One-Shot Object Localization Using Learnt Visual Cues via Siamese Networks

Venkatesh, SG and Amrutur, B (2019) One-Shot Object Localization Using Learnt Visual Cues via Siamese Networks. In: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019, 3-8 Nov. 2019, Macau, China,, pp. 6700-6705.

PDF IEEE_RSJ_INT_CON_INT_ROB_SYS_6700-6705_2019.pdf - Published Version Restricted to Registered users only Download (2MB) | Request a copy

Abstract

A robot that can operate in novel and unstructured environments must be capable of recognizing new, previously unseen, objects. In this work, a visual cue is used to specify a novel object of interest which must be localized in new environments. An end-to-end neural network equipped with a Siamese network is used to learn the cue, infer the object of interest, and then to localize it in new environments. We show that a simulated robot can pick-and-place novel objects pointed to by a laser pointer. We also evaluate the performance of the proposed approach on a dataset derived from the Omniglot handwritten character dataset and on a small dataset of toys. © 2019 IEEE.

Item Type:	Conference Paper
Publication:	IEEE International Conference on Intelligent Robots and Systems
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	cited By 0; Conference of 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019 ; Conference Date: 3 November 2019 Through 8 November 2019; Conference Code:157163
Keywords:	End to end; Hand-written characters; Laser pointer; Object localization; Pick and place; Simulated robot; Unstructured environments; Visual cues, Intelligent robots
Department/Centre:	Division of Electrical Sciences > Electrical Communication Engineering
Date Deposited:	03 Sep 2020 11:33
Last Modified:	03 Sep 2020 11:33
URI:	http://eprints.iisc.ac.in/id/eprint/64911

Actions (login required)

View Item