A Monocular Pointing Pose Estimator for Gestural Instruction of a Mobile Robot

We present an important aspect of our human-robot communication interface which is being developed in the context of our long-term research framework PERSES dealing with highly interactive mobile companion robots. Based on a multi-modal people detection and tracking system, we present a hierarchical...

Full description

Bibliographic Details
Main Authors: Andrea Scheidig, Christian Martin, Steffen Mueler, Horst-Michael Gross, Jan Richarz
Format: Article
Language:English
Published: SAGE Publishing 2008-11-01
Series:International Journal of Advanced Robotic Systems
Online Access:http://www.intechopen.com/articles/show/title/a_monocular_pointing_pose_estimator_for_gestural_instruction_of_a_mobile_robot
_version_ 1818833584357638144
author Andrea Scheidig
Christian Martin
Steffen Mueler
Horst-Michael Gross
Jan Richarz
author_facet Andrea Scheidig
Christian Martin
Steffen Mueler
Horst-Michael Gross
Jan Richarz
author_sort Andrea Scheidig
collection DOAJ
description We present an important aspect of our human-robot communication interface which is being developed in the context of our long-term research framework PERSES dealing with highly interactive mobile companion robots. Based on a multi-modal people detection and tracking system, we present a hierarchical neural architec- ture that estimates a target point at the floor indicated by a pointing pose, thus enabling a user to navigate a mo- bile robot to a specific target position in his local surroundings by means of pointing. In this context, we were especially interested in determining whether it is possible to accomplish such a target point estimator using only monocular images of low-cost cameras. The estimator has been implemented and experimentally investigated on our mobile robotic assistant HOROS. Although only monocular image data of relatively poor quality were util- ized, the estimator accomplishes a good estimation performance, achieving an accuracy better than that of a hu- man viewer on the same data. The achieved recognition results demonstrate that it is in fact possible to realize a user-independent pointing direction estimation using monocular images only, but further efforts are necessary to improve the robustness of this approach for everyday application.
first_indexed 2024-12-19T02:21:15Z
format Article
id doaj.art-9b2fe4cf92bd42d8a87da385ea4dc1c4
institution Directory Open Access Journal
issn 1729-8806
1729-8814
language English
last_indexed 2024-12-19T02:21:15Z
publishDate 2008-11-01
publisher SAGE Publishing
record_format Article
series International Journal of Advanced Robotic Systems
spelling doaj.art-9b2fe4cf92bd42d8a87da385ea4dc1c42022-12-21T20:40:11ZengSAGE PublishingInternational Journal of Advanced Robotic Systems1729-88061729-88142008-11-0141A Monocular Pointing Pose Estimator for Gestural Instruction of a Mobile RobotAndrea ScheidigChristian MartinSteffen MuelerHorst-Michael GrossJan RicharzWe present an important aspect of our human-robot communication interface which is being developed in the context of our long-term research framework PERSES dealing with highly interactive mobile companion robots. Based on a multi-modal people detection and tracking system, we present a hierarchical neural architec- ture that estimates a target point at the floor indicated by a pointing pose, thus enabling a user to navigate a mo- bile robot to a specific target position in his local surroundings by means of pointing. In this context, we were especially interested in determining whether it is possible to accomplish such a target point estimator using only monocular images of low-cost cameras. The estimator has been implemented and experimentally investigated on our mobile robotic assistant HOROS. Although only monocular image data of relatively poor quality were util- ized, the estimator accomplishes a good estimation performance, achieving an accuracy better than that of a hu- man viewer on the same data. The achieved recognition results demonstrate that it is in fact possible to realize a user-independent pointing direction estimation using monocular images only, but further efforts are necessary to improve the robustness of this approach for everyday application.http://www.intechopen.com/articles/show/title/a_monocular_pointing_pose_estimator_for_gestural_instruction_of_a_mobile_robot
spellingShingle Andrea Scheidig
Christian Martin
Steffen Mueler
Horst-Michael Gross
Jan Richarz
A Monocular Pointing Pose Estimator for Gestural Instruction of a Mobile Robot
International Journal of Advanced Robotic Systems
title A Monocular Pointing Pose Estimator for Gestural Instruction of a Mobile Robot
title_full A Monocular Pointing Pose Estimator for Gestural Instruction of a Mobile Robot
title_fullStr A Monocular Pointing Pose Estimator for Gestural Instruction of a Mobile Robot
title_full_unstemmed A Monocular Pointing Pose Estimator for Gestural Instruction of a Mobile Robot
title_short A Monocular Pointing Pose Estimator for Gestural Instruction of a Mobile Robot
title_sort monocular pointing pose estimator for gestural instruction of a mobile robot
url http://www.intechopen.com/articles/show/title/a_monocular_pointing_pose_estimator_for_gestural_instruction_of_a_mobile_robot
work_keys_str_mv AT andreascheidig amonocularpointingposeestimatorforgesturalinstructionofamobilerobot
AT christianmartin amonocularpointingposeestimatorforgesturalinstructionofamobilerobot
AT steffenmueler amonocularpointingposeestimatorforgesturalinstructionofamobilerobot
AT horstmichaelgross amonocularpointingposeestimatorforgesturalinstructionofamobilerobot
AT janricharz amonocularpointingposeestimatorforgesturalinstructionofamobilerobot
AT andreascheidig monocularpointingposeestimatorforgesturalinstructionofamobilerobot
AT christianmartin monocularpointingposeestimatorforgesturalinstructionofamobilerobot
AT steffenmueler monocularpointingposeestimatorforgesturalinstructionofamobilerobot
AT horstmichaelgross monocularpointingposeestimatorforgesturalinstructionofamobilerobot
AT janricharz monocularpointingposeestimatorforgesturalinstructionofamobilerobot