Semantic Web-Mining and Deep Vision for Lifelong Object Discovery - Archive ouverte HAL Access content directly
Conference Papers Year :

Semantic Web-Mining and Deep Vision for Lifelong Object Discovery

(1) , (1) , (2) , (2, 3) , (1) , (4)
1
2
3
4

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.
Fichier principal
Vignette du fichier
young17icra.pdf (99.94 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01524902 , version 1 (19-05-2017)

Identifiers

  • HAL Id : hal-01524902 , version 1

Cite

Jay Young, Lars Kunze, Valerio Basile, Elena Cabrio, Nick Hawes, et al.. Semantic Web-Mining and Deep Vision for Lifelong Object Discovery. IEEE International Conference on Robotics and Automation (ICRA), May 2017, Singapore, Singapore. ⟨hal-01524902⟩
614 View
509 Download

Share

Gmail Facebook Twitter LinkedIn More