{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

Lecture-14 - Change Detection Skin Detection Color Tracking...

Info icon This preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Change Detection, Skin Detection, Color Tracking Lecture-14 Mixture of Gaussians Grimson
Image of page 1

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
2 Algorithm Learn background model by watching 30 second video Detect moving object by measuring deviations from background model, and applying connected component to foreground pixels. Predict position of a region in the next frame using Kalman filter Update background and blob statistics Summary Each pixel is an independent statistical process, which may be combination of several processes. Swaying branches of tree result in a bimodal behavior of pixel intensity. The intensity is fit with a mixture of K Gaussians. ) ( ) ( 2 1 1 2 1 2 1 | | ) 2 ( ) Pr( j t j T j t X X K j j m j t e X µ µ π ω Σ = Σ =
Image of page 2
3 Summary Where X=[R,G,B] T , is a 3x 1 mean vector, is a 3x3 covariance matrix. The method assumes that RGB color channels are independent and have the same variance . In this case = I. Where I is a 3x3 unit matrix. Learning Background Model Every new pixel is checked against all existing distributions. The match is the first distribution such that the pixel value lies within 2 standard deviations of mean. •Another way of measuring distance from a Gaussian distribution is the Mahalanobis distance i.e the match is the distribution with M-distance less than a threshold ) ( ) ( 1 j t j T j t X X d µ µ Σ =
Image of page 3

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
4 Updating • The mean and s.d. of unmatched distributions remain unchanged. For the matched distributions they are updated as: ) ( ) ( ) 1 ( ) 1 ( , , 2 1 , , 1 , , t j t T t j t t j t j t t j t j X X X µ µ ρ σ ρ σ ρ µ ρ µ + = + = • The weights are adjusted: ) ( ) 1 ( , 1 , , t j t j t j M α ω α ω + = = otherwise 0 matches
Image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern