Performing gesture recognition using 2D image data

Performing gesture recognition using 2D image data

  • CN 105,210,115 B
  • Filed: 06/10/2013
  • Issued: 10/30/2020
  • Est. Priority Date: 06/10/2013
  • Status: Active Grant
First Claim
Patent Images

1. An apparatus to recognize gestures, comprising:

  • an offline module that determines a skin tone distribution for a plurality of pixels in a video signal, wherein the offline module comprises an edge detection unit that receives a color image associated with a frame of the video signal and performs edge analysis on the color image for each of a plurality of channels, and wherein the edge detection unit comprises;

    box logic to determine, for each of the plurality of channels, a set of Gaussian derivatives;

    convolution logic for performing a convolution between the set of Gaussian derivatives and each pixel in the color image to obtain a gradient magnitude and a gradient angle for each pixel in the color image on a per channel basis; and

    threshold logic to determine whether each gradient magnitude and associated gradient angle corresponds to an edge using a low threshold and a high threshold, wherein the low threshold and the high threshold are channel-specific; and

    an online module that uses the skin tone distribution to make one or more tile-based gesture determinations for the video signal,wherein the online module deletes non-skin pixels from an input frame associated with the video signal based on the skin tone distribution and subsamples the input frame to obtain a plurality of modified frames, wherein the online module comprises a feature extraction unit to identify a plurality of patches in the plurality of modified frames, and wherein the feature extraction unit comprises;

    determining trace logic of a Hessian trace function;

    convolution logic to, for each pixel in a modified frame, perform a convolution between the Hessian trace function and a set of non-adjacent pixels associated with the pixel in the modified frame to obtain a convolution score;

    scaling logic to invoke the convolution logic for a plurality of variance parameter values to obtain a plurality of convolution scores for the pixels in the modified frame; and

    selection logic to identify a block corresponding to a highest score of the plurality of convolution scores.

View all claims
    ×
    ×

    Thank you for your feedback

    ×
    ×