Affiliation of Author(s):计算机科学与技术学院/人工智能学院/软件学院

Journal:INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING - IDEAL 2017

Key Words:Unmanned aerial vehicles Target tracking CamShift

Abstract:Unmanned aerial vehicles (UAVs) equipped with monitoring systems have played an important role in various fields in recent years. An object tracking algorithm is necessary in order to process information in the wide range of UAV videos. CamShift algorithm is outstanding as its efficient pattern matching and fast convergence. This paper presents an excellent method based on CamShift to implement precise target tracking in UAV videos. This method integrates multi-feature fusion (MF), CamShift, and Kalman filter (KF) called the MF-KF-Camshift algorithm. Experimental results show that the method achieves great performance in dealing with different scenes and meets the real-time requirements.

ISSN No.:0302-9743

Translation or Not:no

Date of Publication:2017-01-01

Co-author:Zhao, Chang,Zheng, Huiting

Correspondence Author:Yuan Jiabing