Knowledge Commons of Institute of Automation,CAS
Key point localization and recurrent neural network based water meter reading recognition | |
Jiguang Zhang1; Wenrui Liu1; Shibiao Xu2; Xiaopeng Zhang1 | |
发表期刊 | Displays |
2022 | |
卷号 | 74期号:2022页码:0-0 |
摘要 | Due to the complicated arrangement of the pipes in the narrow space leads to random orientation of the mechanical water meter dial meanwhile its digit wheels are accompanied by arbitrary angle rotation, which makes the detection and recognition of meter reading more difficult. Even the latest visual network technology cannot deal with the challenges. In this paper, two special visual task networks are being closely cooperated to solve above issues. First, a professional water meter detection method is proposed by redesigning and retraining a human joints detection network to accurately locate four key points of reading region. Based on key points the distorted reading region will be geometric corrected by using homography relation to reduce the interference from shooting angle and improve accuracy of subsequent digit recognition. Then, a water meter reading recognition method is proposed by modifying a recurrent block convolutional network. The robustness of digit recognition is improved by block recognition and transcription of reading region features. During transcription stage, we add new recognition markers and probability vectors between each digit in dictionary to solve the issue of digit wheels rotations. Finally, our method achieves more robust water meter detection in harsh environment and higher recognition accuracy. Experimental results showed that our method can get better performance in detection efficiency (6.15 fps) and accuracy (95.30%) compared with recent related works and closer to the level of practical application. |
关键词 | Mechanical water meters reading Reading region detection Digit wheels recognition Key point location Recurrent convolutional network |
收录类别 | SCI |
语种 | 英语 |
七大方向——子方向分类 | 模式识别基础 |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/47562 |
专题 | 多模态人工智能系统全国重点实验室_三维可视计算 |
通讯作者 | Shibiao Xu |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, Beijing University of Posts and Telecommunications |
推荐引用方式 GB/T 7714 | Jiguang Zhang,Wenrui Liu,Shibiao Xu,et al. Key point localization and recurrent neural network based water meter reading recognition[J]. Displays,2022,74(2022):0-0. |
APA | Jiguang Zhang,Wenrui Liu,Shibiao Xu,&Xiaopeng Zhang.(2022).Key point localization and recurrent neural network based water meter reading recognition.Displays,74(2022),0-0. |
MLA | Jiguang Zhang,et al."Key point localization and recurrent neural network based water meter reading recognition".Displays 74.2022(2022):0-0. |
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 | ||
Key point localizati(4271KB) | 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