Gesture recognition systems

1. A method for performing gesture recognition, the method comprising performing by a computer processor:

receiving one or more raw frames from one or more cameras, each of the one or more raw frames representing a time sequence of images;

segmenting the one or more raw frames to obtain segments by:

determining one or more highly textured regions of the one or more raw frames;

segmenting the one or more highly textured regions in accordance with textured features thereof to determine one or more segments thereof;

determining one or more non-highly textured regions of the one or more raw frames; and

segmenting the one or more non-highly textured regions in accordance with color thereof to determine one or more segments thereof;

after segmenting the one or more raw frames, determining a depth map in accordance with the segments; and

tracking one or more of the segments through the one or more raw frames in accordance with the depth map representing the time sequence of images.

2. The method of claim 1 , wherein the segmenting further comprises:

before determining the one or more highly textured regions of the one or more raw frames, performing by the computer processor an initial motion-based segmentation of the one or more raw frames.

3. The method of claim 1 , wherein the segmenting further comprises:

determining, by the computer processor, position changes of one or more portions between the raw frames indicating motion of a portion thereof; and

segmenting the raw frames in accordance with these determined position changes.

4. The method of claim 1 , wherein raw images are received from two cameras, the method further comprising tracking the one or more of the segments through corresponding ones of the one or more raw frames received from each of the two cameras.

5. The method of claim 4 , further comprising determining, by the computer processor, one or more disparities between the corresponding one of the one or more raw frames in accordance with the segments tracked therein.

6. The method of claim 5 , wherein the one or more disparities are determined by the computer processor in accordance with an application of disparity space decomposition.

7. The method of claim 1 , further comprising:

determining by the computer processor a particular segment to be tracked; and

determining by the computer processor whether the particular segment is providing a static gesture or a dynamic gesture in accordance with a determination of change of position of the particular segment in the time sequence of images.

8. The method of claim 7 , further comprising applying a deep belief network for the gesture recognition in response to determining that the particular segment is providing the static gesture.

9. The method of claim 7 , further comprising applying a disparity space decomposition procedure for the gesture recognition in response to determining if it is determined that the particular segment is providing the dynamic gesture.

10. The method of claim 7 , further comprising:

associating the static gesture or the dynamic gesture with a predetermined action; and

performing an action upon recognition of the static gesture or the dynamic gesture.

11. The method of claim 1 , wherein:

segmenting the one or more highly textured regions in accordance with the textured features thereof to determine the one or more segments thereof is performed in accordance with a morphological analysis of an area employing a convolution kernel to perform texture feature extraction; and

segmenting the one or more non-highly textured regions in accordance with the color thereof to determine the one or more segments thereof is performed in accordance with one of block-based medial filtering and color-based clustering, and a stereo correspondence algorithm to determine pixel depths in the one or more non-highly textured regions.

12. A system for performing gesture recognition, the system comprising:

an input port configured to receive one or more raw frames from one or more cameras, each of the one or more raw frames representing a time sequence of images; and

a processor configured to:

segment the one or more raw frames to obtain segments by:

determining one or more highly textured regions of the one or more raw frames,

segmenting the one or more highly textured regions in accordance with textured features thereof to determine one or more segments thereof

determining one or more non-highly textured regions of the one or more raw frames, and

segmenting the one or more non-highly textured regions in accordance with color thereof to determine one or more segments thereof;

after segmenting the one or more raw frames, generate a depth map in accordance with the segments; and

track one or more of the segments through the one or more raw frames representing the time sequence of images.

13. The system of claim 12 , wherein the processor is further configured to:

before determining the one or more highly textured regions of the one or more raw frames, perform in near-real time an initial motion-based segmentation of the one or more raw frames.

14. The system of claim 12 , wherein the one or more raw frames are a plurality of raw frames, the system further comprising two cameras configured to provide the plurality of raw frames.

15. The system of claim 12 , wherein the processor is further configured to:

segment the one or more highly textured regions in accordance with the textured features thereof to determine the one or more segments thereof is performed in accordance with a morphological analysis of an area employing a convolution kernel to perform texture feature extraction; and

segment the one or more non-highly textured regions in accordance with the color thereof to determine the one or more segments thereof is performed in accordance with one of block-based medial filtering and color-based clustering, and a stereo correspondence algorithm to determine pixel depths in the one or more non-highly textured regions.