In this work, we aim at realizing an eye tracker functionality on an off-the-shelf low cost web-camera. In particular, we address the problem of appearance gaze estimation employing deep learning methods for solving the regression task of predicting the point of gaze on a display. This solution is validated using a commercial infrared eye tracker: we achieve 73.843 Root Mean Square Error (RMSE) in pixels between the predictions. The proposed solution outperforms a relevant web-cam solution in terms of pixel-normalized RMSE 0.022 against 0.116 within the carried out comparative study, respectively.
Real-time Appearance-based Gaze Estimation via Web-Camera / Ligostaev, N.; Conci, N.; Passerone, R.; Somov, A.. - ELETTRONICO. - (2025), pp. 1-6. ( 2025 IEEE International Instrumentation and Measurement Technology Conference, I2MTC 2025 deu 2025) [10.1109/I2MTC62753.2025.11079227].
Real-time Appearance-based Gaze Estimation via Web-Camera
Conci N.;Passerone R.;Somov A.
2025-01-01
Abstract
In this work, we aim at realizing an eye tracker functionality on an off-the-shelf low cost web-camera. In particular, we address the problem of appearance gaze estimation employing deep learning methods for solving the regression task of predicting the point of gaze on a display. This solution is validated using a commercial infrared eye tracker: we achieve 73.843 Root Mean Square Error (RMSE) in pixels between the predictions. The proposed solution outperforms a relevant web-cam solution in terms of pixel-normalized RMSE 0.022 against 0.116 within the carried out comparative study, respectively.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione
