Abstract
Existing human eye tracking research is based on the off-line sample training cascade classifier and the traditional tracking algorithm. However, it is difficult to adapt to situations where human eye is partially blocked, gets morphological changes or scale changes and so on. In order to solve these problems, the tracking-learning-detection algorithm for online single-target long-term tracking is used and improved. A novel eye tracking method—the human eye tracking-learning-detection algorithm with tracking feedback is proposed. The detection area is adjusted adaptively and narrowed by the tracking feedback. Above problems are solved, the interference of similar targets is avoided, and the speed of human eye tracking is enhanced. The experimental results show that the algorithm has high tracking accuracy and frames per second.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.