Abstract
One of the challenges to creating robust trackers is the construction of robust appearance Model. This paper presents a robust appearance model for object tracking. The robust object distribution is acquired by comparing the two Gaussian Mixture Models of the object and background. The probability image generated by the robust object distribution is used for the CAMSHIFT tracking. Experiments on several video sequences show the effectiveness of the proposed method.
Full Text
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call