Image based motion gesture recognition method and system thereof

• US 8,373,654 B2
• Filed: 04/29/2010
• Issued: 02/12/2013
• Est. Priority Date: 04/29/2010
• Status: Active Grant

• Current Assignee: Acer, Inc.
• Original Assignee: Acer, Inc.
• Inventors: Wang, Jing-Wei, Lou, Chung-Cheng
• Primary Examiner(s): PHAM, VIET DAVID
• Application Number:
  US12/770,698
• Publication Number:
  US 20110267258A1
• Time in Patent Office: 1,020 Days
• Field of Search: 345/156, 382/103
• US Class Current: 345/156
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 10/242 by image rotation, e.g. by 90 degrees
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113

Abstract

An image based motion gesture recognition method and system thereof are disclosed. In embodiment, a hand posture detection is performed according to the received image frames, to obtain a first hand posture. It is then determined whether the first hand posture matches a predefined starting posture or not. If the first hand posture matches said predefined starting posture, movement tracking is performed according to hand locations on image frames, to obtain a motion gesture. During said movement tracking, the hand posture detection is performed according to said image frames to obtain a second hand posture, and it is determined whether the second hand posture matches a predefined ending posture. If the second hand posture matches the predefined ending posture, the movement tracking is stopped. Therefore, reduce complexity motion gesture recognition can be reduced and the reliability in interaction can be improved.

Claims

1. An image based motion gesture recognition method, comprising steps of:

receiving image frames;

performing a hand posture detection according to said image frames, to obtain a first hand posture;

determining whether said first hand posture matches a predefined starting posture;

if said first hand posture matches said predefined starting posture, performing a movement tracking according to hand locations on said image frames, to obtain a motion gesture;

performing said hand posture detection according to said image frames during said movement tracking, to obtain a second hand posture;

determining whether said second hand posture matches a predefined ending posture; and

if said second hand posture matches said predefined ending posture, stopping said movement tracking;

wherein the step of performing said hand posture detection further comprises;

detecting whether a hand image exists in at least one of said image frames;

obtaining a contoured hand image according to said hand image if said hand image exists in at least one of said image frames;

determining a hand direction and a finger number according to said contoured hand image, wherein the step of determining said finger number further comprises steps of;

performing a palm orientation calculation to obtain a gravity center of said contoured hand image;

performing a palm cut on said contoured hand image according to said gravity center, to obtain a cut hand image; and

determining said finger number according to said cut hand image;

recognizing said first hand posture or said second hand posture according to said hand direction and said finger number.

2. The image based motion gesture recognition method according to claim 1, further comprising a step of:

continuing said movement tracking if said second hand posture does not match said predefined ending posture.

3. The image based motion gesture recognition method according to claim 1, wherein the step of performing said movement tracking further comprises:

obtaining image blocks containing said hand image in each of said image frames; and

estimating motion vectors of said image blocks in said image frames.

4. The image based motion gesture recognition method according to claim 3, further comprising steps of:

recording said motion vector to obtain a trace; and

recognizing said trace to obtain said motion gesture.

5. The image based motion gesture recognition method according to claim 1, wherein the step of determining said hand direction further comprises a step of:

determining said hand direction according to an edge of said image frame with which said contoured hand image contacts.

6. An image based motion gesture recognition system, comprising:

a storage unit storing a predefined starting posture and a predefined ending posture;

an image capture unit capable of capturing image frames;

a first processing unit capable of performing a hand posture detection according to said image frames, to obtain a first hand posture, wherein said first processing unit further comprises;

a first image processing unit, capable of detecting a hand image existing in at least one of said image frames;

a second image processing unit, capable of obtaining a contoured hand image according to said hand image; and

a hand posture recognition unit, capable of determining a hand direction and a finger number according to said contoured hand image, and recognizing said first hand posture or said second hand posture according to said hand direction and said finger number, wherein said hand posture recognition unit further performs a palm orientation calculation to obtain a gravity center of said contoured hand image, and performs a palm cut on said contoured hand image according to said gravity center, to obtain a cut hand image, and determines said finger number according to said cut hand image;

a comparing unit capable of determining whether said first hand posture matches said predefined starting posture; and

a second processing unit capable of performing a movement tracking according to hand locations on said image frames to obtain a motion gesture, if said first hand posture matches said predefined starting posture;

wherein, said first processing unit performs said hand posture detection according to said image frames during said movement tracking, to obtain a second hand posture, and said second processing unit stops said movement tracking if said comparing unit determines that said second hand posture matches a predefined ending posture.

7. The image based motion gesture recognition system according to claim 6, wherein said second processing unit continues said movement tracking if said comparing unit determines that said second hand posture does not match said predefined ending posture.

8. The image based motion gesture recognition system according to claim 6, wherein said second processing unit further comprises:

a block detection unit, capable of obtaining image blocks containing said hand image in each of said image frames; and

a motion vector unit, capable of estimating motion vectors of image blocks in said image frames.

9. The image based motion gesture recognition system according to claim 8, wherein said second processing unit further comprises:

a trace recognition unit, capable of recording said motion vector to obtain a trace, and recognizing said trace to obtain said motion gesture.

10. The image based motion gesture recognition system according to claim 6, wherein said hand posture recognition unit determines said hand direction according to an edge of said image frame with which said contoured hand image contacts.