Fast Image-Based Tracking by Selective Pixel Integration - Robotics Institute Carnegie Mellon University

Fast Image-Based Tracking by Selective Pixel Integration

Frank Dellaert and Robert Collins
Workshop Paper, ICCV '99 Workshop on Frame-Rate Vision, September, 1999

Abstract

We provide a fast algorithm to perform image-based tracking, which relies on the selective integration of a small subset of pixels that contain a lot of information about the state variables to be estimated. The resulting dramatic decrease in the number of pixels to process results in a substantial speedup of the basic tracking algorithm. We have used this new method within a surveillance application, where it will enable new capabilities of the system, i.e. real-time, dynamic background subtraction from a panning and tilting camera.

BibTeX

@workshop{Dellaert-1999-15004,
author = {Frank Dellaert and Robert Collins},
title = {Fast Image-Based Tracking by Selective Pixel Integration},
booktitle = {Proceedings of ICCV '99 Workshop on Frame-Rate Vision},
year = {1999},
month = {September},
keywords = {Computer Vision, Visual Tracking, Real-time Vision},
}