Machine Learning Using Template Matching Applied to Object Tracking in Video Data

被引：3

作者：

Zuehlke, David A. ^{[1
]}

Henderson, Troy A. ^{[1
]}

McMullen, Sonya A. H. ^{[2
]}

机构：

[1] Embry Riddle Aeronaut Univ, Dept Aerosp Engn, 600 S Clyde Morris Blvd, Daytona Beach, FL 32114 USA

[2] T2S Solut LLC, 4685 Millennium Dr, Belcamp, MD 21017 USA

来源：

ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR MULTI-DOMAIN OPERATIONS APPLICATIONS | 2019年 / 11006卷

关键词：

Template matching; object tracking; image processing;

D O I：

10.1117/12.2518982

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents the algorithms for tracking a moving object through video data using template matching. As the object translates and rotates, the template is adaptively updated so that the object is never lost while in frame. The algorithms were developed in MATLAB and applied to a video of a quadcopter in flight in both visible and infrared imagery. The normalized cross-correlation algorithm is the core of the research, providing an invariant of scale method to perform the template match. Then a bounding box is applied to the matched area and center of mass centroiding allow the object to be tracked frame-to-frame.

引用

页数：7