Multi-target tracking algorithm by corner feature for video stream

DOI

10.2991/ameii-15.2015.134How to use a DOI?

Keywords

Moving Target Tracking; Corner Feature; Matching Optimization; Block State

Abstract

In the field of computer vision research, moving target tracking of sequence images is not well solved, and is an old, important and challenging task. Fast and accurate completion of moving target tracking is very an important and difficult problem. In a dynamic environment, moving target tracking is often influenced by various factors, such as weather changes, shadows, occlusion, background confusion. This paper presents a multi-target tracking algorithm by corner feature for video stream, which can solve the problems of video multi-objective motion tracking. The improved Harris operator can extract some even and stable corners, and the matching optimization reduces the amount of false matching points, so they improve the accuracy of target tracking. Experimental results show that the algorithm can complete a stable matching under a variety of complex conditions, and achieve a steady target tracking under a small part of the block state.

Copyright

© 2015, 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  - Zhaoxia Fu
PY  - 2015/04
DA  - 2015/04
TI  - Multi-target tracking algorithm by corner feature for video stream
BT  - Proceedings of the International Conference on Advances in Mechanical Engineering and Industrial Informatics
PB  - Atlantis Press
SP  - 719
EP  - 722
SN  - 2352-5401
UR  - https://doi.org/10.2991/ameii-15.2015.134
DO  - 10.2991/ameii-15.2015.134
ID  - Fu2015/04
ER  -