multi scale visual tracking by sequential belief propagation
Download
Skip this Video
Download Presentation
Multi-scale Visual Tracking by Sequential Belief Propagation

Loading in 2 Seconds...

play fullscreen
1 / 16

Multi-scale Visual Tracking by Sequential Belief Propagation - PowerPoint PPT Presentation


  • 54 Views
  • Uploaded on

Multi-scale Visual Tracking by Sequential Belief Propagation. Gang Hua, Ying Wu Dept. Electrical & Computer Engr. Northwestern University Evanston, IL 60208 {yingwu,ganghua}@ece.northwestern.edu. Abrupt Motion. sudden changes of target dynamics frame dropping large camera motion

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about ' Multi-scale Visual Tracking by Sequential Belief Propagation' - montgomery-arjun


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
multi scale visual tracking by sequential belief propagation

Multi-scale Visual Tracking by Sequential Belief Propagation

Gang Hua, Ying Wu

Dept. Electrical & Computer Engr.

Northwestern University

Evanston, IL 60208

{yingwu,ganghua}@ece.northwestern.edu

CVPR\'2004

abrupt motion
Abrupt Motion
  • sudden changes of target dynamics
  • frame dropping
  • large camera motion
  • etc.

CVPR\'2004

challenges
Challenges
  • Most existing visual tracking methods assume either small motion or accurate motion models
  • Abrupt motion violates them
  • Hierarchical search is not enough
    • Unidirectional information flow
    • Error accumulation from coarse to fine
    • No mechanism to recover failure in coarse scales

CVPR\'2004

our idea
Our Idea
  • Different scales provide different salient visual features
  • Bi-directional information flow among different scales should help
  • Different scales “collaborate”

CVPR\'2004

our formulation
Our Formulation
  • A Markov network
  • X={Xi ,i=1..L}—target state in different scales
  • Z={Zi ,i=1..L}—Image observation of the target in different scales
  • Undirected link— Potential function Ψij(fi(Xi),fj(Xj)),
  • Directed link—Observation function Pi(Zi|Xi)
  • The task is to infer Pi (Xi|Z), i=1..L

Fig.1. Markov Network (MN)

CVPR\'2004

belief propagation bp
Belief propagation (BP)
  • The joint posterior
  • Belief propagation [Pearl’88, Freeman’99]

CVPR\'2004

dynamic markov network
Dynamic Markov Network
  • Xt={Xt,i ,i=1..L}—Target states at time t
  • Zt={Zt,i ,i=1..L}—Image observations at time t
  • P(Xt,i|Xt-1,i)—Dynamic model in the ith scale
  • Zt={Zk, k=1..t}—Image observation up to time t

Fig.2. Dynamic Markov Network (DMN) modeling target dynamics

CVPR\'2004

bayesian inference in dmn
Bayesian inference in DMN
  • Markovian assumption
  • The Bayesian inference is
  • Independent dynamics model

CVPR\'2004

sequential bp
Sequential BP
  • Message Passing in DMN
  • Belief update in DMN

CVPR\'2004

sequential bp monte carlo
Sequential BP Monte Carlo
  • To handle non-Gaussian densities
  • Monte Carlo implementation
  • A set of collaborative particle filters

CVPR\'2004

algorithm
Algorithm

CVPR\'2004

experiments bouncing ball
Experiments: bouncing ball
  • Sudden dynamics changes fail the single particle filters

The tracking result of the Sequential BP

CVPR\'2004

experiments dropping frames
Experiments: dropping frames
  • Dropping 9/10 of the video frames

BP iteration at a specific time instant

CVPR\'2004

conclusion future work
Conclusion& future work
  • Contributions
    • A new multi-scale tracking approach
    • A rigorous statistical formulation
    • A sequential BP algorithm with Monte Carlo
  • Future work
    • Theoretic study& comparison of the BP with the mean field variational approach
    • Learning model parameters

CVPR\'2004

ad