For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Measuring Particles in Joint Feature-Spatial Space
Liang SHA Guijin WANG Anbang YAO Xinggang LIN
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2009/07/01
Online ISSN: 1745-1337
Print ISSN: 0916-8508
Type of Manuscript: LETTER
object tracking, particle filter (PF), mixture Gaussian kernel function (MGKF), state transition model,
Full Text: PDF(538KB)>>
Particle filter has attracted increasing attention from researchers of object tracking due to its promising property of handling nonlinear and non-Gaussian systems. In this paper, we mainly explore the problem of precisely estimating observation likelihoods of particles in the joint feature-spatial space. For this purpose, a mixture Gaussian kernel function based similarity is presented to evaluate the discrepancy between the target region and the particle region. Such a similarity can be interpreted as the expectation of the spatial weighted feature distribution over the target region. To adapt outburst of object motion, we also present a method to appropriately adjust state transition model by utilizing the priors of motion speed and object size. In comparison with the standard particle filter tracker, our tracking algorithm shows the better performance on challenging video sequences.