How to get accurate results?
Get accurate webcam eye-tracking results with simple setup tips for lighting, positioning, and stability.
Getting reliable results from webcam-based eye-tracking is simple when you follow a few key setup tips. These small adjustments can make a big difference in accuracy and data quality.
TL;DR: Watch this short video for a quick overview of how to set up your testing environment for optimal accuracy :-)
To get the best results from webcam eye-tracking, follow these recommendations:
-
The webcam MUST be mounted on the screen that displays the stimuli in case of Desktops and Laptops. For Smartphones and Tablets, the front-facing camera MUST be used.
-
The webcam image MUST be steady - ensure the setup does not shake. For example, avoid placing a laptop on your knees / moving or carrying your devices.
-
The panelist MUST sit directly in front of the webcam. The webcam SHOULD be positioned slightly below the panelist’s eye level.
-
There MUST be only one face visible to the webcam.
-
The panelist’s eyes MUST be clearly visible in the webcam video. Their face SHOULD take up at least one-third of the webcam frame. Panelists are advised NOT TO wear glasses if possible. If worn, glasses MUST NOT block the pupils or reflect light in a way that interferes with tracking.
-
The panelist SHOULD sit comfortably and SHOULD try to keep their head still. Using a chair with a headrest is recommended.
- The panelist’s face SHOULD be well-lit. Lighting SHOULD NOT change during the test.
- Make sure Hardware & Software requirements are met.
🎯Expected Accuracy
The Accuracy means how close the system’s prediction is to the actual point on the screen where a person is looking. To evaluate the Accuracy of RealEye on Computers and Smartphones, we performed a validation study that involved grid-based tasks - learn more in our Whitepaper.
The results of the study showed that the average accuracy on Computers ≈ 106 pixels, and the average accuracy on Smartphones ≈ 56 pixels.
This indicates that RealEye performs reliably across a wide range of environments and user setups, making it a practical solution for remote eye-tracking research. Check out Who can benefit from RealEye?
💌 If you have any further questions, feel free to reach out to our team at support@realeye.io