Model-based robotic visual servoing

Philippe A. Couvignou, Nikolaos P. Papanikolopoulos, Pradeep K. Khosla

Research output: Contribution to journalConference article

1 Citation (Scopus)

Abstract

This paper presents a model-based approach for visual tracking and servoing in robotics. We propose active deformable models as an effective way for tracking a rigid or semi-rigid (possibly partially occluded) object in movement within the manipulator's workspace. Deformable models simulate the behavior of elastic edges or meshes in real-time. Such models can be designed to adhere to the contour of a rigid or semi-rigid object as defined by the image gradient. Because these models retain a 'memory' of the shape and orientation of the object they track, they can be used effectively in model-based robotic visual servoing. Preliminary experimental results show that the deformable models help us achieve robust tracking even when the target is partially occluded.

Original languageEnglish (US)
Pages (from-to)898-903
Number of pages6
JournalProceedings of the American Control Conference
Volume1
StatePublished - Jan 1 1995
EventProceedings of the 1995 American Control Conference. Part 1 (of 6) - Seattle, WA, USA
Duration: Jun 21 1995Jun 23 1995

Fingerprint

Visual servoing
Robotics
Manipulators
Data storage equipment

Cite this

Model-based robotic visual servoing. / Couvignou, Philippe A.; Papanikolopoulos, Nikolaos P.; Khosla, Pradeep K.

In: Proceedings of the American Control Conference, Vol. 1, 01.01.1995, p. 898-903.

Research output: Contribution to journalConference article

Couvignou, Philippe A. ; Papanikolopoulos, Nikolaos P. ; Khosla, Pradeep K. / Model-based robotic visual servoing. In: Proceedings of the American Control Conference. 1995 ; Vol. 1. pp. 898-903.
@article{a038767b4949494b856710bb6f4b8f81,
title = "Model-based robotic visual servoing",
abstract = "This paper presents a model-based approach for visual tracking and servoing in robotics. We propose active deformable models as an effective way for tracking a rigid or semi-rigid (possibly partially occluded) object in movement within the manipulator's workspace. Deformable models simulate the behavior of elastic edges or meshes in real-time. Such models can be designed to adhere to the contour of a rigid or semi-rigid object as defined by the image gradient. Because these models retain a 'memory' of the shape and orientation of the object they track, they can be used effectively in model-based robotic visual servoing. Preliminary experimental results show that the deformable models help us achieve robust tracking even when the target is partially occluded.",
author = "Couvignou, {Philippe A.} and Papanikolopoulos, {Nikolaos P.} and Khosla, {Pradeep K.}",
year = "1995",
month = "1",
day = "1",
language = "English (US)",
volume = "1",
pages = "898--903",
journal = "Proceedings of the American Control Conference",
issn = "0743-1619",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Model-based robotic visual servoing

AU - Couvignou, Philippe A.

AU - Papanikolopoulos, Nikolaos P.

AU - Khosla, Pradeep K.

PY - 1995/1/1

Y1 - 1995/1/1

N2 - This paper presents a model-based approach for visual tracking and servoing in robotics. We propose active deformable models as an effective way for tracking a rigid or semi-rigid (possibly partially occluded) object in movement within the manipulator's workspace. Deformable models simulate the behavior of elastic edges or meshes in real-time. Such models can be designed to adhere to the contour of a rigid or semi-rigid object as defined by the image gradient. Because these models retain a 'memory' of the shape and orientation of the object they track, they can be used effectively in model-based robotic visual servoing. Preliminary experimental results show that the deformable models help us achieve robust tracking even when the target is partially occluded.

AB - This paper presents a model-based approach for visual tracking and servoing in robotics. We propose active deformable models as an effective way for tracking a rigid or semi-rigid (possibly partially occluded) object in movement within the manipulator's workspace. Deformable models simulate the behavior of elastic edges or meshes in real-time. Such models can be designed to adhere to the contour of a rigid or semi-rigid object as defined by the image gradient. Because these models retain a 'memory' of the shape and orientation of the object they track, they can be used effectively in model-based robotic visual servoing. Preliminary experimental results show that the deformable models help us achieve robust tracking even when the target is partially occluded.

UR - http://www.scopus.com/inward/record.url?scp=0029191489&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029191489&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0029191489

VL - 1

SP - 898

EP - 903

JO - Proceedings of the American Control Conference

JF - Proceedings of the American Control Conference

SN - 0743-1619

ER -