Abstract

The Thermal Infrared Visual Object Tracking challenge 2016, VOT-TIR2016, aims at comparing short-term single-object visual trackers that work on thermal infrared (TIR) sequences and do not apply pre-learned models of object appearance. VOT-TIR2016 is the second benchmark on short-term tracking in TIR sequences. Results of 24 trackers are presented. For each participating tracker, a short description is provided in the appendix. The VOT-TIR2016 challenge is similar to the 2015 challenge, the main difference is the introduction of new, more di-cult sequences into the dataset. Furthermore, VOT-TIR2016 evaluation adopted the improvements regarding overlap calculation in VOT2016. Compared to VOT-TIR2015, a significant general improvement of results has been observed, which partly compensate for the more difficult sequences. The dataset, the evaluation kit, as well as the results are publicly available at the challenge website.

Venue

The 14th European Conference on Computer Vision

Publication Year

2016

Authors

Matas et al.

Cite Us

@Inbook{Felsberg2016,
author=”Felsberg, Michael
and Kristan, Matej
and Matas, Ji{\v{r}}i
and Leonardis, Ale{\v{s}}
and Pflugfelder, Roman
and H{\”a}ger, Gustav
and Berg, Amanda
and Eldesokey, Abdelrahman
and Ahlberg, J{\”o}rgen
and {\v{C}}ehovin, Luka
and Voj{\’i}r̃, Tom{\’a}{\v{s}}
and Luke{\v{z}}i{\v{c}}, Alan
and Fern{\’a}ndez, Gustavo
and Petrosino, Alfredo
and Garcia-Martin, Alvaro
and Montero, Andr{\’e}s Sol{\’i}s
and Varfolomieiev, Anton
and Erdem, Aykut
and Han, Bohyung
and Chang, Chang-Ming
and Du, Dawei
and Erdem, Erkut
and Khan, Fahad Shahbaz
and Porikli, Fatih
and Zhao, Fei
and Bunyak, Filiz
and Battistone, Francesco
and Zhu, Gao
and Seetharaman, Guna
and Li, Hongdong
and Qi, Honggang
and Bischof, Horst
and Possegger, Horst
and Nam, Hyeonseob
and Valmadre, Jack
and Zhu, Jianke
and Feng, Jiayi
and Lang, Jochen
and Martinez, Jose M.
and Palaniappan, Kannappan
and Lebeda, Karel
and Gao, Ke
and Mikolajczyk, Krystian
and Wen, Longyin
and Bertinetto, Luca
and Poostchi, Mahdieh
and Maresca, Mario
and Danelljan, Martin
and Arens, Michael
and Tang, Ming
and Baek, Mooyeol
and Fan, Nana
and Al-Shakarji, Noor
and Miksik, Ondrej
and Akin, Osman
and Torr, Philip H. S.
and Huang, Qingming
and Martin-Nieto, Rafael
and Pelapur, Rengarajan
and Bowden, Richard
and Lagani{\`e}re, Robert
and Krah, Sebastian B.
and Li, Shengkun
and Yao, Shizeng
and Hadfield, Simon
and Lyu, Siwei
and Becker, Stefan
and Golodetz, Stuart
and Hu, Tao
and Mauthner, Thomas
and Santopietro, Vincenzo
and Li, Wenbo
and H{\”u}bner, Wolfgang
and Li, Xin
and Li, Yang
and Xu, Zhan
and He, Zhenyu”,
editor=”Hua, Gang
and J{\’e}gou, Herv{\’e}”,
title=”The Thermal Infrared Visual Object Tracking VOT-TIR2016 Challenge Results”,
bookTitle=”Computer Vision — ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part II”,
year=”2016″,
publisher=”Springer International Publishing”,
address=”Cham”,
pages=”824–849″,
abstract=”The Thermal Infrared Visual Object Tracking challenge 2016, VOT-TIR2016, aims at comparing short-term single-object visual trackers that work on thermal infrared (TIR) sequences and do not apply pre-learned models of object appearance. VOT-TIR2016 is the second benchmark on short-term tracking in TIR sequences. Results of 24 trackers are presented. For each participating tracker, a short description is provided in the appendix. The VOT-TIR2016 challenge is similar to the 2015 challenge, the main difference is the introduction of new, more difficult sequences into the dataset. Furthermore, VOT-TIR2016 evaluation adopted the improvements regarding overlap calculation in VOT2016. Compared to VOT-TIR2015, a significant general improvement of results has been observed, which partly compensate for the more difficult sequences. The dataset, the evaluation kit, as well as the results are publicly available at the challenge website.”,
isbn=”978-3-319-48881-3″,
doi=”10.1007/978-3-319-48881-3_55″,
url=”https://doi.org/10.1007/978-3-319-48881-3_55″
}

Page layout inspired by https://research.google.com/