Download presentation
Presentation is loading. Please wait.
Published byFelicity Norman Modified over 6 years ago
1
Parallelizing the Condensation Algorithm for Visual Tracking
Amay Champaneria MIT Parallel Scientific Computing Monday, May 13, 2002
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
Serial vs. Parallel SerialCondens() { } ParallelCondens() { }
obtain_observations() predict_new_bases() calculate_weights() update() } ParallelCondens() { obtain_observations() Bcast(observations) predict_and_observe() Gather(results) calculate_weights() update() Bcast(updated_results) }
7
Results And higher accuracy than Kalman
8
Tracking Demonstration
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.