• English
    • Welsh
  • English 
    • English
    • Welsh
  • Login
Search DSpace:
  • Home
  • Research at Cardiff Met
  • Library Services
  • Contact Us
View item 
  • DSpace home
  • Cardiff School of Technologies
  • School of Technologies Research
  • View item
  • DSpace home
  • Cardiff School of Technologies
  • School of Technologies Research
  • View item
JavaScript is disabled for your browser. Some features of this site may not work without it.

A Novel Weakly-supervised approach for RGB-D-based Nuclear Waste Object Detection and Categorization

Thumbnail
View/open
Author's post-print (4.957Mb)
Author
Sun, Li
Zhao, Cheng
Yan, Zhi
Liu, Pengcheng
Duckett, Tom
Stolkin, Rustam
Date
2018-12-19
Acceptance date
2018
Type
Article
Publisher
IEEE
ISSN
1530-437X
Metadata
Show full item record
Abstract
This paper addresses the problem of RGBD-based detection and categorization of waste objects for nuclear decommissioning. To enable autonomous robotic manipulation for nuclear decommissioning, nuclear waste objects must be detected and categorized. However, as a novel industrial application, large amounts of annotated waste object data are currently unavailable. To overcome this problem, we propose a weakly-supervised learning approach which is able to learn a deep convolutional neural network (DCNN) from unlabelled RGBD videos while requiring very few annotations. The proposed method also has the potential to be applied to other household or industrial applications. We evaluate our approach on the Washington RGBD object recognition benchmark, achieving the state-of-the-art performance among semi-supervised methods. More importantly, we introduce a novel dataset, i.e. Birmingham nuclear waste simulants dataset, and evaluate our proposed approach on this novel industrial object recognition challenge. We further propose a complete real-time pipeline for RGBD-based detection and categorization of nuclear waste simulants. Our weakly-supervised approach has demonstrated to be highly effective in solving a novel RGB-D object detection and recognition application with limited human annotations.
Journal/conference proceeding
IEEE Sensors Journal;
Citation
Sun, L., Zhao, C., Yan, Z., Liu, P., Duckett, T. and Stolkin, R., 2018. A Novel Weakly-supervised approach for RGB-D-based Nuclear Waste Object Detection and Categorization. IEEE Sensors Journal. https://doi.org/10.1109/JSEN.2018.2888815
URI
http://hdl.handle.net/10369/10234
DOI
https://doi.org/10.1109/JSEN.2018.2888815
Description
Article published in IEEE Sensors Journal, available at https://doi.org/10.1109/JSEN.2018.2888815
Rights
http://www.rioxx.net/licenses/all-rights-reserved
Sponsorship
Cardiff Metropolitan University (Grant ID: Cardiff Metropolian (Internal))
Collections
  • School of Technologies Research [147]

Related items

Showing items related by title, author, subject and abstract.

  • Thumbnail

    Efficient Detection of Anti-Nuclear Antibodies 

    Hole, David (University of Wales Institute Cardiff, 2012)
    A progressively wide range of studies exist into the association of Anti-Nuclear Antibodies (ANAs) with Autoimmune Rheumatic Diseases (ARDS), such as Systemic Lupus Erythematosus (SLE), Sjogrens Syndrome (SjS), Systemic ...
  • Thumbnail

    Low-intensity exercise enhances expression of markers of alternative activation in circulating leukocytes: Roles of PPARy and Th2 cytokines 

    Yakeu, G.; Butcher, Lee; Isa, S.A.; Webb, Richard; Roberts, Aled W.; Thomas, Andrew; Backx, Karianne; James, Philip; Morris, Keith (Elsevier, 2010)
    Objective: Pharmacological activation of the nuclear receptor PPAR is linked to numerous beneficial effects in the contexts of inflammation, lipid homeostasis, Type-2 Diabetes (T2D) and atherosclerosis. These beneficial ...
  • Thumbnail

    Detection of breast cancer susceptibility: Gene 1 (BRCA1) using optimal conditions of Polymerase Chain Reaction (PCR) 

    Al Rahbi, Zakiya Amer Said (Cardiff Metropolitan University, 2011)
    Background: BRCA1 is a tumor suppressor that functions in controlling cell growth, maintaining genomic stability and has been linked to early-onset breast and ovarian cancer. The human BRCA1 gene comprises 24 exons and ...

Browse

DSpace at Cardiff MetCommunities & CollectionsBy issue dateAuthorsTitlesSubjectsThis collectionBy issue dateAuthorsTitlesSubjects

My Account

Login

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors

DSpace software copyright © 2002-2015  DuraSpace
Contact us | Send feedback | Administrator