Robust Feature Tracking

T. Tommasini(*), A. Fusiello(*), E. Trucco(+) and V. Roberto(*)
(*)Laboratorio Immagini, Dipartimento di Matematica e Informatica
Universita` di Udine - Italy
(+)Department of Computing and Electrical Engineering
Heriot-Watt University - United Kingdom

Overview

This work addresses robust feature tracking . We extend the well-known Shi-Tomasi-Kanade tracker by introducing an automatic scheme for rejecting spurious features. We employ a simple and efficient outlier rejection rule, called X84. Experiments with real and synthetic images confirm that our algorithm makes good features to track better.

Method


Results

sequence  
(MPEG, I-frames only)
size parametrs source
Artichoke 480x512x99 rtrack -monitor CMU-VASC   image database
Hotel 480x512x59 rtrack -monitor CMU-VASC   image database
Stairs 512x768x60 rtrack -monitor courtesy of  F. Isgro,  CEE - Heriot-Watt University (UK)
Platform 256x256x20 rtrack -monitor -w  9 -t  0.3 SOFA test sequences
Hyball 170x256x31 rtrack -monitor -w  9 courtesy of  C. Plakas,  OSL - Heriot-Watt University (UK)
Scale 255x384x21 rtrack -monitor -w 13 courtesy of  C. Plakas,  OSL - Heriot-Watt University (UK)
Smallrock 170x256x25 rtrack -monitor -w  9 courtesy of  Chris Smith IMBC, Crete (GR)
Box 240x320x25 rtrack -monitor -w  9 -t  0.08  courtesy of  A. Benedetti, Vision Group, CALTECH (CA)
 
 

Reference paper

T.Tommasini, A.Fusiello, E.Trucco and V.Roberto, Making Good features Track Better, in "1998 IEEE Conference on Computer Vision and Pattern Recognition" , S. Barbara (CA).


Code available

An implementation in C of the Robust Tracker is available from our ftp site.