Orange Peel - Golf Swing Trainer, Golf Training Device, Golf
Monocular 3-D Tracking of the Golf Swing
1
CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH *Computer Vision Laboratory (CVLab), EPFL, 1015 Lausanne, Switzerland °Department Computer Science, University of Toronto, M5S 3H5, Canada ÉCOLE POLYTECHNIQUE FÉDÉRA CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH CVLAB.EPFL.CH Monocular 3-D Tracking of the Golf Swing Raquel Urtasun*, David J. Fleet° and Pascal Fua* Problem: Model-based 3D people tracking from monocular video. Approach: Deterministic nonlinear optimization based on subspace model for pose trajectories detection of key poses for automatic initialization background subtraction 3-frame correspondence Result: With generic optimization methods the tracker fits smooth motions to monocular video. A multiple hypothesis tracker (e.g., particle filter) is not needed to resolve ambiguities. This work was supported (in part) by the Swiss National Science Foundation. http://cvlab.epfl.ch/~rurtasun ⊥ Tracking as Deterministic Hill-Climbing Minimize With respect to Tracking Objective function 1) Consistency with 2D joint detection 2) Silhouette consistency: Reprojection inside mask 3) 2D Correspondences in a 3 frame bundle adjustment [ ] f f m G G ,..., , ,..., , ,..., 1 1 1 μ μ α α φ = ∂F ∂α i = ∂θ j ∂α i ∂F ∂θ j j =1 ndof ∑ ∂F ∂μ t = ∂θ j ∂μ t ∂F ∂θ j j =1 ndof ∑ ∂θ j ∂μ t = α i ∂Θ ij ∂μ t i =1 m ∑ ∂θ j ∂α i = Θ ij Tracking a golf swing Conclusion Deterministic approach Fully 3D motion Lower cost than probabilistic Applications: Sport, Orthopedics Motion synthesis Complementarity of the function terms Initialization Mean motion Tracking an approach swing Future work Larger database Non linear models Multi-activity database Prior Motion Model PCA is used to learn a subspace model for pose trajectories (ie. sequences of joint angles from kinematic human model). 10 examples same subject CMU database PCA: An eigenvector is the whole motion ψ = ψ μ1 , …, ψ μN [ ] T ≈Θ 0 + α i i =1 m ∑ Θ i [ ] ) ( ) ( ) ( 1 0 t i m i i t T t t μ α μ ψ μ ψ μ Θ + Θ ≈ = ∑ = α: style coefficient μ: virtual time G: global motion F = w typei i =1 nobs ∑ Obs typei ( x i , S) 2 + w G G t − ˆ G t 2 + w μ μ t − ˆ μ t ( ) 2 + w μ μ t − ˆ μ t ( ) 2 + w α α t − ˆ α t ( ) 2 i =1 m ∑ Motion: Pose: Key Pose Detection 4 key poses:
Transcript of Monocular 3-D Tracking of the Golf Swing
CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐
*Computer Vision Laboratory (CVLab), EPFL, 1015 Lausanne, Switzerland °Department Computer Science, University of Toronto, M5S 3H5, Canada
ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE
CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐ CVLAB.EPFL.CH⏐
Monocular 3-D Tracking of the Golf Swing Raquel Urtasun*, David J. Fleet° and Pascal Fua*
Problem: Model-based 3D people tracking from monocular video.
Approach: Deterministic nonlinear optimization based on subspace model for pose trajectories detection of key poses for automatic initialization background subtraction 3-frame correspondence
Result: With generic optimization methods the tracker fits smooth motions to monocular video. A multiple hypothesis tracker (e.g., particle filter) is not needed to resolve ambiguities.
This work was supported (in part) by the Swiss National Science Foundation. http://cvlab.epfl.ch/~rurtasun
⊥
Tracking as Deterministic Hill-Climbing
Minimize
With respect to
Tracking Objective function
1) Consistency with 2D joint detection
2) Silhouette consistency: Reprojection inside mask
3) 2D Correspondences in a 3 frame bundle adjustment
[ ]ffm GG ,...,,,...,,,..., 111 µµααφ =
€
∂F∂α i
=∂θ j
∂α i
∂F∂θ jj=1
ndof
∑ ∂F∂µt
=∂θ j
∂µt
∂F∂θ jj=1
ndof
∑∂θ j
∂µt
= α i
∂Θij
∂µti=1
m
∑∂θ j
∂α i
=Θij
Tracking a golf swing
Conclusion
Deterministic approach Fully 3D motion Lower cost than probabilistic Applications: Sport, Orthopedics Motion synthesis
Complementarity of the function terms
Initialization
Mean motion
Tracking an approach swing
Future work
Larger database Non linear models Multi-activity database
Prior Motion Model PCA is used to learn a subspace model for pose trajectories (ie. sequences of joint angles from kinematic human model). 10 examples same subject CMU database PCA: An eigenvector is the whole motion
€
ψ = ψµ1,…,ψµN[ ]T ≈ Θ0 + α ii=1
m
∑ Θi
[ ] )()()(1
0 ti
m
iit
Ttt µαµψµψ µ Θ+Θ≈= ∑
=
α: style coefficient
µ: virtual time G: global motion
€
F = wtypei
i=1
nobs
∑ Obstypei (xi,S)2
+ wG Gt − ˆ G t2
+ wµ µt − ˆ µ t( )2+ wµ µt − ˆ µ t( )2
+ wα α t − ˆ α t( )2
i=1
m
∑
Motion:
Pose:
Key Pose Detection
4 key poses:
