BV-Net: Bin-based Vector-predicted Network for tubular solder joint detection
文献类型:期刊论文
作者 | Zhou, Chenlin1,2; Shen, Xiaofei1,2; Wang, Peng1,2,3; Wei, Wei1,2; Sun, Jia1; Luo, Yongkang1; Li, Yiming1,2 |
刊名 | MEASUREMENT |
出版日期 | 2021-10-01 |
卷号 | 183页码:8 |
ISSN号 | 0263-2241 |
关键词 | Object detection Defect detection Quality inspection Tubular solder joint detection Deep learning |
DOI | 10.1016/j.measurement.2021.109821 |
通讯作者 | Wang, Peng(peng_wang@ia.ac.cn) |
英文摘要 | Tubular solder joint detection is an important and challengeable issue in industry, due to the small objects, rarely collected datasets and real-time and high precision requirements. Traditional methods on defect detection cannot solve tubular solder joint detection due to lacking of angle estimation. In this paper, we propose a tubular solder joint detection method named Bin-based Vector-predicted Network (BV-Net), which combines the framework of state-of-the-art deep-learning-based object detector (YOLOv4) with specific characteristics and requirements of tubular solder joint detection. BV-Net could effectively estimate both the center point and the direction of tubular solder joints. Firstly, To regress the center point, we propose a Circle-based Distance-Intersection over Union (CirDIoU) loss, which gets better learning performance for the center point of tubular solder joint than Distance-Intersection over Union (DIOU) loss. Secondly, to estimate the direction, we introduce a bin-based angle regression method, which transforms a regression task into a classification and regression task, improving the precision of direction estimation greatly. Thirdly, we establish a tubular solder joint dataset and design a new evaluation index: mAP (delta(d), delta(O)) for tubular solder joint detection, combining the relative deviation of center point positioning od and the relative deviation of angle regression delta(theta). Finally, comparison experiments on the dataset are carried out. BV-Net achieved 85.5% mAP (0.5%, 3%) with 34.4 FPS, meeting the requirements of industrial system. In direction estimation, bin-based angle regression method promotes 4.3% mAP (-, 3%), compared with the baseline. In center point positioning, BV-Net outperforms YOLOv4 by an improvement of 0.4% mAP (0.5%,-). The experimental results verified the effectiveness of our method. |
资助项目 | National Natural Science Foundation of China[91748131] ; National Natural Science Foundation of China[62006229] ; National Natural Science Foundation of China[61771471] ; Beijing Municipal Natural Science Foundation, China[4204113] ; Strategic Priority Research Program of Chinese Academy of Science[XDB32050100] |
WOS研究方向 | Engineering ; Instruments & Instrumentation |
语种 | 英语 |
出版者 | ELSEVIER SCI LTD |
WOS记录号 | WOS:000692592600002 |
资助机构 | National Natural Science Foundation of China ; Beijing Municipal Natural Science Foundation, China ; Strategic Priority Research Program of Chinese Academy of Science |
源URL | [http://ir.ia.ac.cn/handle/173211/46007] |
专题 | 智能机器人系统研究 |
通讯作者 | Wang, Peng |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 3.Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai, Peoples R China |
推荐引用方式 GB/T 7714 | Zhou, Chenlin,Shen, Xiaofei,Wang, Peng,et al. BV-Net: Bin-based Vector-predicted Network for tubular solder joint detection[J]. MEASUREMENT,2021,183:8. |
APA | Zhou, Chenlin.,Shen, Xiaofei.,Wang, Peng.,Wei, Wei.,Sun, Jia.,...&Li, Yiming.(2021).BV-Net: Bin-based Vector-predicted Network for tubular solder joint detection.MEASUREMENT,183,8. |
MLA | Zhou, Chenlin,et al."BV-Net: Bin-based Vector-predicted Network for tubular solder joint detection".MEASUREMENT 183(2021):8. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
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。