Gesture-based control system
A method and system for human computer interaction using hand gestures is presented. The system permits a person to precisely control a computer system without wearing an instrumented glove or any other tracking device. In one embodiment, two cameras observe and record images of a user's hands. The hand images are processed by querying a database relating hand image features to the 3D configuration of the hands and fingers (i.e. the 3D hand poses). The 3D hand poses are interpreted as gestures. Each gesture can be interpreted as a command by the computer system. Uses for such a system include, but are not limited to, computer aided design for architecture, mechanical engineering and scientific visualization. Computer-generated 3D virtual objects can be efficiently explored, modeled and assembled using direct 3D manipulation by the user's hands.
1. A method comprising:
receiving image information about a hand from one or more imaging devices;
identifying the hand against a background from the received image information;
identifying, based on a geodesic image distance, a pose of the hand in the received image information by:
calculating the geodesic image distance between a plurality of extrema of the hand, wherein each extrema comprises a finger of the hand; and
determining a pose of the hand based on the geodesic image distance and the received image information;
recognizing that the identified pose of the hand is associated with one or more hand gestures of a plurality of hand gestures; and
generating a control command based on the recognized one or more hand gestures.
2. The method of claim 1 , wherein identifying a pose of the hand comprises identifying contact between two or more fingers of the hand.
3. The method of claim 2 , wherein the two or more fingers are identified based on extrema of the received image information about the hand.
4. The method of claim 1 , wherein determining a pose of the hand based on the geodesic image distance and the received image information comprises comparing the geodesic image distance between extrema of the hand with the Euclidian distance between extrema of the hand.
5. The method of claim 1 , wherein identifying a pose of the hand further comprises:
identifying a plurality of potential poses of the hand based on the received image information; and
blending the plurality of potential poses of the hand to form an estimated pose of the hand.
6. The method of claim 5 , further comprising determining, based on the calculated geodesic image distance, if the estimated pose of the hand represents a “pinching” gesture featuring contact between two or more fingers of the hand.
7. A non-transitory computer-readable storage medium comprising instructions which, when executed by a processor, cause the processor to perform the steps of:
receiving image information about a hand from one or more imaging devices;
identifying the hand against a background from the received image information;
identifying, based on a geodesic image distance, a pose of the hand in the received image information by:
calculating the geodesic image distance between a plurality of extrema of the hand, wherein each extrema comprises a finger of the hand; and
determining a pose of the hand based on the geodesic image distance and the received image information;
recognizing that the identified pose of the hand is associated with one or more hand gestures of a plurality of hand gestures; and
generating a control command based on the recognized one or more hand gestures.
8. The non-transitory computer-readable storage medium of claim 7 , wherein identifying a pose of the hand comprises identifying contact between two or more fingers of the hand.
9. The non-transitory computer-readable storage medium of claim 8 , wherein the two or more fingers are identified based on extrema of the received image information about the hand.
10. The non-transitory computer-readable storage medium of claim 7 , wherein determining a pose of the hand based on the geodesic image distance and the received image information comprises comparing the geodesic image distance between extrema of the hand with the Euclidian distance between extrema of the hand.
11. The non-transitory computer-readable storage medium of claim 7 , wherein identifying a pose of the hand further comprises:
identifying a plurality of potential poses of the hand based on the received image information; and
blending the plurality of potential poses of the hand to form an estimated pose of the hand.
12. The non-transitory computer-readable storage medium of claim 11 , further comprising determining, based on the calculated geodesic image distance, if the estimated pose of the hand represents a “pinching” gesture featuring contact between two or more fingers of the hand.
13. A system comprising:
a communication interface configured to receive image information about a hand from one or more imaging devices;
a processor for executing instructions stored in memory, wherein the execution of the instructions by the processor performs the steps of:
identifying the hand against a background from the received image information;
identifying, based on a geodesic image distance, a pose of the hand in the received image information by:
calculating the geodesic image distance between a plurality of extrema of the hand, wherein each extrema comprises a finger of the hand; and
determining a pose of the hand based on the geodesic image distance and the received image information;
recognizing that the identified pose of the hand is associated with one or more hand gestures of a plurality of hand gestures; and
generating a control command based on the recognized one or more hand gestures.
14. The system of claim 13 , wherein identifying a pose of the hand comprises identifying contact between two or more fingers of the hand.
15. The system of claim 14 , wherein the two or more fingers are identified based on extrema of the received image information about the hand.
16. The system of claim 13 , wherein determining a pose of the hand based on the geodesic image distance and the received image information comprises comparing the geodesic image distance between extrema of the hand with the Euclidian distance between extrema of the hand.
17. The system of claim 13 , wherein identifying a pose of the hand further comprises:
identifying a plurality of potential poses of the hand based on the received image information; and
blending the plurality of potential poses of the hand to form an estimated pose of the hand.