Systems and methods for generating virtual contexts

Patent metadata

Field	Value
Publication number	US-9984409-B2
Application number	US-201414580072-A
Country	US
Kind code	B2
Filing date	Dec 22, 2014
Priority date	Dec 22, 2014
Publication date	May 29, 2018
Grant date	May 29, 2018

Abstract

Techniques for generated and presenting images of items within user selected context images are presented herein. In an example embodiment, an access module can be configured to receive a first environment image. A simulation module coupled to the access module may process the environment image to identify placement areas within the image, and an imaging module may merge an item image with the environment image and filter the merged image in an erosion area. In various embodiments, the items and environments may be selected by a user and presented to a user in real-time or near-real time as part of an online shopping experience. In further embodiments, the environments may be processed from images taken by a device of the user.

First claim

What is claimed is:

1. A system comprising:
an access module implemented by at least one processor and configured to:
access a set of context data, the set of context data comprising a first environment image depicting a first environment;
a simulation module implemented by the at least on processor, the simulation module in communication with the access module and configured to:
segment the first environment image of the environment into a first plurality of segments;
identify a first ground segment from the first plurality of segments;
identify a plurality of unobstructed portions of the first ground segment;
for each of the plurality of unobstructed portions of the first ground segment, determine an unobstructed distance from the unobstructed portion toward a ceiling segment;
identify a plurality of placement areas comprising at least a first placement area within the first environment image based on the first ground segment and a first set of placement cues associated with the first plurality of segments; and
select the first placement area from a plurality of placement areas based at least in part on a proximity of the first placement area to a set of obstruction segments and a set of relevant context segments of the plurality of segments; and
an imaging module implemented by the at least one processor and configured to:
superimpose a wearable item image on the first environment image to generate a first item context base image, wherein the wearable item image is placed within the first placement area by scaling an item size of the wearable item image to match a placement size of the first placement area and to match an item scale to an environment scale and by downsampling the wearable item image to match a wearable item image pixel resolution to a first environment image resolution, and wherein the wearable item image comprises a simulated image of a wearable item modeled with zero-length springs;
identify a first erosion area in the first item context base image, the first erosion area comprising at least a portion of a boundary between the first environment image and the wearable item image; and
perform an image filtering process on the erosion area to generate a first context image comprising at least a portion of the wearable item image and a portion of the first environment image.

2. The system of claim 1 further comprising:
a mobile device comprising at least one processor and a memory coupled to the at least one processor, wherein the mobile device further comprises the access module, the simulation module, and the imaging module.

3. The system of claim 2 wherein the mobile device further comprises a camera module coupled to the access module, wherein the camera module is configured to capture the first environment image.

4. The system of claim 3 further comprising a display module coupled to the imaging module, wherein the display module is configured to output first context image on a display of the mobile device.

5. The system of claim 4 wherein the mobile device further comprises a user interface module configured to:
receive a first user input selecting the wearable item from a virtual marketplace interface of the user interface module; and
receive a second user input selecting a second wearable item from the virtual marketplace interface of the user interface module.

6. The system of claim 5 wherein the mobile device further comprises an antenna coupled to the access module and the at least one processor;
wherein the access module is further configured to:
receive the wearable item image from a network via the antenna; and
receive a second wearable item image from the network via the antenna, wherein the second wearable item image represents the second wearable item, and wherein the second wearable item is different than the wearable item.

7. The system of claim 6 wherein the imaging module is further configured to:
superimpose the second wearable item image on the first environment image to generate a second item context base image, wherein the second wearable item image is placed within the first placement area;
identify a second erosion area in the second item context base image, the second erosion area comprising at least a portion of a boundary between the first environment image and the second wearable item image; and
perform the image filtering process on the second erosion area to generate a second context image comprising at least a portion of the second wearable item image and a second portion of the first environment image.

8. The system of claim 1 further comprising:
a first computing device comprising imaging module and a display module that outputs the first context image to a display of the first computing device;
a server computer communicatively coupled to the first computing device via a network, the server computer comprising the access module and the simulation module; and
a database comprising the set of context data, wherein the access module receives the set of context data from the database.

9. The system of claim 8 wherein the set of context data further comprises a second environment image depicting a second environment different than the first environment;
wherein the simulation module is further configured to:
segment the second environment image into a second plurality of segments;
identify a second ground segment from the second plurality of segments; and
determine at least a second placement area within the second environment image based on the second ground segment and a second set of placement cues associated with the second plurality of segments.

10. The system of claim 9 wherein the first computing device further comprises a user interface module configured to:
receive a first user input selecting the first environment image, wherein the first context image is generated and displayed on the display in response to the first user input; and
receive a second user input, following display of the first context image, selecting the second environment image, wherein in response to the second user input the imaging module is configured to:
superimpose the second wearable item image on the first environment image to generate a second item context base image, wherein the wearable item image is placed within the second placement area;
identify a second erosion area in the second item context base image, the second erosion area comprising at least a portion of a boundary between the second environment image and the wearable item image;
perform the image filtering process on the second erosion area to generate a second context image comprising at least a second portion of the wearable item image and a portion of the second environment image; and
communicate the second context image to the display module to replace the first context image on the display.

11. A method comprising:
accessing, at an access module of a device comprising at least one processor and a memory coupled to the at least one processor, a set of context data, the set of context data comprising a first environment image depicting a first environment;
segmenting, by a simulation module communicatively coupled to the access module, the first environment image of the environment into a first plurality of segments;
identifying a first ground segment from the first plurality of segments;
determining at least a first placement area within the first environment image based on the ground segment and a first set of placement cues associated with the first plurality of segments;
superimposing, by an imaging module, a wearable item image on the first environment image to generate a first item context base image, wherein the wearable item

Assignees

• Ebay Inc

Inventors

• Naware Mihir
• Chhugani Jatin
• Su Jonathan

Classifications

• G06T2210/16

  Cloth · CPC title

• G06F3/04842

  Selection of displayed objects or displayed text elements (G06F3/0482 takes precedence) · CPC title

• G06Q30/0643 Primary

  graphically representing goods, e.g. 3D product representation · CPC title