PROJECT TITLE :
Visual Tracking via Locally Structured Gaussian Process Regression
ABSTRACT:
We tend to propose a brand new target illustration technique, where the temporally obtained targets are jointly represented as a time series operate by exploiting their spatially native structure. With this technique, we tend to propose a brand new tracking algorithm, where tracking is formulated as a problem of Gaussian method regression over the joint representation. Numerous experiments on various difficult video sequences demonstrate that our tracker outperforms many other state-of-the-art trackers.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here