Multi-modal video target acquisition and re-direction system and method

• US 7,028,269 B1
• Filed: 01/20/2000
• Issued: 04/11/2006
• Est. Priority Date: 01/20/2000
• Status: Expired due to Term

• Current Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Lee, Mi-Suen, Cohen-Solal, Eric
• Primary Examiner(s): Hailu, Tadesse
• Application Number:
  US09/488,028
• Time in Patent Office: 2,273 Days
• Field of Search: 345/862, 345/863, 345/727, 345/716, 382/103, 382/255, 382/286, 382/293, 382/311, 382/312, 348/169, 715/862, 715/863, 715/727, 715/716
• US Class Current: 715/863
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: H04N 23/66 Remote control of cameras or camera parts, e.g. by remote control devices

Abstract

The present invention relates generally to the field of video-camera systems, such as a video conferencing systems, and more particularly to video camera targeting systems that locate and acquire targets using an input characterizing a target and a machine-classification system to assist in target acquisition responsively to that input. In some embodiments, the characterization and classification are employed together with one or more inputs of other modalities such as gesture-control. In one example of the system in operation, an operator is able to make pointing gestures toward an object and, simultaneously speak a sentence identifying the object to which the speaker is pointing. At least one term of the sentence, presumably, is associated with a machine-sensible characteristic by which the object can be identified. The system captures and processes the voice and gesture inputs and re-positions a PTZ video camera to focus on the object that best matches both the characteristics and the gesture. Thus, the PTZ camera is aimed based upon the inputs the system receives and the system'"'"'s ability to locate the target by its sensors.

Claims

1. A method of locating and displaying an image of a target, the method comprising the steps of:

sensing a triggering event generated by a human operator;

receiving additional external information that characterizes at least one machine-sensible feature of a target, said receiving step occurring substantially simultaneously with said sensing step; and

aiming a camera in response to said sensing and said receiving step, wherein said sensing step includes sensing a gesture indicating a direction of said target.

2. The method of claim 1, wherein said sensing step includes sensing a gesture of a human operator indicating a target.

3. The method of claim 1, wherein said receiving step includes receiving speech from said human operator.

4. The method of claim 3, further including processing said speech for use with at least one machine sensor, said at least one machine sensor and said speech assisting in locating said target.

5. The method of claim 4, wherein said sensing step includes sensing a gesture indicting a direction from said human operator to said target.

6. The method of claim 4, wherein said processing step includes processing said voice information through a look-up table corresponding said speech to search criteria for use with said at least one sensor.

7. The method of claim 6, wherein said look-up table is modifiable.

8. The method of claim 7, wherein said look-up table is modified by receiving information through the on-line global computer network.

9. The method of claim 7, wherein said look-up table is modified to include an additional voice input and a corresponding search criteria, said added voice input and said corresponding search criteria established by comparing previous association of said added voice input with at least one machine sensible characteristic of at least one correctly identified target associated with said voice input, said machine sensible characteristic being a basis for determining said corresponding search criteria.

10. A method of locating and displaying an image of a target, the method comprising the steps of:

scanning an area within the range of at least one sensor;

identifying potential targets;

storing information concerning machine sensible characteristics and locations of said possible targets;

sensing a triggering event, said triggering event generated by a human operator;

receiving additional external information that characterizes at least one feature of said target, said receiving step occurring substantially simultaneously with said sensing step; and

aiming a camera in response to said sensing, storing and said receiving steps, wherein said sensing step includes sensing a gesture indicating a direction of said target.

11. A method of aiming a camera at a target, comprising the steps of:

inputting an indication of a position of a target;

inputting further information about a machine-sensible characteristic of said target;

aiming a camera at said target in response to said indication and said further information to reduce an error in said aiming, wherein said inputting an indication step includes inputting a gesture indicating a direction of said target.

12. A method of acquiring a target, comprising the steps of:

inputting spatial information to indicate a position of a target;

inputting further information about said target; and

orienting an instrument with respect to said target to acquire said target in response to said spatial information and said further information to reduce an ambiguity in said position, wherein said spatial information includes sensing a gesture indicating a direction of said target.

13. A method as in claim 12, wherein said step of orienting includes orienting a camera.