iCub-main
Template Tracking with Particle Filter

This module expects a template from the following port /templatePFTracker/template/image:i in order to commence tracking.

+ Collaboration diagram for Template Tracking with Particle Filter:

This module expects a template from the following port /templatePFTracker/template/image:i in order to commence tracking.

This is a simple single-object tracker that uses a color histogram-based observation model. Particle filtering is a Monte Carlo sampling approach to Bayesian filtering.The particle filtering algorithm maintains a probability distribution over the state of the system it is monitoring, in this case, the state – location, scale, etc. – of the object being tracked. Particle filtering represents the distribution as a set of weighted samples, or particles. Each particle describes one possible location of the object being tracked. The set of particles contains more weight at locations where the object being tracked is more likely to be. The most probable state of the object is determined by finding the location in the particle filtering distribution with the highest weight.

Libraries

YARP libraries and OpenCV

Parameters

Command-line Parameters

The following key-value pairs can be specified as command-line parameters by prefixing to the key (e.g. –from file.ini. The value part can be changed to suit your needs; the default values are shown below.

Configuration File Parameters

The following key-value pairs can be specified as parameters in the configuration file (they can also be specified as command-line parameters if you so wish). The value part can be changed to suit your needs; the default values are shown below.

Ports Accessed

Ports Created

Input ports

Input Data Files

None

Output Data Files

None

Tested OS

Linux: Ubuntu 9.10 and Debian Stable

Example Instantiation of the Module

templatePFTracker –name tracker –context templatePFTracker –from templatePFTracker.ini

Author
Vadim Tikhanoff

Copyright (C) 2009 RobotCub Consortium

CopyPolicy: Released under the terms of the GNU GPL v2.0.