Develop post- or real-time gaze analysis applications
Useful links: Installation | Source Repository | Issue Tracker | Contact
ArGaze is an open and flexible Python software library designed to provide a unified and modular approach to gaze analysis or gaze interaction.
By offering a wide array of gaze metrics and supporting easy extension to incorporate additional metrics, ArGaze empowers researchers and practitioners to explore novel analytical approaches efficiently.
Eye tracking context
ArGaze facilitates the integration of both screen-based and head-mounted eye tracking systems for live data capture and afterward data playback.
Learn how to handle various eye tracking context by reading the dedicated user guide section.
Gaze analysis pipeline
Once incoming eye tracking data available, ArGaze provides an extensible modules library, allowing to select application-specific algorithms at each pipeline step:
- Fixation/Saccade identification: dispersion threshold identification, velocity threshold identification, etc.
- Area Of Interest (AOI) matching: focus point inside, deviation circle coverage, etc.
- Scan path analysis: transition matrix, entropy, explore/exploit ratio, etc.
All those gaze analysis features can be used with any screen-based eye tracker devices.
Augmented reality based on ArUco marker pipeline
Things goes harder when gaze data comes from head-mounted eye tracker devices. That's why ArGaze provides Augmented Reality (AR) support to map Areas Of Interest (AOI) on OpenCV ArUco markers.
This ArUco marker pipeline can be combined with any wearable eye tracking device Python library, like Tobii or Pupil glasses.
Note
ArUco marker pipeline is greatly inspired by Andrew T. Duchowski, Vsevolod Peysakhovich and Krzysztof Krejtz article about using pose estimation to map gaze to detected fiducial markers.