Measuring the utility consumption of end users is one of the principal processes for every utility provider. Yet, the technology for “smart” electricity, gas, water or heat consumption metering is still immature and it’s roll out is therefore slow. The meters must be changed one by one and that process would take years even in the most tech-savvy utility companies before a complete transition from the traditional analogue meters would be complete.
Until then, companies have to read those analogue meters manually and that is a costly task that encompasses weeks of unnecessary labor. Reading the digits, writing down the consumption and the meter ID by hand, transferring it into Excel sheets and consequently feeding it to CRM systems, is a slow and cumbersome process prone to error and often subject to fraud.
Together with the partner company ISDD, Cognexa analyzed the workflow of meter-reading crews to develop a mobile application that makes the entire process-chain exponentially more efficient and convenient.
The previously cumbersome chain of tasks got reduced to one single and easy step: taking a picture of the meter. Our OCR technology locates the meter display, reads the digits and sends them directly to the utility provider’s CRM system once an Internet connection is available.
The reading itself is carried out offline, which solves the problem of poor Internet signal in the underground pits. Fraud prevention mechanisms include analysis of GPS location and a timestamp of the photo, plus a reference point containing each meter’s past values. The application automatically alerts the measurer, when photos is too blurred or otherwise unreadable.
For a detailed description of the use case please visit: https://www.cognexa.com/visual-metering
The development of the application has been successfully completed in 2018 and since it has been deployed by a major utility company in Slovakia. It has full-filled the expectations of our partners to increase the work efficiency of the meter-reading crews and overall satisfaction of all parties involved.
Furthermore, as the solution supports automated archiving of the measurement and it's verification, trust element between all the stakeholders has also increased.
Offline mobile deep learning app for seamless water meter reading
3 months to fully functional Android app
TensorFlow, Python, Java, Android, CxFlow, OpenCV