Fast Compressive Tracking based on Adaptively Learning Scheme

DOI

10.2991/mecae-17.2017.8How to use a DOI?

Keywords

Compressed Sensing, Target Tracking, Real-Time, Adaptively Learning.

Abstract

In this paper, we proposed a fast compressive tracking algorithm based on adaptively learning scheme (FCTAL). First, we designed a special nonlinear model for updating the learning parameter of na‹ve Bayes classifier. Second, we improved the target position decision strategy from FCT for getting it refrain from the single maximum classifier response value. Experimental results demonstrated that FCTAL can not only achieve a greater tracking accuracy than FCT and other three compared tracking algorithms on video frame sequences from Background Clutters & Low Resolution (BC&LR) and Fast Motion & Motion Blur (FM&MB) but also meet the requirements of real-time applications.

Copyright

© 2017, 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  - Ling Gan
AU  - Jian Ding
PY  - 2017/03
DA  - 2017/03
TI  - Fast Compressive Tracking based on Adaptively Learning Scheme
BT  - Proceedings of the 2017 International Conference on Mechanical, Electronic, Control and Automation Engineering (MECAE 2017)
PB  - Atlantis Press
SP  - 43
EP  - 50
SN  - 2352-5401
UR  - https://doi.org/10.2991/mecae-17.2017.8
DO  - 10.2991/mecae-17.2017.8
ID  - Gan2017/03
ER  -