1 / 8

Parallelizing the Condensation Algorithm for Visual Tracking

Parallelizing the Condensation Algorithm for Visual Tracking. Amay Champaneria MIT 6.338 - Parallel Scientific Computing Monday, May 13, 2002 http://money.lcs.mit.edu/~amayc/partracker/. The Problem: Pen-Tracking. Track the tip of a pen

shaun
Download Presentation

Parallelizing the Condensation Algorithm for Visual Tracking

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. Parallelizing the Condensation Algorithm for Visual Tracking Amay Champaneria MIT 6.338 - Parallel Scientific Computing Monday, May 13, 2002 http://money.lcs.mit.edu/~amayc/partracker/

  2. The Problem: Pen-Tracking • Track the tip of a pen • Given a model of the pen tip, search the image for the best match • Where to search? • Previous approaches: • Maximum correlation • Kalman filter

  3. The Condensation Algorithm • Developed by Isard and Blake (IJCV 1998) • Condensation = Conditional Density Propogation • Estimate the future probability density by sampling from the current density and weighting the samples by some measure of their likelihood • Visualization…

  4. Visualization of Condensation

  5. Why Parallelize? • Condensation involves taking independent samples (a Monte-Carlo method) • More samples -> higher accuracy, more robust tracking • Allows us to track against cluttered backgrounds

  6. SerialCondens() { obtain_observations() predict_new_bases() calculate_weights() update() } ParallelCondens() { obtain_observations() Bcast(observations) predict_and_observe() Gather(results) calculate_weights() update() Bcast(updated_results) } Serial vs. Parallel

  7. And higher accuracy than Kalman Results

  8. Tracking Demonstration

More Related