1. Part-based visual tracking with online latent structural learning -Rui Yao et al. ICCV 2013
Cvlab
Jung ilchae

2. Abstract Part based tracking On-line structural SVM training
Two stage training

3. 2.1 representation 𝐵 𝑡 =𝑏𝑜𝑢𝑛𝑑𝑖𝑛𝑔 𝑏𝑜𝑥 𝑏 𝑡 𝑖 = 𝑖 𝑡ℎ 𝑝𝑎𝑟𝑡 𝑏𝑜𝑥⇒(c,r,h,w)
𝑦 𝑡 =𝑏𝑜𝑢𝑛𝑑𝑖𝑛𝑔 𝑏𝑜𝑥 𝑜𝑓𝑓𝑠𝑒𝑡 𝑧 𝑡 𝑖 =𝑝𝑎𝑟𝑡 𝑏𝑜𝑥 𝑜𝑓𝑓𝑠𝑒𝑡⇒ ∆𝑐,∆𝑟,∆𝑤,∆ℎ
Φ 𝑥 𝑡 , 𝑦, 𝑧 = [ 𝜙 1 𝑥 𝑡 , 𝑧 1 , 𝜙 1 𝑥 𝑡 , 𝑧 2 ,⋅⋅⋅ 𝜙 1 𝑥 𝑡 , 𝑧 𝑀 , 𝜙 2 𝑥 𝑡 , 𝑦 , 𝜙 3 𝑦, 𝑧 1 , 𝜙 3 𝑦, 𝑧 2 ⋅⋅⋅ 𝜙 3 𝑦, 𝑧 𝑀 ]
𝑏 𝑡 1
𝐵 𝑡
𝑏 𝑡 2
𝑏 𝑡 3
𝑏 𝑡 4
𝜙 1 ()=𝐴𝑝𝑝𝑒𝑎𝑟𝑎𝑛𝑐𝑒 𝑚𝑜𝑑𝑒𝑙 𝑓𝑜𝑟 𝑝𝑎𝑟𝑡 𝑏𝑜𝑥 𝜙 2 ()=𝐴𝑝𝑝𝑒𝑎𝑟𝑎𝑛𝑐𝑒 𝑚𝑜𝑑𝑒𝑙 𝑓𝑜𝑟 𝑏𝑜𝑢𝑛𝑑𝑖𝑛𝑔 𝑏𝑜𝑥 𝜙 3 ()=𝑟𝑒𝑙𝑎𝑡𝑖𝑜𝑛𝑠 𝑏𝑒𝑡𝑤𝑒𝑒𝑛 𝑏𝑜𝑢𝑛𝑑𝑖𝑛𝑔 𝑏𝑜𝑥 𝑎𝑛𝑑 𝑝𝑎𝑟𝑡 𝑏𝑜𝑥
𝜙 1 (), 𝜙 2 ()=𝑐𝑜𝑚𝑝𝑢𝑡𝑒𝑑 𝑓𝑟𝑜𝑚 2𝑠𝑐𝑎𝑙𝑒𝑠, 6 𝑡𝑦𝑝𝑒 ℎ𝑎𝑎𝑟−𝑙𝑖𝑘𝑒 𝑚𝑎𝑠𝑘𝑠
𝜙 3 ()= 𝑎, 𝑎 2 𝑠.𝑡 𝑎=𝑑𝑖𝑠𝑡𝑎𝑛𝑐𝑒 𝑏𝑒𝑡𝑤𝑒𝑒𝑛 𝐵 𝑡 𝑎𝑛𝑑 𝑏 𝑡 𝑖

4. Framework Finding target with 𝑤 𝑡 Training S-SVM sampling
true
Training S-SVM
true
sampling
Finding target with sampling near 𝐵 𝑡−1 , 𝑏 𝑡−1 𝑖 𝑖=1,,𝑀 𝑦 𝑡 ∗ , 𝑧 𝑡 ∗ = arg max 𝑦,𝑧 𝑤 𝑡 Φ 𝑥 𝑡 , 𝑦, 𝑧
Sampling training data near the new target Training structured SVM to maximize target’s score

5. 2.2 latent pegasos for training online
𝑤 𝑡+1 = arg min{ 𝑤 𝜆 2 𝑤 𝑁 𝑖=1 𝑁 ∆ 𝑦 𝑡 , 𝑦 𝑡,𝑖 + max 𝑧′ <𝑤,Φ( 𝑥 𝑡 , 𝑦 𝑡,𝑖 , 𝑧 ′ )>− max 𝑧 <𝑤,Φ( 𝑥 𝑡 , 𝑦 𝑡 , 𝑧 ′ )> }
∆ 𝑦 𝑡 ,𝑦 =1− ( 𝐵 𝑡−1 + 𝑦 𝑡 )∩( 𝐵 𝑡−1 +𝑦) ( 𝐵 𝑡−1 + 𝑦 𝑡 )∪( 𝐵 𝑡−1 +𝑦)
𝑎 + =max⁡(0,𝑎)
Find 𝑤 by gradient descent algorithm
𝑤 𝑡+1 ← 1− 𝜂 𝑡 𝜆 𝑤 𝑡 + 𝜂 𝑡 𝑁 𝑖=1 𝑀 1[ max 𝑧 ′ 𝑓( 𝑥 𝑡 , 𝑦 𝑡,𝑖 , 𝑧 ′ ; 𝑤 𝑡 ) − max 𝑧 𝑓 𝑥 𝑡 , 𝑦 𝑡 ,𝑧; 𝑤 𝑡 +∆ 𝑦 𝑡 , 𝑦 𝑡,𝑖 >0 ] 𝛿Φ t y t
𝛻 𝑡 =𝜆 𝑤 𝑡 − 1 𝑁 𝑖=1 𝑁 1 max 𝑧 ′ 𝑓( 𝑥 𝑡 , 𝑦 𝑡,𝑖 , 𝑧 ′ ; 𝑤 𝑡 − max 𝑧 𝑓 𝑥 𝑡 , 𝑦 𝑡 ,𝑧; 𝑤 𝑡 +∆ 𝑦 𝑡 , 𝑦 𝑡,𝑖 >0 ]δ Φ t y t
𝑠.𝑡 𝑧 = arg max 𝑧 𝑓 𝑥 𝑡 , 𝑦 𝑡 ,𝑧; 𝑤 𝑡 , 𝑧′ = arg max 𝑧′ 𝑓( 𝑥 𝑡 , 𝑦 𝑡,𝑖 , 𝑧 ′ ; 𝑤 𝑡 ) δ Φ t y t =Φ( 𝑥 𝑡 , 𝑦 𝑡 , 𝑧 )-Φ( 𝑥 𝑡 , 𝑦 𝑡 , 𝑧′ )

6. 2.2 latent pegasos for training online
The label cost ∆ does not take into account the part boxes
∆ 𝑦 𝑡 ,𝑦 =1− ( 𝐵 𝑡−1 + 𝑦 𝑡 )∩( 𝐵 𝑡−1 +𝑦) ( 𝐵 𝑡−1 + 𝑦 𝑡 )∪( 𝐵 𝑡−1 +𝑦)

7. 3. Two stage training Stage 1. Update 𝑢 𝑡+1 𝑖 𝑖=1,,𝑀 for part boxes
𝑢 𝑡+1 𝑗 = arg min 𝑢 𝑗 𝜆 𝑢 𝑗 𝑁 𝑘=1 𝑁 ∆ 𝑧 𝑡 , 𝑧 𝑡,𝑘 𝑗 +< 𝑢 𝑗 ,Φ 𝑥 𝑡 , 𝑧 𝑡,𝑘 𝑗 >−< 𝑢 𝑗 ,Φ( 𝑥 𝑡 , 𝑧 𝑡 𝑗 )> +
Stage 2. Update 𝑣 𝑡+1 𝑖 𝑖=0,,, bounding box
𝑣 𝑡+1 ← 1− 𝜂 𝑡 𝜆 𝑣 𝑡 + 𝜂 𝑡 𝑁 𝑖=1 𝑀 1 max 𝑧 ′ 𝑓( 𝑥 𝑡 , 𝑦 𝑡,𝑖 , 𝑧 ′ ; 𝑣 𝑡 − max 𝑧 𝑓 𝑥 𝑡 , 𝑦 𝑡 ,𝑧; 𝑣 𝑡 +∆ 𝑦 𝑡 , 𝑦 𝑡,𝑖 >0]𝛿 Φ t y t δ Φ t y t =Φ( 𝑥 𝑡 , 𝑦 𝑡 , 𝑧 )-Φ( 𝑥 𝑡 , 𝑦 𝑡 , 𝑧′ )

8. 3. Two stage training

9. Another problem
Part box initialization

10. Another problem
Tracking of a non-rigid object via patch based dynamic appearance modeling and adaptive Basin hopping Monte Carlo Sampling –CVPR 09’
Part box initialization
This Paper
Is sufficiently Big part-box advantageous?

11. 3. Result

12. 3. Result

13. 3. Experiment

14. contribution Strong at Partial occlusion & shape deformatation
Online learning latent SVM
2 stage training -> more accurate

15. Discussion No accumulation of positive targets
Problems of this paper
No accumulation of positive targets
Restriction of fixed size of bounding box
Problem of part based tracking
Part initialization – location, size
Relations between bounding box and part boxes

16. Feedback
My recent work: Tracking with part graph matching - Part box initialization - Feature Change : size, or others - Definition of relation between bounding box and part box