Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Object-based Place Recognition and Scene Change Detection for Perimeter Patrol Chang Cheng, Andreas Koschan and Mongi A. Abidi
 

Summary: Object-based Place Recognition and Scene Change Detection for Perimeter Patrol
Chang Cheng, Andreas Koschan and Mongi A. Abidi
Imaging, Robotics, and Intelligent Systems Lab., The University of Tennessee, 1508 Middle Drive, Knoxville, TN 37996
Email Addresses:{ccheng1, akoschan, abidi}@utk.edu
INTRODUCTION
Robotic perimeter patrol refers to patrolling around a
closed area by a team of robots. The robots need to visit a
target area repeatedly in order to monitor potential
changes in the state of that area. To achieve this task
autonomously, a robot needs to be able to reliably
recognize a place in a large complex environment and
also needs to be able to detect scene changes in the place.
Recently localization technology like GPS can be
employed to provide accurate position information to the
robots. In some cases, however, the GPS signal may not
be available in the patrolled area or may be disturbed. In
this scenario, one possible solution is to recognize a place
based on visual features extracted from the environment.
Humans are capable of recognizing places even in large
complex environments; many psychological works show

  

Source: Abidi, Mongi A. - Department of Electrical and Computer Engineering, University of Tennessee
Koschan, Andreas - Imaging, Robotics, and Intelligent Systems, University of Tennessee

 

Collections: Computer Technologies and Information Sciences; Engineering