1 / 19

Outline of the Talk

Integration of shape constraints in data association filters Giambattista Gennari, Alessandro Chiuso, Fabio Cuzzolin, Ruggero Frezza University of Padova chiuso@dei.unipd.it www.dei.unipd.it/~chiuso. Outline of the Talk. Tracking and Data Association Classical solution: independent dynamics

jadzia
Download Presentation

Outline of the Talk

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. Integration of shape constraints in data association filtersGiambattista Gennari, Alessandro Chiuso, Fabio Cuzzolin, Ruggero FrezzaUniversity of Padovachiuso@dei.unipd.itwww.dei.unipd.it/~chiuso IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  2. Outline of the Talk • Tracking and Data Association • Classical solution: independent dynamics • Our approach : integration of shape • Occlusions • Experiments IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  3. Tracking and Data Association • PROBLEM:Set of targets generating UNLABELLED measurements Associate and Track • Occlusions • Clutter IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  4. SHAPE AND COORDINATION Motion invariant properties of targets: • Rigid or Articulated bodies • Formations of vehicles • (Flock of birds) • Deformable objects Distances and/or angles Connectivity – distances Relative velocity Group of admissible deformations (probabilistic or deterministic) IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  5. Probabilistic Tracking and Data Association CLASSICALLY: JPDAF – MHT + Dynamical Models OUR APPROACH: JPDAF- (MHT) + Independent Dynamical Models + Shape Information Full (joint) model -not flexible -computationally expensive Model targets Independently -flexible and easy -not robust occlusions exchange tracks + Flexible + Robust to occlusions and track proximity - Computation (Monte Carlo) IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  6. Independent Motion • Targets are described by independent dynamics Index of Target • Flexible and easy • Lack of robustness in presence of occlusions, false detections and closely spaced targets IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  7. Associations • An association is a map matching unlabelled measurements to targets • Employ the overall model to compute the probability of each association Measurements Measurements matched to clutter Association Measurements matched to targets IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  8. Description of “Shape” Probabilistic Model Motion Invariant Targets positions • Prior Knowledge • Learn from Data • Example: pairwise distances of non perfectly rigid bodies IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  9. Shape Integration • We assume the overall model can be factored into two terms describing the mutual configuration and single target dynamics Shape constraints Kalman filters and independent dynamical models IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  10. Occlusions • To compute marginalize over the occluded : Detected points Missing points (occlusions) • Compute the integral through Monte Carlo techniques IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  11. Monte Carlo Integration • Sample: • Weight: • Integrate: • Fair sample from the posterior IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  12. Summary Conditional state estimates INDEPENDENT KALMAN FILTERS SHAPE …. T1 T2 TN Association probabilities OVERALL MODEL Monte Carlo fair samples for occluded points state estimation Measurements IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  13. State Estimation • An overall state estimate can be obtained summing the conditional state estimates weighted by the corresponding association probabilities • Alternatively, several state estimates can be propagated over time (multi hypothesis tracker ) Necessary in the learning phase ! IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  14. Results • Real data from a motion capture system • Rapid motion • High numbers of false detections • Occlusions lasting several frames IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  15. Results Commercial system: looses and confuses tracks With shape knowledge learned from data IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  16. Conclusions • Algorithm for integrating shape knowledge into data association filter • Robust in presence of occlusions and clutter • Provide a framework for learning shape models (this requires use of multiple hypothesis kind of algorithms) • (In the example shape was learned from data) IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  17. IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  18. Shape Constraints • In many cases, coordinated points exhibit properties which are invariant with respect to their motion, they satisfy some sort of shape constraints: • pairwise distances of rigidly linked points are constant • the position and velocity of a point moving in group are similar to those of its neighbors IEEE CDC 2004 - Nassau, Bahamas, December 14-17

  19. Coordinated Motion • Rigid motion • Articulated bodies, • Groups of people moving together, • Formations • Taking into account coordination improves tracking robustness • We describe shape and motion separately and combine them together ( more flexible than joint models ) IEEE CDC 2004 - Nassau, Bahamas, December 14-17

More Related