The Open UniversitySkip to content
 

Task-Agnostic Object Recognition for Mobile Robots through Few-Shot Image Matching

Chiatti, Agnese; Bardaro, Gianluca; Bastianelli, Emanuele; Tiddi, Ilaria; Mitra, Prasenjit and Motta, Enrico (2020). Task-Agnostic Object Recognition for Mobile Robots through Few-Shot Image Matching. Electronics, 9(3), article no. 380.

Full text available as:
[img]
Preview
PDF (Version of Record) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (341kB) | Preview
DOI (Digital Object Identifier) Link: https://doi.org/10.3390/electronics9030380
Google Scholar: Look up in Google Scholar

Abstract

To assist humans with their daily tasks, mobile robots are expected to navigate complex and dynamic environments, presenting unpredictable combinations of known and unknown objects. Most state-of-the-art object recognition methods are unsuitable for this scenario because they require that: (i) all target object classes are known beforehand, and (ii) a vast number of training examples is provided for each class. This evidence calls for novel methods to handle unknown object classes, for which fewer images are initially available (few-shot recognition). One way of tackling the problem is learning how to match novel objects to their most similar supporting example. Here, we compare different (shallow and deep) approaches to few-shot image matching on a novel data set, consisting of 2D views of common object types drawn from a combination of ShapeNet and Google. First, we assess if the similarity of objects learned from a combination of ShapeNet and Google can scale up to new object classes, i.e., categories unseen at training time. Furthermore, we show how normalising the learned embeddings can impact the generalisation abilities of the tested methods, in the context of two novel configurations: (i) where the weights of a Convolutional two-branch Network are imprinted and (ii) where the embeddings of a Convolutional Siamese Network are L2-normalised.

Item Type: Journal Item
Copyright Holders: 2020 The Authors
ISSN: 2079-9292
Project Funding Details:
Funded Project NameProject IDFunding Body
SciRoc780086European Union Horizon 2020
Keywords: few-shot object recognition; image matching; robotics
Academic Unit/School: Faculty of Science, Technology, Engineering and Mathematics (STEM) > Knowledge Media Institute (KMi)
Faculty of Science, Technology, Engineering and Mathematics (STEM)
Item ID: 69496
Depositing User: Agnese Chiatti
Date Deposited: 04 Mar 2020 13:49
Last Modified: 15 Mar 2020 12:41
URI: http://oro.open.ac.uk/id/eprint/69496
Share this page:

Metrics

Altmetrics from Altmetric

Citations from Dimensions

Download history for this item

These details should be considered as only a guide to the number of downloads performed manually. Algorithmic methods have been applied in an attempt to remove automated downloads from the displayed statistics but no guarantee can be made as to the accuracy of the figures.

Actions (login may be required)

Policies | Disclaimer

© The Open University   contact the OU