Method for robust human face tracking in presence of multiple persons

Claim 1

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 μ t (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 μ t (k+1) which is used to define the interval [μ t (k)−δ, μ t (k)+δ]; redetermining the trimmed mean until |μ t (k+1)−μ t (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.

Claim 2

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 μ t (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 μ t (k+1) which is used to define the interval [μ t (k)−δ, μ t (k)+δ]; redetermining the trimmed mean until |μ t (k+1)−μ t (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.

Claim 6

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 σ t based on the samples within the interval [μ*−δ, μ*+δ]; and setting size=c*σ t where c is a scaling factor; and extracting and outputting the tracked face regions.

Claim 7

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 σ t based on the samples within the interval [μ*−δ, μ*+δ]; and setting size=c*σ t where c is a scaling factor; and extracting and outputting the tracked face regions.

Claim 11

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 σ t based on the samples within the interval [μ*−δ, μ*+δ]; If h(μ*+d*σ t )≧g*h(μ*) or h(μ*−d*σ t )≧g*h(μ*) where, e.g., d=1.0 and g=0.4, then increase σ t until the condition is no longer true; and setting size=c*σ t , where c is a scaling factor; and extracting and outputting the tracked face regions.

Claim 12

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 σ t based on the samples within the interval [μ*−δ, μ*+δ]; If h(μ*+d*σ t )≧g*h(μ*) or h(μ*−d*σ t )≧g*h(μ*) where, e.g., d=1.0 and g=0.4, then increase σ t until the condition is no longer true; and setting size=c*σ t , where c is a scaling factor; and extracting and outputting the tracked face regions.

Claim 16

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.

Claim 17

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.

Claim 21

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 h y c by projecting columns in the color-filtered image within the range [μ x *−Δ, μ x *+Δ], where Δ determines the number of samples used in the determination; determining size in the y direction based on h y c ; and estimating face locations for tracking facial motion; and extracting and outputting the tracked face regions.

Claim 22

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 h y c by projecting columns in the color-filtered image within the range [μ x *−Δ, μ x *+Δ], where Δ determines the number of samples used in the determination; determining size in the y direction based on h y c ; and estimating face locations for tracking facial motion; and extracting and outputting the tracked face regions.