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

Sun, Li and Zhao, Cheng and Yan, Zhi and Liu, Pengcheng and Duckett, Tom and Stolkin, Rustam (2019) A Novel Weakly-supervised approach for RGB-D-based Nuclear Waste Object Detection and Categorization. IEEE Sensors Journal, 19 (9). pp. 3487-3500. ISSN 1530-437X

Full content URL: http://doi.org/10.1109/JSEN.2018.2888815

Documents
A Novel Weakly-supervised approach for RGB-D-based Nuclear Waste Object Detection and Categorization
Accepted Manuscript
[img]
[Download]
[img] PDF
Tom Duckett (002).pdf - Whole Document

5MB
Item Type:Article
Item Status:Live Archive

Abstract

This paper addresses the problem of RGBD-based detection and categorization of
waste objects for nuclear de- commissioning. 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
unavail- able. 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 RGB- D 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.

Keywords:Radioactive pollution, Three-dimensional displays, Proposals, Object detection, Training, Real-time systems, Object recognition
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
ID Code:35699
Deposited On:16 Apr 2019 14:08

Repository Staff Only: item control page