Visual Object Tracking evaluation

Dnr:

SNIC 2015/4-47

Type:

SNAC Small

Principal Investigator:

Michael Felsberg

Affiliation:

Linköpings universitet

Start Date:

2015-10-06

End Date:

2017-11-01

Primary Classification:

10207: Datorseende och robotik (autonoma system)

Webpage:

http://www.votchallenge.net/vot2015/

Allocation

Abstract

The Thermal Infrared Visual Object Tracking challenge 2015, VOT-TIR2015, aims at comparing short-term single-object visual trackers that work on thermal infrared sequences and do not apply pre-learned models of object appearance. Results of 20 trackers are presented. The number of tested trackers makes VOT-TIR2015 the largest benchmark on short-term tracking in TIR sequences to date. For each participating tracker, a short description is provided in the appendix. The VOT-TIR2015 challenge is based on features of the VOT2013 challenge, but introducing the following novelties: (i) the dataset is newly collected from various sources in academia and industry, (ii) the VOT2013 attributes are adapted to TIR data, (iii) the evaluation is performed using insights gained during VOT2013 and VOT2014 and is similar to VOT2015.