Method for robust human face tracking in presence of multiple persons
AssigneeSharp Laboratories of America, Inc.
InventorsRichard J. Qian, Kristine E. Matthews
Life of this patent
Estimating the term…
Abstract
A method for robust human face tracking in the presence of multiple facial images includes taking a frame from a color video sequence as a current input image; filtering the current input image to form a filtered image; estimating the locations and sizes of faces in the filtered image based on a projection histogram of the filtered image; estimating face motion in the filtered image; and outputting the location and size of the tracked faces within the filtered image.
Claims20
A method for robust human face tracking in the presence of multiple facial images comprising:
- taking a frame from a color video sequence as a current input image;
- filtering the current input image in chromaticity space;
- estimating the locations of faces in the image based on a projection histogram of the filtered image, including:
- determining a sample mean μ and standard deviation σ using all of the samples in a distribution;
- setting μt(0)=μ and δ=max (a*σ, b*image-width) where a and b are scaling factors, resulting in an initial trimmed mean μ(k) within an initial trimmed interval (k);
- determining a trimmed mean μt (k+1) which is used to define the interval [μt(k)−δ, μt(k)+δ];
- redetermining the trimmed mean until |μt (k+1)−μt(k)|<ε where ε is tolerance;
- and determining a robust mean μ* within a final trimmed interval;
- and
- extracting and outputting the tracked face regions.
A method for robust human face tracking in the presence of multiple facial images comprising:
- taking a frame from a color video sequence as a current input image;
- filtering the current input image in chromaticity space;
- estimating the locations of faces in the image based on a projection histogram of the filtered image;
- determining the size of a facial area by:
- determining the trimmed standard deviation σt based on the samples within the interval [μ*−δ, μ*+δ];
- and
- setting size=c*σt where c is a scaling factor;
- and
- extracting and outputting the tracked face regions.
A method for robust human face tracking in the presence of multiple facial images comprising:
- taking a frame from a color video sequence as a current input image;
- filtering the current input image in chromaticity space;
- estimating the locations of faces in the image based on a projection histogram of the filtered image
- determining the size of a facial area by:
- determining the trimmed standard deviation σt based on the samples within the interval [μ*−δ, μ*+δ];
- If h(μ*+d*σt)≧g*h(μ*) or h(μ*−d*σt)≧g*h(μ*) where, e.g., d=1.0 and g=0.4, then increase σt until the condition is no longer true;
- and
- setting size=c*σt, where c is a scaling factor;
- and
- extracting and outputting the tracked face regions.
A method for robust human face tracking in the presence of multiple facial images comprising:
- taking a frame from a color video sequence as a current input image;
- filtering the current input image in chromaticity space;
- estimating the locations of faces in the image based on a projection histogram of the filtered image
- determining the size of a facial area by:
- setting width = 1 ( 2 N + 1 ) ∑ i = - N N h y ( μ y * + i ) ;
- and
- setting height = 1 ( 2 N + 1 ) ∑ i = - N N h x ( μ x * + i ) ,
- wherein N determines the number of samples used in the determination of the size of the facial image;
- and
- extracting and outputting the tracked face regions.
A method for robust human face tracking in the presence of multiple facial images comprising:
- taking a frame from a color video sequence as a current input image;
- filtering the current input image in chromaticity space;
- estimating the locations of faces in the image based on a projection histogram of the filtered image
- determining the size of a facial area by determining the size from a projection histogram of a clipped region of the color-filtered image by:
- forming the clipped projection histogram hyc by projecting columns in the color-filtered image within the range [μx*−Δ, μx*+Δ], where Δ determines the number of samples used in the determination;
- determining size in the y direction based on hyc;
- and
- estimating face locations for tracking facial motion;
- and
- extracting and outputting the tracked face regions.
Dependencies are inferred from the claim text.