A software framework for simulating eye trackers

Böhme, Martin; Dörr, Michael; Graw, Mathis; Martinetz, Thomas; Barth, Erhardt

doi:10.1145/1344471.1344529

Cited by 39 publications

(24 citation statements)

References 8 publications

(9 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simulated data is used in this section to be able to asses the effects of potential noise-factors separately. The simulator [Böhme et al 2008] allows for detailed modeling of the different components of the setup and eye specific parameters. The evaluation is divided according to the presence of head movements and the number of calibration targets (N).…”

Section: Assessment On Simulated Datamentioning

confidence: 99%

Homography normalization for robust gaze estimation in uncalibrated setups

Hansen

Agustin

Villanueva

2010

Proceedings of the 2010 Symposium on Eye-Tracking Research &Amp; Applications - ETRA '10

View full text Add to dashboard Cite

Homography normalization is presented as a novel gaze estimation method for uncalibrated setups. The method applies when head movements are present but without any requirements to camera calibration or geometric calibration. The method is geometrically and empirically demonstrated to be robust to head pose changes and despite being less constrained than cross-ratio methods, it consistently performs favorably by several degrees on both simulated data and data from physical setups. The physical setups include the use of off-the-shelf web cameras with infrared light (night vision) and standard cameras with and without infrared light. The benefits of homography normalization and uncalibrated setups in general are also demonstrated through obtaining gaze estimates (in the visible spectrum) using only the screen reflections on the cornea.

show abstract

Section: Assessment On Simulated Datamentioning

confidence: 99%

Homography normalization for robust gaze estimation in uncalibrated setups

Hansen

Agustin

Villanueva

2010

Proceedings of the 2010 Symposium on Eye-Tracking Research &Amp; Applications - ETRA '10

View full text Add to dashboard Cite

show abstract

“…Simulation data was generated using the simulator developed by [39]. The simulator allows for detailed modeling of different components of the hardware setup and user eye in 3D.…”

Section: A Simulation Setupmentioning

confidence: 99%

A Regression-Based User Calibration Framework for Real-Time Gaze Estimation

Arar

Gao

Thiran

2017

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Abstract-Eye movements play a very significant role in human computer interaction (HCI) as they are natural and fast, and contain important cues for human cognitive state and visual attention. Over the last two decades, many techniques have been proposed to accurately estimate the gaze. Among these, video-based remote eye trackers have attracted much interest since they enable non-intrusive gaze estimation. To achieve high estimation accuracies for remote systems, user calibration is inevitable in order to compensate for the estimation bias caused by person-specific eye parameters. Although several explicit and implicit user calibration methods have been proposed to ease the calibration burden, the procedure is still cumbersome and needs further improvement. In this paper, we present a comprehensive analysis of regression-based user calibration techniques. We propose a novel weighted least squares regression-based user calibration method together with a real-time cross-ratio based gaze estimation framework. The proposed system enables to obtain high estimation accuracy with minimum user effort which leads to user-friendly HCI applications. Experimental results conducted on both simulations and user experiments show that our framework achieves a significant performance improvement over the state-of-the-art user calibration methods when only a few points are available for the calibration.

show abstract

“…working distance of about 50 − 60 cm) and anthropomorphic averages be calculated to be planar up to the fourth decimal. These results were obtained through simulated experiments of an eye located in different positions in 3D space [Böhme et al 2008] and can be generally applied in similar methods (e.g. cross ratio-based gaze estimation methods) to argue that the reflections are planar.…”

Section: Glint Normalizationmentioning

confidence: 99%

“…The experiments were conducted on both simulated data and real data obtained from a web camera. The simulated data is generated through the open source eye tracker simulator [Böhme et al 2008] while the experiments on real data uses a standard (Sandberg) web camera with night vision. The standard wide angle web camera lens has been replaced with a corresponding 12 mm lens to ensure the camera is placed away from the user.…”

Section: Experiments With Pattern Detectionmentioning

confidence: 99%

Robust glint detection through homography normalization

Hansen

Roholm

Ferreiros

2014

Proceedings of the Symposium on Eye Tracking Research and Applications

View full text Add to dashboard Cite

A novel normalization principle for robust glint detection is presented. The method is based on geometric properties of corneal reflections and allows for simple and effective detection of glints even in the presence of several spurious and identically appearing reflections. The method is tested on both simulated and data obtained from web cameras. The proposed method is a possible direction towards making eye trackers more robust to challenging scenarios.

show abstract

A software framework for simulating eye trackers

Cited by 39 publications

References 8 publications

Homography normalization for robust gaze estimation in uncalibrated setups

Homography normalization for robust gaze estimation in uncalibrated setups

A Regression-Based User Calibration Framework for Real-Time Gaze Estimation

Robust glint detection through homography normalization

Contact Info

Product

Resources

About