Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Improving Video-Based Robot Self Localization Through Outlier Removal Brad Grinstead, Andreas Koschan, Andrei Gribok, and Mongi A. Abidi
 

Summary: Improving Video-Based Robot Self Localization Through Outlier Removal
Brad Grinstead, Andreas Koschan, Andrei Gribok, and Mongi A. Abidi
The University of Tennessee
334 Ferris Hall
1508 Middle Drive
{bgrinste, akoschan, agribok, abidi}@utk.edu
Abstract The purpose of this paper is to present a method for rejecting false matches of points from successive views in a
video sequence e.g., one used to perform Pose from Motion for a mobile sensing platform. Invariably, the algorithms
used to determine point correspondences between two images output false matches along with the true. These false
matches negatively impact the calculations required to perform the pose estimation from video. This paper presents a new
algorithm for identifying these false matches and removing them from consideration in order to improve system
performance. Experimental results show that our algorithm works in cases where the percentage of false matches may be
as high as 80%, providing a set of point correspondences whose true/false match ratio is much higher than the mutual best
match method commonly used for outlier filtering, resulting in comparable or better outlier rejection increasing the
true/false match ratio by 2-3 times in only a fraction of the time.
Keywords: Robot self-localization, pose from motion, outlier rejection, feature matching, epipolar geometry.
1. INTRODUCTION
Performing tasks in a variety of environments is an
increasing demand in DOE applications for robotic
systems. This requires that the robots have the ability to

  

Source: Abidi, Mongi A. - Department of Electrical and Computer Engineering, University of Tennessee

 

Collections: Computer Technologies and Information Sciences