Image-Based Automatic Watermeter Reading under Challenging Environments.
Image-Based Automatic Watermeter Reading under Challenging Environments.
复制标题
DOI：
10.3390/s21020434
复制
发表时间：
2021-01-09
期刊：
影响因子：
--
通讯作者：
Zeng M
中科院分区：
文献类型：
--
作者：
Hong Q;Ding Y;Lin J;Wang M;Wei Q;Wang X;Zeng M
随着人工智能和第五代移动的网络技术的快速发展，仪器自动阅读成为智慧城市中智能传感器越来越重要的课题。我们提出了一个基于单张图像的全流水线自动抄表，利用深度学习方法为智能水表阅读提供新的技术支持。为了应对水表所在的各种具有挑战性的环境，我们的管道将任务分解为基于典型水表结构的单个子任务。这些子任务包括组件定位、方向对齐、空间布局引导阅读和基于回归的指针阅读。所设计的算法的方向对齐和空间布局指导量身定制，以提高我们的神经网络的鲁棒性。我们还收集了真实的场景中的水表图像，并构建了一个用于训练和评估的数据集。实验结果表明，该方法的有效性，即使在具有挑战性的环境下，不同的照明，遮挡，和不同的方向。由于我们的管道中采用了轻量级算法，该系统可以轻松部署并完全自动化。
With the rapid development of artificial intelligence and fifth-generation mobile network technologies, automatic instrument reading has become an increasingly important topic for intelligent sensors in smart cities. We propose a full pipeline to automatically read watermeters based on a single image, using deep learning methods to provide new technical support for an intelligent water meter reading. To handle the various challenging environments where watermeters reside, our pipeline disentangled the task into individual subtasks based on the structures of typical watermeters. These subtasks include component localization, orientation alignment, spatial layout guidance reading, and regression-based pointer reading. The devised algorithms for orientation alignment and spatial layout guidance are tailored to improve the robustness of our neural network. We also collect images of watermeters in real scenes and build a dataset for training and evaluation. Experimental results demonstrate the effectiveness of the proposed method even under challenging environments with varying lighting, occlusions, and different orientations. Thanks to the lightweight algorithms adopted in our pipeline, the system can be easily deployed and fully automated.
登录
查看更多内容
影响因子：
19.5
作者：
Everingham, Mark;Eslami, S. M. Ali;Zisserman, Andrew
通讯作者：
Zisserman, Andrew
影响因子：
2.9
作者：
LeCun, Y.;Boser, B.;Jackel, L. D.
通讯作者：
Jackel, L. D.
影响因子：
1.1
作者：
Laroca, Rayson;Barroso, Victor;Menotti, David
通讯作者：
Menotti, David
影响因子：
3.9
作者：
Li, Xue Jun;Chong, Peter Han Joo
通讯作者：
Chong, Peter Han Joo