On-line adaption of class-specific codebooks for instance tracking
J Gall, N Razavi and Luc Van Gool
In: 21st British machine vision conference - BMVC 2010, 31 Aug - 3 Sept, 2010, Aberystwyth, UK.
Off-line trained class-specific object detectors are designed to detect any instance of
the class in a given image or video sequence. In the context of object tracking, however,
one seeks the location and scale of a target object, which is a specific instance of the class.
Hence, the target needs to be separated not only from the background but also from other
instances in the video sequence. We address this problem by adapting a class-specific
object detector to the target, making it more instance-specific. To this end, we learn offline
a codebook for the object class that models the spatial distribution and appearance
of object parts. For tracking, the codebook is coupled with a particle filter. While the
posterior probability of the location and scale of the target is used to learn on-line the
probability of each part in the codebook belonging to the target, the probabilistic votes
for the object cast by the codebook entries are used to model the likelihood.
|EPrint Type:||Conference or Workshop Item (Paper)|
|Project Keyword:||Project Keyword UNSPECIFIED|
|Deposited By:||Luc Van Gool|
|Deposited On:||17 March 2011|