A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline...

34
A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, Jul 2013 1

Transcript of A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline...

Page 1: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

1

A General Framework for Tracking MultiplePeople from a Moving Camera

Wongun Choi, Caroline Pantofaru, Silvio Savarese

IEEE TRANSACTION ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, July 2013

Page 2: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

2

Overview• Motivation• Related Work• Introduction• Proposed Method• Experiment Result• Conclusion

Page 3: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

3

Motivation1.Final goal is tracking multiple people from a moving camera, including outdoor video scene and indoor video scene.

2.There are some challenge to solve:

1) People have variety poses

2) Complexity of the motion patterns of multiple people

in the same scene

3) Changeable scene and illumination effect

Page 4: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

4

Related work1. Tracking by online learning :Learning appearance model [10],[5],[34],[7],[26]Color histogram and mean shift [10]2. Tracking with a moving camera:Probabilistic framework multiple detectors [42],[43]Stereo and graphical model [12],[13][5] S. Avidan. Ensemble tracking. In PAMI, 2007[7] C. Bibby and I. Reid. Robust real-time visual tracking using pixelwise posteriors. In ECCV, 2008[10] D. Comaniciu and P. Meer. Mean shift:Arobust approach toward feature space analysis. In PAMI, 2002.[12] A. Ess, B. Leibe, K. Schindler, and L. van Gool. A mobile vision system for robust multi-person tracking. In CVPR, 2008.[13] A. Ess, B. Leibe, K. Schindler, and L. van Gool. Robust multi person tracking from a mobile platform. PAMI, 2009.[26] S. Kwak, W. Nam, B. Han, and J. Han. Learning occlusion with likelihoods for visual tracking. In ICCV, 2011[34] D. Ramanan, D. Forsyth, and A. Zisserman. Tracking people by learning their appearance. PAMI, Jan. 2007.[42] C. Wojek, S. Walk, S. Roth, and B. Schiele. Monocular 3d scene understanding with explicit occlusion reasoning. In CVPR, 2011.[43] C. Wojek, S. Walk, and B. Schiele. Multi-cue onboard pedestrian detection. In CVPR, 2009

Page 5: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

5

Introduction(1)To solve these issues proposed method:1) People have variety poses :

Fusing multiple person detection method and some observations

2) Complexity of the motion patterns of multiple people in the same scene

Build a motion model that capture the interaction between targets

3) Changeable scene and illumination effect

Proposed a novel 3D model which explain the process of video generation

Page 6: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

6

Introduction(2)Observation cues:

Page 7: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

7

Introduction(3)Build 3D Model:

Page 8: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

8

Introduction(4)Particle filter:1.Def: posterior density estimation algorithms that estimate the posterior density of the state-space by directly implementing the Bayesian recursion equations

2.Using sampling for generating state distribution of posterior and using resamplingTo reconstruct the new distribution

Page 9: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

9

Introduction(5)Reversible-Jump Markov Chain Monte Carlo(RJMCMC):

A class of algorithms for sampling from probability distributions based on constructing a Markov chain which allows changes of the dimensionality of the state

Page 10: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

10

Proposed MethodSystem overview:1.Using observation cues to generate detection hypotheses and an observationModel2.Build a motion model account both for people’s unexpected motions as well as interactions between people3. Sampling procedure for the RJ-MCMC tracker which include evaluation(resampling)

Page 11: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

11

Proposed MethodModel representation:

Page 12: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

12

Proposed Method Using as random variables and model their relationship by joint

posterior probability The tracking problem can formulate as finding maximum-a-posteri (MAP)

(a) Observation likelihood(b) Motion model (transition model)(c) Posterior at time t-1

Page 13: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

13

Proposed Method(a) Observation likelihood:

Camera projection function:

Page 14: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

14

Proposed MethodTarget Observation Likelihood:

j:detectorswj: weight for detector j

Page 15: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

15

Proposed MethodTarget Observation Likelihood: 1) pedestrian detector 2) upper body detector 3) target-specific detector based on appearance model 4) detector based on upper-body shape from depth 5) face detector 6) skin detector 7) motion detector

Page 16: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

16

Proposed MethodPedestrian and upper body detector using HOG:

Page 17: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

17

Proposed MethodFace detector using OpenCV Viola-jones face detector:

Page 18: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

18

Proposed MethodSkin color detector using threshold on HSV color space:

Page 19: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

19

Proposed MethodDepth shape detector using world coordinate system:

Page 20: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

20

Proposed MethodMotion detector by project motion points into image plane and threshold:

Page 21: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

21

Proposed MethodGeometric Feature likelihood by interest point detector:

is the uniform distribution

Page 22: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

22

Proposed MethodMotion prior:

Page 23: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

23

Proposed MethodCamera motion prior:

Page 24: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

24

Proposed MethodTarget motion prior:

Page 25: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

25

Proposed MethodExistence prior:

Page 26: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

26

Proposed Method

Motion prior:

Independent

Interacting

Page 27: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

27

Proposed MethodIndependent Motion prior :

update

Page 28: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

28

Proposed MethodInteracting Motion prior:

Mode variable

Page 29: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

29

Proposed MethodRepulsion:

Group motion:

Repulsion force

Page 30: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

30

Proposed MethodTracking by Reversible Jump Markov Chain Monte Carlo Particle filtering: Sampling:

Convert posterior problem:

Page 31: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

31

Experimental result Using ETH dataset [12]

Video frame rate ~14Hz

Resolution 640*480 pixels

Page 32: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

32

Experimental result Single frame detection accuracy via overlap ratio between the ground truth bounding

box and tracked bounding box.

Page 33: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

33

Experimental result

Page 34: A General Framework for Tracking Multiple People from a Moving Camera Wongun Choi, Caroline Pantofaru, Silvio Savarese IEEE TRANSACTION ON PATTERN ANALYSIS.

34

Conclusion

• Combine probabilistic model with joint variables– Relationship between the camera, targets’ and geometric features

• Combine multiple cues– adaptable to different sensor configurations and different

environments

• Allowing people to interact• Automatically detecting people