Evaluating Template Rescaling in Short-Term Single-Object Tracking
2015 (English)Conference paper (Refereed)
In recent years, short-term single-object tracking has emerged has a popular research topic, as it constitutes the core of more general tracking systems. Many such tracking methods are based on matching a part of the image with a template that is learnt online and represented by, for example, a correlation ﬁlter or a distribution ﬁeld. In order for such a tracker to be able to not only ﬁnd the position, but also the scale, of the tracked object in the next frame, some kind of scale estimation step is needed. This step is sometimes separate from the position estimation step, but is nevertheless jointly evaluated in de facto benchmarks. However, for practical as well as scientiﬁc reasons, the scale estimation step should be evaluated separately – for example,theremightincertainsituationsbeothermethodsmore suitable for the task. In this paper, we describe an evaluation method for scale estimation in template-based short-term single-object tracking, and evaluate two state-of-the-art tracking methods where estimation of scale and position are separable.
Place, publisher, year, edition, pages
IEEE , 2015.
Computer Vision and Robotics (Autonomous Systems)
IdentifiersURN: urn:nbn:se:liu:diva-121356ISBN: 9781467376327OAI: oai:DiVA.org:liu-121356DiVA: diva2:853786
17th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance (PETS), Karlsruhe, Germany, August 25, 2015
FunderSwedish Research Council, D0570301EU, FP7, Seventh Framework Programme, 312784