A Method of Image Target Tracking based on Multi Target Algorithm

DOI

10.2991/snce-18.2018.190How to use a DOI?

Keywords

Image target tracking; Multi target algorithm; Fingerprint image; Data communication module

Abstract

The target tracking is an important part of video target analysis, and the video target analysis also includes the processing of the image sequence, so as to explore the law of the video moving target, or to test the early warning of semantic and non semantic support in tracking system, including target detection, environment detection, target classification, behavior understanding, target tracking and so on. In this paper, a random finite set framework based on probability hypothesis density algorithm is applied to video target tracking, the image after background subtraction is taken as the observed value, and the clutter is filtered. And also the data association algorithm is applied to associate the target positions at different time points to get the complete target trajectory information, and meanwhile, the number of targets at each moment is estimated. This algorithm can effectively deal with the changes in the number of targets caused by the appearance and disappearance of the target in the scene.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yufeng Yang
AU  - Kuo Fu
PY  - 2018/05
DA  - 2018/05
TI  - A Method of Image Target Tracking based on Multi Target Algorithm
BT  - Proceedings of the 8th International Conference on Social Network, Communication and Education (SNCE 2018)
PB  - Atlantis Press
SP  - 925
EP  - 928
SN  - 2352-538X
UR  - https://doi.org/10.2991/snce-18.2018.190
DO  - 10.2991/snce-18.2018.190
ID  - Yang2018/05
ER  -