Head and camera rotation invariant eye tracking algorithm based on segmented group method of data handling
- PDF / 1,442,762 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 64 Downloads / 238 Views
ORIGINAL PAPER
Head and camera rotation invariant eye tracking algorithm based on segmented group method of data handling Mohammad Reza Mohebbian1 · Javad Rasti2 Received: 7 June 2019 / Revised: 3 June 2020 / Accepted: 17 August 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Eye-gaze tracking through camera is commonly used in a number of areas, such as computer user interface systems, sports science, psychology, and biometrics. The robustness of the head and camera rotation tracking algorithm has been a critical problem in recent years. In this paper, Haar-like features and a modified version of the group method of data handling, as well as segmented regression, are used together to find the base points of the eyes in a facial image. Then, a geometric transformation is applied to detect precise eye-gaze direction. The proposed algorithm is tested on GI4E and Columbia Gaze datasets and compared to other algorithms. The results show adequate accuracy, especially when the head/camera is rotated. Keywords Eye tracking · Haar-like features · Group method of data handling · Segmented regression
1 Introduction Eye tracking is commonly used in numerous applications where it is important to know where the subject is looking toward. For example, in marketing and advertisement, the arrangement of the goods in a supermarket can affect the shopping behavior; thus, finding the customer’s gaze direction gets important [1]. The other instance is detecting the direction where a professional basketball player looks during a penalty kick, where it might be instructive for beginners [2]. Other examples can be found in biometrics [3, 4], computer user interfaces [5], and psychiatric [2, 6]. In more recent studies, eye-gaze and eye-state monitoring in the automobile industry is used in driver assistance applications to assess driver’s attention and awareness [7, 8]. As an illustration, a gaze-based monitoring system in a vehicle uses a camera installed on a dashboard to trigger a machine learning system to send feedback signals for awakening the driver. In fact, this system can detect whether the driver is sleepy or
B
Javad Rasti [email protected] Mohammad Reza Mohebbian [email protected]
1
Electrical and Computer Engineering Department, University of Saskatchewan, Saskatoon, SK, Canada
2
Biomedical Engineering Department, Faculty of Engineering, University of Isfahan, Isfahan, Iran
involved in other tasks (such as talking on cell phone), thus not paying enough attention to the route. A variety of incidents may be prevented through this monitoring system. Eye tracking can also be used as a control method or contact tool for a wide variety of people with physical impairments. For instance, people with spinal cord injuries cannot control devices like wheelchairs. Here, eye tracking is an easier approach compared to other control methods such as speech recognition or EEG/ECG interpretation. In fact, eye tracking provides a broad range of potentials to be used in assistive technologies [9]. The rest of
Data Loading...
