You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

56 lines
3.0 KiB

4 years ago
# OpenGaze: Open Source Toolkit for Camera-Based Gaze Estimation and Interaction
<!--The current demo video includes clips from Friends, which may violate the copyright. Although people think 28 seconds could be a boundary:!topic/youtube/rQhkI20Rm8k, there is no golden rule for it:>
<!--//[![Demo](]( "OpenGaze Friends Demo")-->
Appearance-based gaze estimation methods that only require an off-the-shelf camera have significantly improved and promise a wide range of new applications in gaze-based interaction and attentive user interfaces. However, these methods are not yet widely used in the human-computer interaction (HCI) community.
To democratize their use in HCI, we present OpenGaze, the first software toolkit that is specifically developed for gaze interface designers. OpenGaze is open source and aims to implement state-of-the-art methods for camera-based gaze estimation and interaction.
<img src="" height="80"/><img src="" height="80"><img src="" height="80">
## Functionality
The toolkit is capable of performing the following gaze-related tasks:
* **Gaze Estimation**
Show estimated gaze on the screen given screen-camera relationship.
[![Demo](]( "Gaze visualization demo")
* **Gaze Visualization**
Show gaze direction inital from the center of faces in the input image.
[![Demo](]( "Gaze visualization demo")
* **Personal Calibration**
Perform personal calibration and remapped the gaze target on the screen.
[![Demo](]( "Gaze visualization demo")
## Installation
[Unix Installation](
## Use
[Command line arguments](
## Citation
If you use any of the resources provided on this page in any of your publications, please cite the following paper:
**Evaluation of Appearance-Based Methods and Implications for Gaze-Based Applications?** <br/>
Xucong Zhang, Yusuke Sugano, Andreas Bulling<br/>
Proc. ACM SIGCHI Conference on Human Factors in Computing Systems (CHI), 2019<br/>
BibTex, PDF
## License
The license agreement can be found in Copyright.txt
You have to respect boost, OpenFace and OpenCV licenses.
Furthermore, you have to respect the licenses of the datasets used for [model training](: