Self-tuning motion model for visual tracking

Hangkai Tan; Qingjie Zhao; Xiongpeng Wang

doi:10.1007/978-981-10-5230-9_8

Self-tuning motion model for visual tracking

Hangkai Tan^*, Qingjie Zhao, Xiongpeng Wang

^*Corresponding author for this work

School of Computer Science and Technology

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In visual tracking, how to select a suitable motion model is an important problem to deal with, since the movements in real world are always irregular in most cases. We propose a self-tuning motion model for target tracking in this paper, where the current motion model is computed according to the relative distance of the target positions in the last two frames. Our method has achieved excellent performance when experimenting on the sequences where the targets move unstably, abruptly or even when partial occlusion exists, and the method is particularly robust to the unsuitable initial motion model.

Original language	English
Title of host publication	Cognitive Systems and Signal Processing - 3rd International Conference, ICCSIP 2016, Revised Selected Papers
Editors	Fuchun Sun, Huaping Liu, Dewen Hu
Publisher	Springer Verlag
Pages	74-81
Number of pages	8
ISBN (Print)	9789811052293
DOIs	https://doi.org/10.1007/978-981-10-5230-9_8
Publication status	Published - 2017
Event	3rd International Conference on Cognitive Systems and Information Processing, ICCSIP 2016 - Beijing, China Duration: 19 Nov 2016 → 23 Nov 2016

Publication series

Name	Communications in Computer and Information Science
Volume	710
ISSN (Print)	1865-0929

Conference

Conference	3rd International Conference on Cognitive Systems and Information Processing, ICCSIP 2016
Country/Territory	China
City	Beijing
Period	19/11/16 → 23/11/16

Keywords

Logistic regression
Self-tuning motion models
Visual tracking

Access to Document

10.1007/978-981-10-5230-9_8

Cite this

Tan, H., Zhao, Q., & Wang, X. (2017). Self-tuning motion model for visual tracking. In F. Sun, H. Liu, & D. Hu (Eds.), Cognitive Systems and Signal Processing - 3rd International Conference, ICCSIP 2016, Revised Selected Papers (pp. 74-81). (Communications in Computer and Information Science; Vol. 710). Springer Verlag. https://doi.org/10.1007/978-981-10-5230-9_8

@inproceedings{5b99ab3c53d7412da9e9de44c41ce288,

title = "Self-tuning motion model for visual tracking",

abstract = "In visual tracking, how to select a suitable motion model is an important problem to deal with, since the movements in real world are always irregular in most cases. We propose a self-tuning motion model for target tracking in this paper, where the current motion model is computed according to the relative distance of the target positions in the last two frames. Our method has achieved excellent performance when experimenting on the sequences where the targets move unstably, abruptly or even when partial occlusion exists, and the method is particularly robust to the unsuitable initial motion model.",

keywords = "Logistic regression, Self-tuning motion models, Visual tracking",

author = "Hangkai Tan and Qingjie Zhao and Xiongpeng Wang",

note = "Publisher Copyright: {\textcopyright} Springer Nature Singapore Pte Ltd. 2017.; 3rd International Conference on Cognitive Systems and Information Processing, ICCSIP 2016 ; Conference date: 19-11-2016 Through 23-11-2016",

year = "2017",

doi = "10.1007/978-981-10-5230-9_8",

language = "English",

isbn = "9789811052293",

series = "Communications in Computer and Information Science",

publisher = "Springer Verlag",

pages = "74--81",

editor = "Fuchun Sun and Huaping Liu and Dewen Hu",

booktitle = "Cognitive Systems and Signal Processing - 3rd International Conference, ICCSIP 2016, Revised Selected Papers",

address = "Germany",

}

Tan, H, Zhao, Q & Wang, X 2017, Self-tuning motion model for visual tracking. in F Sun, H Liu & D Hu (eds), Cognitive Systems and Signal Processing - 3rd International Conference, ICCSIP 2016, Revised Selected Papers. Communications in Computer and Information Science, vol. 710, Springer Verlag, pp. 74-81, 3rd International Conference on Cognitive Systems and Information Processing, ICCSIP 2016, Beijing, China, 19/11/16. https://doi.org/10.1007/978-981-10-5230-9_8

Self-tuning motion model for visual tracking. / Tan, Hangkai; Zhao, Qingjie; Wang, Xiongpeng.
Cognitive Systems and Signal Processing - 3rd International Conference, ICCSIP 2016, Revised Selected Papers. ed. / Fuchun Sun; Huaping Liu; Dewen Hu. Springer Verlag, 2017. p. 74-81 (Communications in Computer and Information Science; Vol. 710).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Self-tuning motion model for visual tracking

AU - Tan, Hangkai

AU - Zhao, Qingjie

AU - Wang, Xiongpeng

N1 - Publisher Copyright: © Springer Nature Singapore Pte Ltd. 2017.

PY - 2017

Y1 - 2017

N2 - In visual tracking, how to select a suitable motion model is an important problem to deal with, since the movements in real world are always irregular in most cases. We propose a self-tuning motion model for target tracking in this paper, where the current motion model is computed according to the relative distance of the target positions in the last two frames. Our method has achieved excellent performance when experimenting on the sequences where the targets move unstably, abruptly or even when partial occlusion exists, and the method is particularly robust to the unsuitable initial motion model.

AB - In visual tracking, how to select a suitable motion model is an important problem to deal with, since the movements in real world are always irregular in most cases. We propose a self-tuning motion model for target tracking in this paper, where the current motion model is computed according to the relative distance of the target positions in the last two frames. Our method has achieved excellent performance when experimenting on the sequences where the targets move unstably, abruptly or even when partial occlusion exists, and the method is particularly robust to the unsuitable initial motion model.

KW - Logistic regression

KW - Self-tuning motion models

KW - Visual tracking

UR - http://www.scopus.com/inward/record.url?scp=85026780223&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-5230-9_8

DO - 10.1007/978-981-10-5230-9_8

M3 - Conference contribution

AN - SCOPUS:85026780223

SN - 9789811052293

T3 - Communications in Computer and Information Science

SP - 74

EP - 81

BT - Cognitive Systems and Signal Processing - 3rd International Conference, ICCSIP 2016, Revised Selected Papers

A2 - Sun, Fuchun

A2 - Liu, Huaping

A2 - Hu, Dewen

PB - Springer Verlag

T2 - 3rd International Conference on Cognitive Systems and Information Processing, ICCSIP 2016

Y2 - 19 November 2016 through 23 November 2016

ER -

Self-tuning motion model for visual tracking

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this