Minnesota robotic visual tracker: a flexible testbed for vision-guided robotic research

Scott A. Brandt, Christopher E. Smith, Nikolaos P Papanikolopoulos

Research output: Contribution to journalConference article

8 Citations (Scopus)

Abstract

Most early research in robotic visual tracking, especially prior to 1990, separated the vision processing and robot control aspects of the system. Recent attempts to solve the problem close the control loop by incorporating the output of the vision processing as an input to the control subsystem. The Controlled Active Vision framework describes one such approach wherein dynamic target, camera, and environmental factors are incorporated via adaptive controllers that utilize the Sum-of-Squared Differences (SSD) optical flow measurements as an input to the control loop. This paper describes recent work at the University of Minnesota's Artificial Intelligence, Robotics, and Vision Laboratory in developing the Minnesota Robotic Visual Tracker (MRVT), a Controlled Active Vision robotic testbed. In addition, enhancements to the basic SSD algorithm are presented that produce order-of-magnitude improvements over previously reported results.

Original languageEnglish (US)
Pages (from-to)1363-1368
Number of pages6
JournalProceedings of the IEEE International Conference on Systems, Man and Cybernetics
Volume2
StatePublished - Dec 1 1994
EventProceedings of the 1994 IEEE International Conference on Systems, Man and Cybernetics. Part 1 (of 3) - San Antonio, TX, USA
Duration: Oct 2 1994Oct 5 1994

Fingerprint

Testbeds
Robotics
Optical flows
Flow measurement
Processing
Artificial intelligence
Cameras
Robots
Controllers

Cite this

Minnesota robotic visual tracker : a flexible testbed for vision-guided robotic research. / Brandt, Scott A.; Smith, Christopher E.; Papanikolopoulos, Nikolaos P.

In: Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Vol. 2, 01.12.1994, p. 1363-1368.

Research output: Contribution to journalConference article

@article{cae82b9ce7d44986b25eae0f4cfda07e,
title = "Minnesota robotic visual tracker: a flexible testbed for vision-guided robotic research",
abstract = "Most early research in robotic visual tracking, especially prior to 1990, separated the vision processing and robot control aspects of the system. Recent attempts to solve the problem close the control loop by incorporating the output of the vision processing as an input to the control subsystem. The Controlled Active Vision framework describes one such approach wherein dynamic target, camera, and environmental factors are incorporated via adaptive controllers that utilize the Sum-of-Squared Differences (SSD) optical flow measurements as an input to the control loop. This paper describes recent work at the University of Minnesota's Artificial Intelligence, Robotics, and Vision Laboratory in developing the Minnesota Robotic Visual Tracker (MRVT), a Controlled Active Vision robotic testbed. In addition, enhancements to the basic SSD algorithm are presented that produce order-of-magnitude improvements over previously reported results.",
author = "Brandt, {Scott A.} and Smith, {Christopher E.} and Papanikolopoulos, {Nikolaos P}",
year = "1994",
month = "12",
day = "1",
language = "English (US)",
volume = "2",
pages = "1363--1368",
journal = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
issn = "0884-3627",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Minnesota robotic visual tracker

T2 - a flexible testbed for vision-guided robotic research

AU - Brandt, Scott A.

AU - Smith, Christopher E.

AU - Papanikolopoulos, Nikolaos P

PY - 1994/12/1

Y1 - 1994/12/1

N2 - Most early research in robotic visual tracking, especially prior to 1990, separated the vision processing and robot control aspects of the system. Recent attempts to solve the problem close the control loop by incorporating the output of the vision processing as an input to the control subsystem. The Controlled Active Vision framework describes one such approach wherein dynamic target, camera, and environmental factors are incorporated via adaptive controllers that utilize the Sum-of-Squared Differences (SSD) optical flow measurements as an input to the control loop. This paper describes recent work at the University of Minnesota's Artificial Intelligence, Robotics, and Vision Laboratory in developing the Minnesota Robotic Visual Tracker (MRVT), a Controlled Active Vision robotic testbed. In addition, enhancements to the basic SSD algorithm are presented that produce order-of-magnitude improvements over previously reported results.

AB - Most early research in robotic visual tracking, especially prior to 1990, separated the vision processing and robot control aspects of the system. Recent attempts to solve the problem close the control loop by incorporating the output of the vision processing as an input to the control subsystem. The Controlled Active Vision framework describes one such approach wherein dynamic target, camera, and environmental factors are incorporated via adaptive controllers that utilize the Sum-of-Squared Differences (SSD) optical flow measurements as an input to the control loop. This paper describes recent work at the University of Minnesota's Artificial Intelligence, Robotics, and Vision Laboratory in developing the Minnesota Robotic Visual Tracker (MRVT), a Controlled Active Vision robotic testbed. In addition, enhancements to the basic SSD algorithm are presented that produce order-of-magnitude improvements over previously reported results.

UR - http://www.scopus.com/inward/record.url?scp=0028757639&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028757639&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0028757639

VL - 2

SP - 1363

EP - 1368

JO - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

JF - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

SN - 0884-3627

ER -