, by one or more computing devices, a plurality of images, each having therewith associated depth data;
determining, by the one or more computing devices, based at least in part on the depth data for each image in the plurality of images, that a first object, visible within at least one of the plurality of images, is dynamic;
identifying, by the one or more computing devices and based on the depth data, a set of potential states of the first object;
selecting, by the one or more computing devices, a state, from the set of potential states, in which the first object is to be displayed;
providing, by the one or more computing devices, a user with directions in connection with navigating a pathway within a map, wherein the directions provided to the user are based at least in part on the selected state of the first object
determining, by the one or more computing devices, based on the depth data, that a second object within at least one of the plurality of images is dynamic;
identifying, by the one or more computing devices and based on the depth data, a set of potential states of the second object;
determining, by the one or more computing devices, that a relationship exists between the set of potential states of the first object and the set of potential states of the second object; and
selecting, by the one or more computing devices, a state in which the second object is to be displayed within the model based on the determined relationship between the set of potential states of the first object and the set of potential states of the second object.

14. The method of claim 13 , further comprising:
generating, by the one or more computing devices, a model of objects shown in the plurality of images, including the first object;
receiving a request of a user to view the model; and
providing a rendering of the model for display to the user.

15. The method of claim 14 , wherein the rendering of the model displays the objects relative to a first point in time, and wherein the selected state of the first object is based on the first point in time.

16. The method of claim 13 , wherein chronological data is associated with the plurality of images, and wherein sele

Assignees

• Google Inc

Inventors

• Mcclendon Brian
• Jones Jonah

Classifications

• G06T7/2086

  Physics · mapped topic

• G06T17/05 Primary

  Geographic models · CPC title

• G01C21/206

  specially adapted for indoor navigation · CPC title

• G06T7/251

  involving models · CPC title

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title