Abstract
It is an important and challenging problem to tack variant-pose target, especially when the appearance of target changes during the period of occlusion. The traditional feature matching methods can not work well under the situations of target pose varying. This paper analyzes the characteristics of human visual tracking, and proposes a visual tracking model based on feature-imagination. Human tracking is realized by using this model combined with the traditional histogram matching method. The experiment results show that our method can perform feature-imagination from the features of human front to the features of human back. Compared with the traditional histogram matching method, the proposed method has obvious advantages in tracking variant-pose target.
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.