Semantic web-mining and deep vision for lifelong object discovery

Jay Young; Lars Kunze; Valerio  Basile; Elena  Cabrio; Nicholas Hawes; Barbara  Caputo

doi:10.1109/ICRA.2017.7989323

Semantic web-mining and deep vision for lifelong object discovery

Jay Young, Lars Kunze, Valerio Basile, Elena Cabrio, Nicholas Hawes, Barbara Caputo

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

13 Citations (Scopus)

243 Downloads (Pure)

Abstract

Autonomous robots that are to assist humans in their daily lives must recognize and understand the meaning of objects in their environment. However, the open nature of the world means robots must be able to learn and extend their knowledge about previously unknown objects on-line. In this work we investigate the problem of unknown object hypotheses generation, and employ a semantic Web-mining framework along with deep-learning-based object detectors. This allows us to make use of both visual and semantic features in combined hypotheses generation. Experiments on data from mobile robots in real world application deployments show that this combination improves performance over the use of either method in isolation.

Original language	English
Title of host publication	2017 IEEE International Conference on Robotics and Automation (ICRA)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	2774-2779
Number of pages	6
ISBN (Electronic)	9781509046331
ISBN (Print)	9781509046348 (PoD)
DOIs	https://doi.org/10.1109/ICRA.2017.7989323
Publication status	Published - 24 Jul 2017
Event	2017 IEEE International Conference on Robotics and Automation (ICRA 2017) - Singapore Duration: 29 May 2017 → 3 Jun 2017

Conference

Conference	2017 IEEE International Conference on Robotics and Automation (ICRA 2017)
City	Singapore
Period	29/05/17 → 3/06/17

Keywords

Semantics
Knowledge based systems
Three-dimensional displays
Visualization
Mobile robots
Service robots

Access to Document

10.1109/ICRA.2017.7989323Licence: None: All rights reserved

J_Young_et_al_Semantic_web-mining_and_deep_vision_ICRA_2017_2017
Checked for eligibility: 03/03/2017 © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. J. Young, L. Kunze, V. Basile, E. Cabrio, N. Hawes and B. Caputo, "Semantic web-mining and deep vision for lifelong object discovery," 2017 IEEE International Conference on Robotics and Automation (ICRA), Singapore, 2017, pp. 2774-2779. doi: 10.1109/ICRA.2017.7989323
Accepted author manuscript, 228 KBLicence: Other (please specify with Rights Statement)

https://ieeexplore.ieee.org/document/7989323/Licence: None: All rights reserved

Cite this

@inproceedings{dab0c8b0903f49349ea25a4941f687eb,

title = "Semantic web-mining and deep vision for lifelong object discovery",

abstract = "Autonomous robots that are to assist humans in their daily lives must recognize and understand the meaning of objects in their environment. However, the open nature of the world means robots must be able to learn and extend their knowledge about previously unknown objects on-line. In this work we investigate the problem of unknown object hypotheses generation, and employ a semantic Web-mining framework along with deep-learning-based object detectors. This allows us to make use of both visual and semantic features in combined hypotheses generation. Experiments on data from mobile robots in real world application deployments show that this combination improves performance over the use of either method in isolation.",

keywords = "Semantics, Knowledge based systems, Three-dimensional displays, Visualization, Mobile robots, Service robots",

author = "Jay Young and Lars Kunze and Valerio Basile and Elena Cabrio and Nicholas Hawes and Barbara Caputo",

year = "2017",

month = jul,

day = "24",

doi = "10.1109/ICRA.2017.7989323",

language = "English",

isbn = "9781509046348 (PoD)",

pages = "2774--2779",

booktitle = "2017 IEEE International Conference on Robotics and Automation (ICRA)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

note = "2017 IEEE International Conference on Robotics and Automation (ICRA 2017) ; Conference date: 29-05-2017 Through 03-06-2017",

}

Young, J, Kunze, L, Basile, V, Cabrio, E, Hawes, N & Caputo, B 2017, Semantic web-mining and deep vision for lifelong object discovery. in 2017 IEEE International Conference on Robotics and Automation (ICRA). Institute of Electrical and Electronics Engineers (IEEE), pp. 2774-2779, 2017 IEEE International Conference on Robotics and Automation (ICRA 2017), Singapore, 29/05/17. https://doi.org/10.1109/ICRA.2017.7989323

TY - GEN

T1 - Semantic web-mining and deep vision for lifelong object discovery

AU - Young, Jay

AU - Kunze, Lars

AU - Basile, Valerio

AU - Cabrio, Elena

AU - Hawes, Nicholas

AU - Caputo, Barbara

PY - 2017/7/24

Y1 - 2017/7/24

N2 - Autonomous robots that are to assist humans in their daily lives must recognize and understand the meaning of objects in their environment. However, the open nature of the world means robots must be able to learn and extend their knowledge about previously unknown objects on-line. In this work we investigate the problem of unknown object hypotheses generation, and employ a semantic Web-mining framework along with deep-learning-based object detectors. This allows us to make use of both visual and semantic features in combined hypotheses generation. Experiments on data from mobile robots in real world application deployments show that this combination improves performance over the use of either method in isolation.

AB - Autonomous robots that are to assist humans in their daily lives must recognize and understand the meaning of objects in their environment. However, the open nature of the world means robots must be able to learn and extend their knowledge about previously unknown objects on-line. In this work we investigate the problem of unknown object hypotheses generation, and employ a semantic Web-mining framework along with deep-learning-based object detectors. This allows us to make use of both visual and semantic features in combined hypotheses generation. Experiments on data from mobile robots in real world application deployments show that this combination improves performance over the use of either method in isolation.

KW - Semantics

KW - Knowledge based systems

KW - Three-dimensional displays

KW - Visualization

KW - Mobile robots

KW - Service robots

U2 - 10.1109/ICRA.2017.7989323

DO - 10.1109/ICRA.2017.7989323

M3 - Conference contribution

SN - 9781509046348 (PoD)

SP - 2774

EP - 2779

BT - 2017 IEEE International Conference on Robotics and Automation (ICRA)

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 2017 IEEE International Conference on Robotics and Automation (ICRA 2017)

Y2 - 29 May 2017 through 3 June 2017

ER -

Semantic web-mining and deep vision for lifelong object discovery

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this