mean shift tracker
play

Mean-Shift Tracker 16-385 Computer Vision (Kris Kitani) Carnegie - PowerPoint PPT Presentation

Mean-Shift Tracker 16-385 Computer Vision (Kris Kitani) Carnegie Mellon University Mean Shift Algorithm A mode seeking algorithm Fukunaga & Hostetler (1975) Mean Shift Algorithm A mode seeking algorithm Fukunaga &


  1. Search for similar descriptor in neighborhood in next frame Target Candidate

  2. Compute a descriptor for the new target Target

  3. Search for similar descriptor in neighborhood in next frame Target Candidate

  4. How do we model the target and candidate regions?

  5. Modeling the target M-dimensional target descriptor q = { q 1 , . . . , q M } (centered at target center) a ‘fancy’ (confusing) way to write a weighted histogram X k ( k x n k 2 ) δ [ b ( x n ) � m ] q m = C A normalized n color histogram Normalization function of inverse quantization bin ID (weighted by distance) factor distance function (weight) sum over Kronecker delta all pixels function

  6. Modeling the candidate M-dimensional candidate descriptor p ( y ) = { p 1 ( y ) , . . . , p M ( y } y 0 (centered at location y ) a weighted histogram at y � 2 ! � y − x n X � � p m = C h δ [ b ( x n ) − m ] k � � h � � n bandwidth

  7. Similarity between the target and candidate p d ( y ) = 1 − ρ [ p ( y ) , q ] Distance function X p Bhattacharyya Coefficient ρ ( y ) ≡ ρ [ p ( y ) , q ] = p m ( y ) q u m p ( y ) Just the Cosine distance between two unit vectors ρ ( y ) = cos θ y = p ( y ) > q X p k p kk q k = p m ( y ) q m m θ q

  8. Now we can compute the similarity between a target and multiple candidate regions

  9. target q p ( y ) ρ [ p ( y ) , q ] image similarity over image

  10. target q we want to find this peak p ( y ) ρ [ p ( y ) , q ] image similarity over image

  11. Objective function max ρ [ p ( y ) , q ] min y d ( y ) same as y Assuming a good initial guess ρ [ p ( y 0 + y ) , q ] Linearize around the initial guess (Taylor series expansion) ρ [ p ( y ) , q ] ≈ 1 p m ( y 0 ) q m + 1 r q m X X p p m ( y ) 2 2 p m ( y 0 ) m m function at specified value derivative

  12. Linearized objective ρ [ p ( y ) , q ] ≈ 1 p m ( y 0 ) q m + 1 r q m X X p p m ( y ) 2 2 p m ( y 0 ) m m � 2 ! � Remember y − x n X � � p m = C h δ [ b ( x n ) − m ] k definition of this? � � h � � n Fully expanded ( � 2 ! ) r � ρ [ p ( y ) , q ] ≈ 1 p m ( y 0 ) q m + 1 q m y − x n X X X p � � δ [ b ( x n ) − m ] C h k � � 2 2 p m ( y 0 ) h � � m m n

  13. Fully expanded linearized objective ( � 2 ! ) r � ρ [ p ( y ) , q ] ≈ 1 p m ( y 0 ) q m + 1 q m y − x n X X X p � � δ [ b ( x n ) − m ] C h k � � 2 2 p m ( y 0 ) h � � m m n Moving terms around… � 2 ! � ρ [ p ( y ) , q ] ≈ 1 p m ( y 0 ) q m + C h y − x n X X p � � w n k � � 2 2 h � � m n Does not depend on unknown y Weighted kernel density estimate r q m X w n = p m ( y 0 ) δ [ b ( x n ) − m ] where m q m > p m ( y 0 ) Weight is bigger when

  14. OK, why are we doing all this math?

  15. We want to maximize this max ρ [ p ( y ) , q ] y

  16. We want to maximize this max ρ [ p ( y ) , q ] y Fully expanded linearized objective � 2 ! � ρ [ p ( y ) , q ] ≈ 1 p m ( y 0 ) q m + C h y − x n X X p � � w n k � � 2 2 h � � m n r q m X w n = p m ( y 0 ) δ [ b ( x n ) − m ] where m

  17. We want to maximize this max ρ [ p ( y ) , q ] y Fully expanded linearized objective � 2 ! � ρ [ p ( y ) , q ] ≈ 1 p m ( y 0 ) q m + C h y − x n X X p � � w n k � � 2 2 h � � m n doesn’t depend on unknown y r q m X w n = p m ( y 0 ) δ [ b ( x n ) − m ] where m

  18. We want to maximize this max ρ [ p ( y ) , q ] y only need to maximize this! Fully expanded linearized objective � 2 ! � ρ [ p ( y ) , q ] ≈ 1 p m ( y 0 ) q m + C h y − x n X X p � � w n k � � 2 2 h � � m n doesn’t depend on unknown y r q m X w n = p m ( y 0 ) δ [ b ( x n ) − m ] where m

  19. We want to maximize this max ρ [ p ( y ) , q ] y Fully expanded linearized objective � 2 ! � ρ [ p ( y ) , q ] ≈ 1 p m ( y 0 ) q m + C h y − x n X X p � � w n k � � 2 2 h � � m n doesn’t depend on unknown y r q m X w n = p m ( y 0 ) δ [ b ( x n ) − m ] where m what can we use to solve this weighted KDE? Mean Shift Algorithm!

  20. � 2 ! � C h y − x n X � � w n k � � h 2 � � n the new sample of mean of this KDE is ✓� 2 ◆ � � y 0 − x n P � � n x n w n g h � y 1 = (this was derived earlier) ✓� 2 ◆ � � y 0 − x n P (new candidate � � n w n g h location) �

  21. Mean-Shift Object Tracking For each frame: 1. Initialize location 
 y 0 Compute 
 q Compute p ( y 0 ) 2. Derive weights w n 3. Shift to new candidate location (mean shift) y 1 p ( y 1 ) 4. Compute k y 0 � y 1 k < ✏ 5. If return 
 Otherwise and go back to 2 y 0 ← y 1

  22. Compute a descriptor for the target Target q

  23. Search for similar descriptor in neighborhood in next frame Target Candidate max ρ [ p ( y ) , q ] y

Recommend


More recommend