Method and system for cooperative diversity visual cognition in wireless video sensor networks

Patent metadata

Field	Value
Publication number	US-9398268-B2
Application number	US-201213480064-A
Country	US
Kind code	B2
Filing date	May 24, 2012
Priority date	May 25, 2011
Publication date	Jul 19, 2016
Grant date	Jul 19, 2016

Abstract

A method and system for cooperative diversity visual cognition in a wireless sensor network is disclosed. The method and system are capable of solving distributed visual cognition tasks (for example, online simultaneous reconstruction of 3D models of a large area) by using multiple video streams and exploiting cooperative diversity video sensing information while ensuring an optimal tradeoff between energy consumption and video quality of images received from said multiple video streams.

First claim

The invention claimed is:

1. A method for cooperative diversity visual cognition in a wireless sensor network comprising:
receiving, by at least one video sensor node deployed in an area, a request for a video image of the area for a visual cognition task;
determining, by the at least one video sensor node, an estimate of a performance metric of the at least one video sensor node for the visual cognition task based on a contribution of the at least one video sensor node to a value of a communicative coalition of video sensor nodes associated with the visual cognition task;
determining, by the at least one video sensor node, whether to join the communicative coalition of video sensor nodes associated with the visual cognition task based on the determined estimate of the performance metric of the at least one video sensor node; and
in response to a determination to join the communicative coalition by the at least one video sensor node, obtaining and transmitting to a requestor the video image of the area,
wherein the step of determining, by the at least one video sensor node, whether to join the communicative coalition of video sensor nodes associated with the visual cognition task comprises:
declining, by the at least one video sensor node, to join the communicative coalition in response to determining that the contribution of the at least one video sensor node to the value of the communicative coalition associated with the visual cognition task does not increase a total performance metric of the communicative coalition associated with the visual cognition task.

2. The method of claim 1 , wherein declining to join the communicative coalition comprises declining to obtain and transmit the data to the requestor.

3. The method of claim 1 , wherein the step of determining the estimate of the performance metric, by the at least one video sensor node, comprises:
determining at least one metric, the at least one metric being an optimal tradeoff between a detriment and a benefit associated with the at least one video sensor node in the contribution to the value of the communicative coalition associated with the visual cognition task.

4. The method of claim 3 , wherein the at least one metric is the Shapley value.

5. The method of claim 1 , wherein determining the estimate of the performance metric comprises executing a merge-split algorithm for determining a coalitional structure.

6. The method of claim 1 , wherein the step of determining, by the at least one video sensor node, whether to join the communicative coalition comprises:
determining to join the communicative coalition when the estimate of the performance metric indicates that the at least one video sensor node increases a total performance metric of the communicative coalition associated with the visual cognition task.

7. The method of claim 6 , wherein the total performance metric of the communicative coalition associated with the visual cognition task is equal to an estimate of an aggregated performance metric of a plurality of video sensor nodes within the communicative coalition.

8. The method of claim 1 , further comprising:
if the at least one video sensor node determines to join the communicative coalition, exchanging data, by the at least one video sensor node, with the at least one other video sensor node in the area.

9. The method of claim 8 , wherein exchanging the data with the at least one other video sensor node in the area comprises exchanging sensory metadata.

10. The method of claim 9 , wherein the request is associated with a plurality of characteristics, and the plurality of characteristics associated with the request comprises:
the performance metric associated with the visual cognition task, a metric of energy consumption, and delay in transmitting the video image to the requestor.

11. The method of claim 6 , further comprising:
subsequent to the joining the communicative coalition, disjoining, by the at least one video sensor node, the communicative coalition in response to determining that the performance metric of the at least one video sensor node no longer increases the total performance metric of the communicative coalition associated with the visual cognition task.

12. A video sensor node for cooperative diversity visual cognition in a wireless sensor network, the video sensor node comprising:
a processor; and
a memory storing computer program instructions, which when executed by the processor cause the processor to perform operations comprising:
receiving a request for a video image of an area in which the video sensor node is deployed for a visual cognition task;
determining an estimate of a performance metric of the video sensor node for the visual cognition task based on a contribution of the video sensor node to a value of a communicative coalition of video sensor nodes associated with the visual cognition task;
determining whether to join the communicative coalition of video sensor nodes associated with the visual cognition task based on the determined estimate of the performance metric of the video sensor node; and
obtaining and transmitting to a requestor the video image of the area in response to a determination to join the communicative coalition,
wherein determining whether to join the communicative coalition of video sensor nodes associated with the visual cognition task comprises:
declining to join the communicative coalition in response to determining that the contribution of the at least one video sensor node to the value of the communicative coalition associated with the visual cognition task does not increase a total performance metric of the communicative coalition associated with the visual cognition task.

13. The video sensor node of claim 12 , wherein the operations further comprise:
exchanging data with at least one other video sensor node in the area in response to joining the communicative coalition.

14. The video sensor node of claim 12 , wherein the operations further comprise:
subsequent to the joining the communicative coalition, disjoining the communicative coalition in response to determining that the performance metric of the video sensor node no longer maximizes a total performance metric of the communicative coalition associated with the visual cognition task.

15. A non-transitory computer readable medium storing computer program instructions for cooperative diversity visual cognition in a wireless sensor network, the computer program instructions, when executed, cause a processor to perform a method comprising:
receiving, by at least one video sensor node deployed in an area, a request for a video image of the area for a visual cognition task;
determining, by the at least one video sensor node, an estimate of a performance metric of the at least one video sensor node for the visual cognition task based on a contribution of the at least one video sensor node to a value of a communicative coalition of video sensor nodes associated with the visual cognition task;
determining, by the at least one video sensor node, whether to join the communicative coalition of video sensor nodes associated with the visual cognition task based on the determined estimate of the performance metric of the at least one video sensor node; and
in response to a determination to join the communicative coalition by the at least one video sensor node, obtaining and transmitting to a requestor the video image of the area,
wherein the step of determining, by the at least one video sensor node, whether to join the communicative coalition of video sensor nodes associated with the visual cognition task comprises

Assignees

• Singh Maneesh Kumar
• Comaniciu Cristina
• Comaniciu Dorin
• Kluckner Stefan
• Siemens Corp
• Siemens Ag Oesterreich
• Stevens Inst Technology

Inventors

• Singh Maneesh Kumar
• Comaniciu Cristina
• Comaniciu Dorin
• Kluckner Stefan

Classifications

• H04N7/181 Primary

  for receiving images from a plurality of remote sources · CPC title