一种基于表端识别算法的智能摄像水表研究

Research on Smart Camera Water Meter Based on Meter Recognition Algorithm

针对目前人工抄读水表难度大、耗时费力等缺点,基于CJ/T 188-2004行业标准提出了一种基于表端图像识别的智能摄像水表抄表方案。通过在机械水表上安装以STM32为核心的摄像直读模块,采用GC0329芯片采集水表字轮的图片并传输给MCU,利用写入MCU的识别算法将图片数值化,由M-Bus总线通过相应的标准通讯协议将图片和数据传输到上位机进行显示。测试表明,在-20~70℃黑暗环境下,摄像水表的识别率达到99%以上,具有较高的抄表应用价值。

To overcome the current shortcomings of manual water meter reading,such as it is difficult,time-consuming and labor-intensive,a smart camera water meter reading program using meter end image recognition is proposed based on the CJ/T188-2004 sectoral standard.A camera direct reading module with STM32 as the core is installed on the mechanical water meter to use the GC0329 chip to collect the picture of the water meter word wheel and transmit it to the MCU,and then use the recognition algorithm to digitize the picture.The M-Bus bus uses the corresponding communication protocol to the pictures and data are transmitted to the host computer for display.The test shows that the recognition rate of the camera water meter reaches more than 99%in the dark environment of-20℃-70℃,which has high application value for meter reading.