Abstract Kernel Correlation Filter (KCF) tracker has shown great potential on precision,
robustness and efficiency. However, the candidate region used to train the correlation filter is …

Target continuous tracking problem is an important research topic in the field of computer
vision. To conquer difficulties of target loss under complex situation, size changes and …

In order to realize the stable, accurate and realtime target tracking, a novel target tracking
algorithm combining scale-invariant features extraction and fast pattern matching is …

Decomposing target into several parts may improve the capability of tracking algorithm to
deal with appearance variations such as occlusion and deformation. In this letter, we …

It is difficult that gate setting and target line-of-sight estimation are performed effectively by
the traditional extended Kalman filter (EKF) according to a target motion model, because the …

The location and scale filters in discriminative correlation filter methods are lack of accurate
rotation representation capability and updated with fixed intervals, which leads to tracking …

The most existing algorithms have to build the complex model and draw a large number of
training samples to achieve accurate object tracking, which will produce large amount of …

In the real scene, the target itself and the background will be unpredictable changes, such
as the occlusion and other factors will bring greater challenges to the object tracking. In this …

Kernelized correlation filters (KCF) algorithm tracker updating its model parameters at every
frame makes it unable to effectively deal with the problems of fast motion and interference of …