期刊
IEEE SENSORS JOURNAL
卷 19, 期 9, 页码 3487-3500出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSEN.2018.2888815
关键词
Nuclear waste detection and categorization; nuclear waste decommissioning; autonomous waste sorting and segregation
资金
- EU Project H2020 RoMaNS [645582]
- EPSRC [EP/M026477/1, EP/P017487/1, EP/R02572X/1]
- DISTINCTIVE - a university consortium - Research Councils U.K. Energy Program
- Royal Society Industry Fellowship
- National Natural Science Foundation of China [61803396]
- EU Project CHIST-ERA (Perception-Guided Robotic Grasping)
- EU [H2020 ILIAD 732737]
- EPSRC [EP/P017487/1, EP/M026477/1, EP/R02572X/1] Funding Source: UKRI
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 he 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 from unlabeled 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-theart 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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据