1 / 16

Multi-scale Visual Tracking by Sequential Belief Propagation

This research paper presents a multi-scale visual tracking approach using sequential belief propagation. It addresses challenges such as abrupt motion, frame dropping, and large camera motion. The proposed algorithm utilizes different scales and bi-directional information flow to improve tracking performance.

tlaird
Télécharger la présentation

Multi-scale Visual Tracking by Sequential Belief Propagation

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. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. 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

  2. Abrupt Motion • sudden changes of target dynamics • frame dropping • large camera motion • etc. CVPR'2004

  3. 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

  4. Our Idea • Different scales provide different salient visual features • Bi-directional information flow among different scales should help • Different scales “collaborate” CVPR'2004

  5. 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

  6. Belief propagation (BP) • The joint posterior • Belief propagation [Pearl’88, Freeman’99] CVPR'2004

  7. 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

  8. Bayesian inference in DMN • Markovian assumption • The Bayesian inference is • Independent dynamics model CVPR'2004

  9. Sequential BP • Message Passing in DMN • Belief update in DMN CVPR'2004

  10. Sequential BP Monte Carlo • To handle non-Gaussian densities • Monte Carlo implementation • A set of collaborative particle filters CVPR'2004

  11. Algorithm CVPR'2004

  12. Experiments: bouncing ball • Sudden dynamics changes fail the single particle filters The tracking result of the Sequential BP CVPR'2004

  13. Experiments: dropping frames • Dropping 9/10 of the video frames BP iteration at a specific time instant CVPR'2004

  14. Experiments: shaking camera CVPR'2004

  15. Experiments: scale changes CVPR'2004

  16. 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

More Related