Multiple-Object Tracking in Large-Scale Scene

Wenbo YUAN; Zhiqiang CAO; Min TAN; Hongkai CHEN

doi:10.1587/transinf.2015EDP7481

Multiple-Object Tracking in Large-Scale Scene

Wenbo YUAN, Zhiqiang CAO, Min TAN, Hongkai CHEN

Full Text Views

0

Share
Cite this

Summary :

In this paper, a multiple-object tracking approach in large-scale scene is proposed based on visual sensor network. Firstly, the object detection is carried out by extracting the HOG features. Then, object tracking is performed based on an improved particle filter method. On the one hand, a kind of temporal and spatial dynamic model is designed to improve the tracking precision. On the other hand, the cumulative error generated from evaluating particles is eliminated through an appearance model. In addition, losses of the tracking will be incurred for several reasons, such as occlusion, scene switching and leaving. When the object is in the scene under monitoring by visual sensor network again, object tracking will continue through object re-identification. Finally, continuous multiple-object tracking in large-scale scene is implemented. A database is established by collecting data through the visual sensor network. Then the performances of object tracking and object re-identification are tested. The effectiveness of the proposed multiple-object tracking approach is verified.

Publication: IEICE TRANSACTIONS on Information Vol.E99-D No.7 pp.1903-1909

Publication Date: 2016/07/01

Publicized: 2016/04/21

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2015EDP7481

Type of Manuscript: PAPER

Category: Image Recognition, Computer Vision

Authors

Wenbo YUAN
  Chinese Academy of Sciences
Zhiqiang CAO
  Chinese Academy of Sciences
Min TAN
  Chinese Academy of Sciences
Hongkai CHEN
  Chinese Academy of Sciences

Keyword

visual sensor network, HOG, improved particle filter, re-identification, object tracking

Cite this

Copy

Wenbo YUAN, Zhiqiang CAO, Min TAN, Hongkai CHEN, "Multiple-Object Tracking in Large-Scale Scene" in IEICE TRANSACTIONS on Information, vol. E99-D, no. 7, pp. 1903-1909, July 2016, doi: 10.1587/transinf.2015EDP7481.
Abstract: In this paper, a multiple-object tracking approach in large-scale scene is proposed based on visual sensor network. Firstly, the object detection is carried out by extracting the HOG features. Then, object tracking is performed based on an improved particle filter method. On the one hand, a kind of temporal and spatial dynamic model is designed to improve the tracking precision. On the other hand, the cumulative error generated from evaluating particles is eliminated through an appearance model. In addition, losses of the tracking will be incurred for several reasons, such as occlusion, scene switching and leaving. When the object is in the scene under monitoring by visual sensor network again, object tracking will continue through object re-identification. Finally, continuous multiple-object tracking in large-scale scene is implemented. A database is established by collecting data through the visual sensor network. Then the performances of object tracking and object re-identification are tested. The effectiveness of the proposed multiple-object tracking approach is verified.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.2015EDP7481/_p

Copy

@ARTICLE{e99-d_7_1903,
author={Wenbo YUAN, Zhiqiang CAO, Min TAN, Hongkai CHEN, },
journal={IEICE TRANSACTIONS on Information},
title={Multiple-Object Tracking in Large-Scale Scene},
year={2016},
volume={E99-D},
number={7},
pages={1903-1909},
abstract={In this paper, a multiple-object tracking approach in large-scale scene is proposed based on visual sensor network. Firstly, the object detection is carried out by extracting the HOG features. Then, object tracking is performed based on an improved particle filter method. On the one hand, a kind of temporal and spatial dynamic model is designed to improve the tracking precision. On the other hand, the cumulative error generated from evaluating particles is eliminated through an appearance model. In addition, losses of the tracking will be incurred for several reasons, such as occlusion, scene switching and leaving. When the object is in the scene under monitoring by visual sensor network again, object tracking will continue through object re-identification. Finally, continuous multiple-object tracking in large-scale scene is implemented. A database is established by collecting data through the visual sensor network. Then the performances of object tracking and object re-identification are tested. The effectiveness of the proposed multiple-object tracking approach is verified.},
keywords={},
doi={10.1587/transinf.2015EDP7481},
ISSN={1745-1361},
month={July},}

Copy

TY - JOUR
TI - Multiple-Object Tracking in Large-Scale Scene
T2 - IEICE TRANSACTIONS on Information
SP - 1903
EP - 1909
AU - Wenbo YUAN
AU - Zhiqiang CAO
AU - Min TAN
AU - Hongkai CHEN
PY - 2016
DO - 10.1587/transinf.2015EDP7481
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2016
AB - In this paper, a multiple-object tracking approach in large-scale scene is proposed based on visual sensor network. Firstly, the object detection is carried out by extracting the HOG features. Then, object tracking is performed based on an improved particle filter method. On the one hand, a kind of temporal and spatial dynamic model is designed to improve the tracking precision. On the other hand, the cumulative error generated from evaluating particles is eliminated through an appearance model. In addition, losses of the tracking will be incurred for several reasons, such as occlusion, scene switching and leaving. When the object is in the scene under monitoring by visual sensor network again, object tracking will continue through object re-identification. Finally, continuous multiple-object tracking in large-scale scene is implemented. A database is established by collecting data through the visual sensor network. Then the performances of object tracking and object re-identification are tested. The effectiveness of the proposed multiple-object tracking approach is verified.
ER -