Interest-point-based landmark computation for agents’ spatial description coordination

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In applications involving multiple conversational agents, each of these agents has its own view of a visual scene, and thus all the agents must establish common visual landmarks in order to coordinate their space understanding and to coherently share generated spatial descriptions of this scene. Whereas natural language processing approaches contribute to define the common ground through dialogues between these agents, we propose in this paper a computer-vision system to determine the object of reference for both agents efficiently and automatically. Our approach consists in processing each agent's view by computing the related, visual interest points, and then by matching them in order to extract the salient and meaningful landmark. Our approach has been successfully tested on real-world data, and its performance and design allow its use for embedded robotic system communication.
Original languageEnglish
Title of host publicationProceedings of the 8th International Conference on Agents and Artificial Intelligence
Subtitle of host publicationICAART
PublisherSciTePress
Pages566-569
Number of pages4
Volume2
ISBN (Print)978-989-758-172-4
DOIs
Publication statusPublished - 2016
Externally publishedYes

Fingerprint

Processing
Computer vision
Robotics
Communication

Keywords

  • Qualitative Spatial Reasoning
  • Object Detention
  • Local Feature Descriptors
  • Feature Extraction
  • Visual Scene Understanding
  • Automated Image Annotation
  • Robotics
  • Autonomic Agents

Cite this

Olszewska, J. I. (2016). Interest-point-based landmark computation for agents’ spatial description coordination. In Proceedings of the 8th International Conference on Agents and Artificial Intelligence: ICAART (Vol. 2, pp. 566-569). SciTePress. https://doi.org/10.5220/0005847705660569
Olszewska, J.I. / Interest-point-based landmark computation for agents’ spatial description coordination. Proceedings of the 8th International Conference on Agents and Artificial Intelligence: ICAART. Vol. 2 SciTePress, 2016. pp. 566-569
@inproceedings{56fded645aeb4ac88c96735ba90a2328,
title = "Interest-point-based landmark computation for agents’ spatial description coordination",
abstract = "In applications involving multiple conversational agents, each of these agents has its own view of a visual scene, and thus all the agents must establish common visual landmarks in order to coordinate their space understanding and to coherently share generated spatial descriptions of this scene. Whereas natural language processing approaches contribute to define the common ground through dialogues between these agents, we propose in this paper a computer-vision system to determine the object of reference for both agents efficiently and automatically. Our approach consists in processing each agent's view by computing the related, visual interest points, and then by matching them in order to extract the salient and meaningful landmark. Our approach has been successfully tested on real-world data, and its performance and design allow its use for embedded robotic system communication.",
keywords = "Qualitative Spatial Reasoning, Object Detention, Local Feature Descriptors, Feature Extraction, Visual Scene Understanding, Automated Image Annotation, Robotics, Autonomic Agents",
author = "J.I. Olszewska",
year = "2016",
doi = "10.5220/0005847705660569",
language = "English",
isbn = "978-989-758-172-4",
volume = "2",
pages = "566--569",
booktitle = "Proceedings of the 8th International Conference on Agents and Artificial Intelligence",
publisher = "SciTePress",
address = "Portugal",

}

Olszewska, JI 2016, Interest-point-based landmark computation for agents’ spatial description coordination. in Proceedings of the 8th International Conference on Agents and Artificial Intelligence: ICAART. vol. 2, SciTePress, pp. 566-569. https://doi.org/10.5220/0005847705660569

Interest-point-based landmark computation for agents’ spatial description coordination. / Olszewska, J.I.

Proceedings of the 8th International Conference on Agents and Artificial Intelligence: ICAART. Vol. 2 SciTePress, 2016. p. 566-569.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Interest-point-based landmark computation for agents’ spatial description coordination

AU - Olszewska, J.I.

PY - 2016

Y1 - 2016

N2 - In applications involving multiple conversational agents, each of these agents has its own view of a visual scene, and thus all the agents must establish common visual landmarks in order to coordinate their space understanding and to coherently share generated spatial descriptions of this scene. Whereas natural language processing approaches contribute to define the common ground through dialogues between these agents, we propose in this paper a computer-vision system to determine the object of reference for both agents efficiently and automatically. Our approach consists in processing each agent's view by computing the related, visual interest points, and then by matching them in order to extract the salient and meaningful landmark. Our approach has been successfully tested on real-world data, and its performance and design allow its use for embedded robotic system communication.

AB - In applications involving multiple conversational agents, each of these agents has its own view of a visual scene, and thus all the agents must establish common visual landmarks in order to coordinate their space understanding and to coherently share generated spatial descriptions of this scene. Whereas natural language processing approaches contribute to define the common ground through dialogues between these agents, we propose in this paper a computer-vision system to determine the object of reference for both agents efficiently and automatically. Our approach consists in processing each agent's view by computing the related, visual interest points, and then by matching them in order to extract the salient and meaningful landmark. Our approach has been successfully tested on real-world data, and its performance and design allow its use for embedded robotic system communication.

KW - Qualitative Spatial Reasoning

KW - Object Detention

KW - Local Feature Descriptors

KW - Feature Extraction

KW - Visual Scene Understanding

KW - Automated Image Annotation

KW - Robotics

KW - Autonomic Agents

U2 - 10.5220/0005847705660569

DO - 10.5220/0005847705660569

M3 - Conference contribution

SN - 978-989-758-172-4

VL - 2

SP - 566

EP - 569

BT - Proceedings of the 8th International Conference on Agents and Artificial Intelligence

PB - SciTePress

ER -

Olszewska JI. Interest-point-based landmark computation for agents’ spatial description coordination. In Proceedings of the 8th International Conference on Agents and Artificial Intelligence: ICAART. Vol. 2. SciTePress. 2016. p. 566-569 https://doi.org/10.5220/0005847705660569