Few-shot learning approach for 3D defect detection in lithium battery | |
Wu,Ke1,2; Tan,Jie1; Li,Jingwei1,2; Liu,Chengbao1 | |
刊名 | Journal of Physics: Conference Series |
2021-04-01 | |
卷号 | 1884期号:1 |
ISSN号 | 1742-6588 |
DOI | 10.1088/1742-6596/1884/1/012024 |
英文摘要 | Abstract Detecting the surface defects in a lithium battery with an aluminium/steel shell is a difficult task. The effect of reflectivity, the limitation of acquiring the 3D information, and the shortage of massive amounts of labelled training data make the 2D detection method hard to classify surface defects. In this work, a few-shot learning approach for 3D defect detection in lithium batteries is proposed. The multi-exposure-based structured light method is introduced to reconstruct the 3D shape of the lithium battery. Then, the anomaly part of the 3D point cloud is transferred into 2D images by the height-gray transformation. The MiniImageNet datasets are used as the source domain to pretrain the Cross-Domain Few-Shot Learning (CD-FSL) model. The accuracy in our experiment result is 97.17%, which means that our method can be used to classify the surface defects of the lithium battery. |
语种 | 英语 |
出版者 | IOP Publishing |
WOS记录号 | IOP:1742-6588-1884-1-012024 |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/44284] |
专题 | 综合信息系统研究中心_工业智能技术与系统 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences, Beijing, China 2.School of artificial intelligence, University of Chinese Academy of Sciences, Beijing, China |
推荐引用方式 GB/T 7714 | Wu,Ke,Tan,Jie,Li,Jingwei,et al. Few-shot learning approach for 3D defect detection in lithium battery[J]. Journal of Physics: Conference Series,2021,1884(1). |
APA | Wu,Ke,Tan,Jie,Li,Jingwei,&Liu,Chengbao.(2021).Few-shot learning approach for 3D defect detection in lithium battery.Journal of Physics: Conference Series,1884(1). |
MLA | Wu,Ke,et al."Few-shot learning approach for 3D defect detection in lithium battery".Journal of Physics: Conference Series 1884.1(2021). |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论