System and methods for persona identification using combined probability maps

• US 9,414,016 B2
• Filed: 12/31/2013
• Issued: 08/09/2016
• Est. Priority Date: 12/31/2013
• Status: Active Grant

• Current Assignee: Personify Incorporated (Wilson Human Capital Group, Inc.)
• Original Assignee: Personify Incorporated (Wilson Human Capital Group, Inc.)
• Inventors: Lin, Dennis, Francisco, Glenn, Nguyen, Quang, Dang, Long
• Primary Examiner(s): Koziol, Stephen R
• Assistant Examiner(s): CONNER, SEAN M
• Application Number:
  US14/145,874
• Publication Number:
  US 20150187076A1
• Time in Patent Office: 952 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/23 Clustering techniques
• CPC Class Codes: G06F 18/251 of input or preprocessed data
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 2207/20228 Disparity calculation for image-based rendering
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/143 involving probabilistic approaches, e.g. Markov random field [MRF] modelling
• CPC Class Codes: G06T 7/149 involving deformable models, e.g. active contour models
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation
• CPC Class Codes: G06V 10/755 Deformable models or variational models, e.g. snakes or active contours
• CPC Class Codes: G06V 10/803 of input or preprocessed data
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: H04N 7/147 Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals selecting H04Q
• CPC Class Codes: H04N 7/15 Conference systems

Abstract

Disclosed herein are systems and methods for extracting person image data comprising: obtaining at least one frame of pixel data and corresponding image depth data; processing the at least one frame of pixel data and the image depth data with a plurality of persona identification modules to generate a corresponding plurality of persona probability maps; combining the plurality of persona probability maps to obtain an aggregate persona probability map; and generating a persona image by extracting pixels from the at least one frame of pixel data based on the aggregate persona probability map.

Claims

1. A method comprising:

obtaining at least one frame of pixel data and corresponding image depth data;

processing the at least one frame of pixel data and the corresponding image depth data with a plurality of persona identification modules to generate a corresponding plurality of persona probability maps, wherein the plurality of persona probability maps includes a hair-identification-module persona probability map, and wherein the plurality of persona identification modules comprises a hair-identification module for generating the hair-identification-module probability map at least in part by;

identifying a plurality of pixel columns that cross an identified head contour; and

for each pixel column in the plurality of pixel columns;

performing a color-based segmentation of the pixels in the pixel column into a foreground segment, a hair segment, and a background segment; and

assigning the pixels in the hair segment an increased foreground-probability value in the hair-identification-module persona probability map;

combining the plurality of persona probability maps to obtain an aggregate persona probability map; and

generating a persona image by extracting pixels from the at least one frame of pixel data based on the aggregate persona probability map.

2. The method of claim 1, wherein:

the at least one frame of pixel data comprises two frames of stereo pixel data; and

the corresponding image depth data is obtained from disparity data generated by a stereo disparity module.

3. The method of claim 2, wherein processing the at least one frame of pixel data and the corresponding image depth data comprises:

generating a foreground-background map from the disparity data by designating pixels having a disparity value above a threshold as foreground pixels.

4. The method of claim 2, wherein:

the disparity data comprises a plurality of disparity values for each pixel, each of the plurality of disparity values having an associated confidence value; and

processing the at least one frame of pixel data and the corresponding image depth data comprises generating a foreground-background map from the disparity data by identifying pixels having a cumulative confidence measure above a threshold as foreground pixels.

5. The method of claim 1, wherein processing the at least one frame of pixel data and the corresponding image depth data comprises converting the corresponding image depth data to a foreground-background map using a thresholding operation.

6. The method of claim 5, wherein processing the at least one frame of pixel data and the corresponding image depth data further comprises performing a distance transform on the foreground-background map to obtain a persona probability map.

7. The method of claim 1, wherein extracting pixels is performed using a graph cut module.

8. The method of claim 1, wherein the aggregate persona probability map is formed by combining the plurality of persona probability maps using predetermined weights.

13. The method of claim 1, further comprising converting the head contour into a multi-segment polygon that approximates the head contour, the multi-segment polygon being formed of multiple head-contour segments, wherein identifying the plurality of pixel columns that cross the identified head contour comprises identifying pixel columns that cross one of the head-contour segments.

14. The method of claim 1, wherein performing a color-based segmentation comprises performing a color-based segmentation using a clustering algorithm.

15. The method of claim 14, wherein the clustering algorithm is a k-means algorithm with k=3.

16. The method of claim 1, wherein performing the color-based segmentation of the pixels in a given pixel column into the foreground segment, the hair segment, and the background segment of the given pixel column comprises:

identifying an average foreground-pixel color, an average hair-pixel color, and an average background-pixel color for the given pixel column; and

identifying the foreground segment, the hair segment, and the background segment of the given pixel column using a clustering algorithm to cluster the pixels in the given pixel column around the identified average foreground-pixel color, the identified average hair-pixel color, and the identified average background-pixel color for the given pixel column, respectively.

17. The method of claim 16, wherein:

identifying the average foreground-pixel color for the given pixel column comprises identifying the average foreground-pixel color for the given pixel column based on a first set of pixels at an innermost end of the given pixel column;

identifying the average hair-pixel color for the given pixel column comprises identifying the average hair-pixel color for the given pixel column based on a second set of pixels that includes a point where the given pixel column crosses the identified head contour; and

identifying the average background-pixel color for the given pixel column comprises identifying the average background-pixel color for the given pixel column based on a third set of pixels at an outermost end of the given pixel column.

18. The method of claim 1, further comprising, for each pixel column in the plurality of pixel columns:

assigning the pixels in the foreground and background segments an equal probability of being in the foreground and being in the background in the hair-identification-module persona probability map.

19. The method of claim 1, wherein assigning the pixels in the hair segment an increased foreground-probability value in the hair-identification-module persona probability map comprises:

assigning a first value to the pixels in the hair segment in the hair-identification-module persona probability map; and

assigning a second value to the pixels in the foreground and background segments in the hair-identification-module persona probability map, wherein the first value corresponds to a higher probability of being a foreground pixel than does the second value.

9. A method comprising:

obtaining at least one frame of pixel data and corresponding image depth data;

processing the corresponding image depth data to generate a foreground-background map;

processing the at least one frame of pixel data and the foreground-background map to generate a plurality of persona probability maps at least in part through use of a hair-identification module, wherein the plurality of persona probability maps includes a hair-identification-module persona probability map that is generated by the hair-identification module at least in part by;

identifying a plurality of pixel columns that cross an identified head contour; and

for each pixel column in the plurality of pixel columns;

performing a color-based segmentation of the pixels in the pixel column into a foreground segment, a hair segment, and a background; and

assigning the pixels in the hair segment an increased foreground-probability value in the hair-identification-module persona probability map;

combining the plurality of persona probability maps to obtain an aggregate persona probability map; and

generating a persona image by extracting pixels from the at least one frame of pixel data based on the aggregate persona probability map.

10. The method of claim 9, wherein the foreground-background map is generated from a disparity data volume.

11. The method of claim 9, wherein processing the at least one frame of pixel data and the foreground-background map to generate a plurality of persona probability maps comprises:

performing a distance transform on the foreground-background map to generate a persona probability map.

12. An apparatus comprising:

a foreground-background module configured to generate a foreground-background map based on image depth data;

a plurality of persona identification modules configured to generate a corresponding plurality of persona probability maps, wherein the plurality of persona identification modules comprises a hair-identification module, wherein the plurality of persona probability maps includes a hair-identification-module persona probability map that is generated by the hair-identification module at least in part by;

identifying a plurality of pixel columns that cross an identified head contour; and

for each pixel column in the plurality of pixel columns;

performing a color-based segmentation of the pixels in the pixel column into a foreground segment, a hair segment, and a background segment; and

assigning the pixels in the hair segment an increased foreground-probability value in the hair-identification-module persona probability map;

a combiner module configured to generate an aggregate persona probability map based on the plurality of persona probability maps; and

a persona extraction module configured to generate a persona image by extracting pixels from at least one frame of pixel data based on the aggregate persona probability map.