Similarity measure for nonparametric kernel density based object tracking

An object tracking algorithm using a novel simple symmetric similar-ity function between spatially-smoothed kernel-density estimates of the
model and target distributions is proposed and tested. The similarity
measure is based on the expectation of the density estimates over the
model or target images. The density is estimated using radial-basis ker-
nel functions that measure the affinity between points and provide a bet-
ter outlier rejection property. The mean-shift algorithm is used to track
objects by iteratively maximizing this similarity function. To alleviate
the quadratic complexity of the density estimation, we employ Gaussian
kernels and the fast Gauss transform to reduce the computations to linear
order. This leads to a very efficient and robust nonparametric tracking al-
gorithm. The proposed algorithm is tested with several image sequences
and shown to achieve robust and reliable real-time tracking. Several se-
quences are placed at http://www.cs.umd.edu/users/yangcj/node3.html.