The Eye Tribe

Hi,

How is calculted the:

Accuracy Accuracy
MeanError MeanError
Point2D MeanEstimatedCoords
StandardDeviation StandardDeviation

of each CalibrationPoint in CalibrationResult? I want to represent graphically the error of each calibration point but do not know what the parameters mean.

I asume you are using the C# SDK. The values of the CalibrationResult is automatically populated by the SDK once you have successfully completed a calibration process. The object you recieve through ICalibrationProcessHandler.OnCalibrationResult() or using GazeManager.LastCalibrationResult when the system is calibrated is what you need. Have a look at the open source C# samples for an example of how this is done.

Thanks Anders.

Yes, I'm using the C# SDK. I know how to use the libraries, but I want to know more about the concepts of the metrics. I'm comparing several eyetrackers and I want to know more about the way that the different metrics are calculated.

For instance, the AverageErrorDegree is expressed in degrees, but how is this done without the value of the distance between the eyetracker and the user?

For instance, the AverageErrorDegree is expressed in degrees, but how is this done without the value of the distance between the eyetracker and the user?

I am afraid that we do not share information related to the internal tracking and estimation algorithms of our system.

Should you want to compare to other trackers, I suggest you do so using the same distances and write a test program that cashes both average error and distance between gaze point and estimated gaze.