Adaptive Updating Probabilistic Model for Visual Tracking

Kai FANG; Shuoyan LIU; Chunjie XU; Hao XUE

doi:10.1587/transinf.2016EDL8188

Adaptive Updating Probabilistic Model for Visual Tracking

Kai FANG, Shuoyan LIU, Chunjie XU, Hao XUE

Full Text Views

0

Share
Cite this

Summary :

In this paper, an adaptive updating probabilistic model is proposed to track an object in real-world environment that includes motion blur, illumination changes, pose variations, and occlusions. This model adaptively updates tracker with the searching and updating process. The searching process focuses on how to learn appropriate tracker and updating process aims to correct it as a robust and efficient tracker in unconstrained real-world environments. Specifically, according to various changes in an object's appearance and recent probability matrix (TPM), tracker probability is achieved in Expectation-Maximization (EM) manner. When the tracking in each frame is completed, the estimated object's state is obtained and then fed into update current TPM and tracker probability via running EM in a similar manner. The highest tracker probability denotes the object location in every frame. The experimental result demonstrates that our method tracks targets accurately and robustly in the real-world tracking environments.

Publication: IEICE TRANSACTIONS on Information Vol.E100-D No.4 pp.914-917

Publication Date: 2017/04/01

Publicized: 2017/01/06

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2016EDL8188

Type of Manuscript: LETTER

Category: Pattern Recognition

Authors

Kai FANG
  China Academy of Railway Sciences
Shuoyan LIU
  China Academy of Railway Sciences
Chunjie XU
  China Academy of Railway Sciences
Hao XUE
  China Academy of Railway Sciences

Keyword

visual tracking, transition probability matrix, expectation-maximization

Cite this

Copy

Kai FANG, Shuoyan LIU, Chunjie XU, Hao XUE, "Adaptive Updating Probabilistic Model for Visual Tracking" in IEICE TRANSACTIONS on Information, vol. E100-D, no. 4, pp. 914-917, April 2017, doi: 10.1587/transinf.2016EDL8188.
Abstract: In this paper, an adaptive updating probabilistic model is proposed to track an object in real-world environment that includes motion blur, illumination changes, pose variations, and occlusions. This model adaptively updates tracker with the searching and updating process. The searching process focuses on how to learn appropriate tracker and updating process aims to correct it as a robust and efficient tracker in unconstrained real-world environments. Specifically, according to various changes in an object's appearance and recent probability matrix (TPM), tracker probability is achieved in Expectation-Maximization (EM) manner. When the tracking in each frame is completed, the estimated object's state is obtained and then fed into update current TPM and tracker probability via running EM in a similar manner. The highest tracker probability denotes the object location in every frame. The experimental result demonstrates that our method tracks targets accurately and robustly in the real-world tracking environments.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2016EDL8188/_p

Copy

@ARTICLE{e100-d_4_914,
author={Kai FANG, Shuoyan LIU, Chunjie XU, Hao XUE, },
journal={IEICE TRANSACTIONS on Information},
title={Adaptive Updating Probabilistic Model for Visual Tracking},
year={2017},
volume={E100-D},
number={4},
pages={914-917},
abstract={In this paper, an adaptive updating probabilistic model is proposed to track an object in real-world environment that includes motion blur, illumination changes, pose variations, and occlusions. This model adaptively updates tracker with the searching and updating process. The searching process focuses on how to learn appropriate tracker and updating process aims to correct it as a robust and efficient tracker in unconstrained real-world environments. Specifically, according to various changes in an object's appearance and recent probability matrix (TPM), tracker probability is achieved in Expectation-Maximization (EM) manner. When the tracking in each frame is completed, the estimated object's state is obtained and then fed into update current TPM and tracker probability via running EM in a similar manner. The highest tracker probability denotes the object location in every frame. The experimental result demonstrates that our method tracks targets accurately and robustly in the real-world tracking environments.},
keywords={},
doi={10.1587/transinf.2016EDL8188},
ISSN={1745-1361},
month={April},}

Copy

TY - JOUR
TI - Adaptive Updating Probabilistic Model for Visual Tracking
T2 - IEICE TRANSACTIONS on Information
SP - 914
EP - 917
AU - Kai FANG
AU - Shuoyan LIU
AU - Chunjie XU
AU - Hao XUE
PY - 2017
DO - 10.1587/transinf.2016EDL8188
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - April 2017
AB - In this paper, an adaptive updating probabilistic model is proposed to track an object in real-world environment that includes motion blur, illumination changes, pose variations, and occlusions. This model adaptively updates tracker with the searching and updating process. The searching process focuses on how to learn appropriate tracker and updating process aims to correct it as a robust and efficient tracker in unconstrained real-world environments. Specifically, according to various changes in an object's appearance and recent probability matrix (TPM), tracker probability is achieved in Expectation-Maximization (EM) manner. When the tracking in each frame is completed, the estimated object's state is obtained and then fed into update current TPM and tracker probability via running EM in a similar manner. The highest tracker probability denotes the object location in every frame. The experimental result demonstrates that our method tracks targets accurately and robustly in the real-world tracking environments.
ER -