Regresar

Calibration of residential water meters by using computer vision

Abstract:

We present an artificial vision based system that quickly and semi-automatically calibrates water meters. The system operates with an artificial neural net architecture which is able to visually read analog needles and dynamically track the float position of a lab rotameter. By using a closed water flow circuit powered by a low power centrifugal pump, the computer reads through a web camera the water meter needles position, measuring the time required for a full turn and calculating the associated water flow. Simultaneously a second camera tracks the float of a rotameter connected to the water circuit and digitalizes the indicated flow. The two amounts are compared by using column indicators, telling the operator to correct the water meter by excess or defect if necessary. The system has been tested in real time and with real instruments.