Probabilistic models for robot-based object segmentation

Daniel Beale, Pejman Iravani, Peter Hall

Research output: Contribution to journalArticle

  • 10 Citations

Abstract

This paper introduces a novel probabilistic method for robot based object segmentation. The method integrates knowledge of the robot's motion to determine the shape and location of objects. This allows a robot with no prior knowledge of its workspace to isolate objects against their surroundings by moving them and observing their visual feedback. The main contribution of the paper is to improve upon current methods by allowing object segmentation in changing environments and moving backgrounds. The approach allows optimal values for the algorithm parameters to be estimated. Empirical studies against alternatives demonstrate clear improvements in both planar and three dimensional motion.
LanguageEnglish
Pages1080-1089
Number of pages10
JournalRobotics and Autonomous Systems
Volume59
Issue number12
Early online date16 Aug 2011
DOIs
StatusPublished - Dec 2011

Fingerprint

Probabilistic Model
Segmentation
Robot
Robots
Motion
Probabilistic Methods
Workspace
Prior Knowledge
Empirical Study
Feedback
Integrate
Three-dimensional
Object
Statistical Models
Alternatives
Demonstrate

Cite this

Probabilistic models for robot-based object segmentation. / Beale, Daniel; Iravani, Pejman; Hall, Peter.

In: Robotics and Autonomous Systems, Vol. 59, No. 12, 12.2011, p. 1080-1089.

Research output: Contribution to journalArticle

@article{5dc54b02beed4b69bff9462a4d049e60,
title = "Probabilistic models for robot-based object segmentation",
abstract = "This paper introduces a novel probabilistic method for robot based object segmentation. The method integrates knowledge of the robot's motion to determine the shape and location of objects. This allows a robot with no prior knowledge of its workspace to isolate objects against their surroundings by moving them and observing their visual feedback. The main contribution of the paper is to improve upon current methods by allowing object segmentation in changing environments and moving backgrounds. The approach allows optimal values for the algorithm parameters to be estimated. Empirical studies against alternatives demonstrate clear improvements in both planar and three dimensional motion.",
author = "Daniel Beale and Pejman Iravani and Peter Hall",
year = "2011",
month = "12",
doi = "10.1016/j.robot.2011.08.003",
language = "English",
volume = "59",
pages = "1080--1089",
journal = "Robotics and Autonomous Systems",
issn = "0921-8890",
publisher = "Elsevier",
number = "12",

}

TY - JOUR

T1 - Probabilistic models for robot-based object segmentation

AU - Beale,Daniel

AU - Iravani,Pejman

AU - Hall,Peter

PY - 2011/12

Y1 - 2011/12

N2 - This paper introduces a novel probabilistic method for robot based object segmentation. The method integrates knowledge of the robot's motion to determine the shape and location of objects. This allows a robot with no prior knowledge of its workspace to isolate objects against their surroundings by moving them and observing their visual feedback. The main contribution of the paper is to improve upon current methods by allowing object segmentation in changing environments and moving backgrounds. The approach allows optimal values for the algorithm parameters to be estimated. Empirical studies against alternatives demonstrate clear improvements in both planar and three dimensional motion.

AB - This paper introduces a novel probabilistic method for robot based object segmentation. The method integrates knowledge of the robot's motion to determine the shape and location of objects. This allows a robot with no prior knowledge of its workspace to isolate objects against their surroundings by moving them and observing their visual feedback. The main contribution of the paper is to improve upon current methods by allowing object segmentation in changing environments and moving backgrounds. The approach allows optimal values for the algorithm parameters to be estimated. Empirical studies against alternatives demonstrate clear improvements in both planar and three dimensional motion.

UR - http://www.scopus.com/inward/record.url?scp=80053565312&partnerID=8YFLogxK

UR - http://dx.doi.org/10.1016/j.robot.2011.08.003

U2 - 10.1016/j.robot.2011.08.003

DO - 10.1016/j.robot.2011.08.003

M3 - Article

VL - 59

SP - 1080

EP - 1089

JO - Robotics and Autonomous Systems

T2 - Robotics and Autonomous Systems

JF - Robotics and Autonomous Systems

SN - 0921-8890

IS - 12

ER -