Multi-sensing devices cooperative recognition system

• US 7,340,078 B2
• Filed: 06/28/2004
• Issued: 03/04/2008
• Est. Priority Date: 10/08/2003
• Status: Expired due to Fees

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Shikano, Hiroaki, Irie, Naohiko
• Primary Examiner(s): Ahmed; Samir
• Assistant Examiner(s): BHATNAGAR, ANAND P
• Application Number:
  US10/876,596
• Publication Number:
  US 20050078854A1
• Time in Patent Office: 1,345 Days
• Field of Search: 382/100, 382/103, 382/107, 348/143, 348/154, 348/155, 348/169, 348170-172, 342/20, 342 52- 59
• US Class Current: 382/103
• CPC Class Codes: G06V 20/10 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

Abstract

Disclosed here is an information processing system capable of recognizing actions and circumstances of a user with respect to both space and time as a “situation” to recognize the user'"'"'s request using a plurality of sensing nodes that work cooperatively with each another, thereby responding autonomously to the user'"'"'s request according to the recognition results. The plurality of sensing nodes and a responding device are disposed in a target space to build up a network for recognizing the situation in the target space. And, a plurality of recognition means are used to recognize the situation with respect to both space and time related to the existence of the user. And, an integral processing portion (master) is selected from among the plurality of sensing nodes, thereby dispersing the system load. If there are a plurality of users, the system can make recognition in accordance with the request of each of those users.

Claims

1. An information processing system comprising:

a plurality of sensing nodes each of which has a position detection module;

a first master sensing node which is selected from said plurality of sensing nodes, which builds up a first network with sensing nodes each of which exists in an peripheral area of said first master sensing node, and which includes;

a position determination unit which determines a position of a moving object in a predetermined space based on position information of said moving object detected by sensing nodes in said first network;

a situation determination unit which recognizes a situation change in said predetermined space based on said position of said moving object; and

a master determination unit which selects a subsequently-operating master sensing node from the plurality of sensing nodes to build up a second network with peripheral sensing nodes among said plurality of sensing nodes in accordance with said situation change.

2. The system according to claim 1, wherein said second master sensing node is closest to said moving object among said plurality of sensing nodes.

3. The system according to claim 1, wherein each of said plurality of sensing nodes further has a face detection module and a gesture detection module, and

said first master sensing node instructs said plurality of sensing nodes to activate at least one detection module and to stop any other unnecessary detection modules in accordance with said situation change.

4. The system according to claim 1, wherein said first master sensing node recognizes said moving object moving out of said predetermined space and passes control to another system existing in a space into which said moving object is moving.

5. The system according to claim 1, wherein each of said sensing nodes built up said first network detects a difference between frames positioned before and after a moving image photographed by the position detection module and detects angle information of said moving object, and said position determination unit determines said position of said moving object by three-point position measurement principles using said angle information.

6. The system according to claim 1, wherein each of said sensing nodes in said first network recognizes a gesture pattern of said moving object and sends said gesture pattern to said first master sensing node, and said first master sensing node recognizes a gesture type according to said gesture pattern and recognizes said situation change with respect to a time axis.

7. The system according to claim 1, further comprising a responding device, wherein said first master sensing node sends an action command to instruct said responding device to take a predetermined action in accordance with said situation change, and said responding device takes an action in accordance with said received comment.

8. The system according to claim 1, wherein when recognizing a plurality of moving objects in said predetermined space, said first master sensing node selects at least one simultaneously-operating master sensing node from the plurality of sensing nodes each of which builds up another network with peripheral sensing nodes from said plurality of sensing nodes.

9. An information processing method implemented by an information processing system including a plurality of sensing nodes each of which has a position detection module, a first master sensing node being selected from said plurality of sensing nodes and building up a first network with sensing nodes each of which exists in a peripheral area of said first master sensing node, the method comprising:

detecting position information of a moving object in a predetermined space by said sensing nodes in said first network;

sending, by said sensing nodes in said first network, said detected position information to said first master sensing node;

determining, by said first master sensing node, a position of said moving object based on said position information;

recognizing, by said first master sensing node, a situation change in said predetermined space based on said determined position of said moving object;

selecting, by said first master sensing node, a subsequently-operating master sensing node from the plurality of sensing nodes in accordance with said situation change; and

building up, by said second master sensing node, a second network with peripheral sensing node among said plurality of sensing nodes.

10. The method according to claim 9, wherein said second master sensing node is closest to said moving object among said plurality of sensing nodes.

11. The method according to claim 9, wherein each of said plurality of sensing nodes further has a face detection module and a gesture detection module, and the method further comprising:

instructing, by said first master sensing node, said plurality of sensing nodes to activate at least one detection module and to stop any other unnecessary detection modules in accordance with said situation change.

12. The method according to claim 9, further comprising:

recognizing said moving object that is going out of said predetermined space; and

object is moving by said first master sensing node.

13. The method according to claim 9, wherein said position information is angle information of said moving object detected based on a difference between frames positioned before and after a moving image photographed by a camera, and said position of said moving object is determined by three-point position measurement principles using said angle information.

14. The method according to claim 9, further comprising:

recognizing a gesture pattern of said moving object by each of sensing nodes in said first network;

sending said gesture pattern to said first master sensing node; and

recognizing, by said first master sensing node, a gesture type according to said gesture pattern and recognizing said situation change with respect to a time axis.

15. The method according to claim 9, further comprising:

sending, by said first master sensing node, an action command to instruct a responding device to take a predetermined action in accordance with said situation change; and

taking an action, by said responding device, in accordance with said received command.

16. The method according to claim 9, further comprising:

when recognizing a plurality of moving objects in said predetermined space, selecting, by said first master sensing node, at least one simultaneously-operating master sensing node from the plurality of sensing nodes each of which builds up another network with peripheral sensing nodes from said plurality of sensing nodes.