PERSON REIDENTIFICATION USING MCE-KISS METRIC LEARNING WITH MAXIMUM LIKELIHOOD FUNCTION
Abstract
Nowadays, in the area of Intelligent
Video Surveillance (IVR), person reidentification
receives an intensive attention. Person
reidentification aims to match an instance of a
person captured by one camera system to the
instance of a person captured by another camera
system. It is considered as a challenging problem
because the appearance of person varies through
the scenes, lightning conditions, shadows,
different pose of person that has to be searched
for. Recently, many algorithms proposed like
LMNN, ITML are not suitable for large training
samples. This paper introduces Minimum
Classification Error (MCE) based KISS metric
algorithm with smoothing technique to improve
reidentification. Smoothing technique is done
with maximum likelihood functions which
enlarge small eigenvalues in the estimated
covariance matrices.
Downloads
Author(s) and co-author(s) jointly and severally represent and warrant that the Article is original with the author(s) and does not infringe any copyright or violate any other right of any third parties, and that the Article has not been published elsewhere. Author(s) agree to the terms that the IJRDO Journal will have the full right to remove the published article on any misconduct found in the published article.
