A Trajectory-based Attention Model for Sequential Impurity Detection | |
Wenhao He; Haitao Song; Yue Guo; Xiaonan Wang; Guibin Bian; Kui Yuan | |
发表期刊 | Neurocomputing |
ISSN | 0925-2312 |
2020 | |
卷号 | 410期号:410页码:271-283 |
通讯作者 | Guo, Yue(guoyue2013@ia.ac.cn) |
摘要 | Impurity detection involves detecting small impurities in the liquid inside an opaque glass bottle with complex textures by looking through the bottleneck. Sometimes experts have to observe continuous frames to determine the existence of an impurity. In recent years, region-based convolutional neural networks have gained incremental successes in common object detection tasks. However, sequential impurity detections present more challenging issues than detecting targets in a single frame, because consecutive motions and appearance changes of impurities cannot be captured using those common object detectors. In this paper, we propose a simple and controllable ensemble architecture to alleviate this problem. Specifically, a siamese fusion network is used to generate impurity proposals, then an attention model based on visual features and trajectories is proposed to localize a unique region proposal in each frame, finally, a sequential region proposal classifier using a long-term recurrent convolutional network is applied to refine impurity detection performances. The proposed method achieves 79.81%mAP on IML-DET datasets, outperforming a comparable state-of-the-art Mask R-CNN model. |
关键词 | Impurity detection Siamese fusion network Trajectory-based attention model Sequential region proposal classification |
DOI | 10.1016/j.neucom.2020.06.008 |
关键词[WOS] | NETWORKS |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Key R&D Program of China[2018YFB1306300] ; National Natural Science Foundation (NNSF) of China[61421004] |
项目资助者 | National Key R&D Program of China ; National Natural Science Foundation (NNSF) of China |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000579799300023 |
出版者 | ELSEVIER |
七大方向——子方向分类 | 人工智能+制造 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40609 |
专题 | 智能制造技术与系统研究中心_多维数据分析(彭思龙)-技术团队 |
通讯作者 | Yue Guo |
作者单位 | 中国科学院自动化研究所 |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Wenhao He,Haitao Song,Yue Guo,et al. A Trajectory-based Attention Model for Sequential Impurity Detection[J]. Neurocomputing,2020,410(410):271-283. |
APA | Wenhao He,Haitao Song,Yue Guo,Xiaonan Wang,Guibin Bian,&Kui Yuan.(2020).A Trajectory-based Attention Model for Sequential Impurity Detection.Neurocomputing,410(410),271-283. |
MLA | Wenhao He,et al."A Trajectory-based Attention Model for Sequential Impurity Detection".Neurocomputing 410.410(2020):271-283. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
1-s2.0-S092523122030(2153KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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