Any Object Tracking and Following by a Flying Drone

被引:21
作者
Bartak, Roman [1 ]
Vyskovsky, Adam [1 ]
机构
[1] Charles Univ Prague, Fac Math & Phys, Malostranske Namesti 25, Prague 1, Czech Republic
来源
2015 FOURTEENTH MEXICAN INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (MICAI) | 2015年
关键词
D O I
10.1109/MICAI.2015.12
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
AR. Drone is a quadcopter with onboard sensors including a frontal camera. The drone can be controlled from a computer via WiFi. This paper describes a method for autonomous tracking of a selected object by AR. Drone. We utilize a computer-vision approach called tracking-learning-detection (TLD) to track an arbitrary object selected by a user in the videostream going from the front camera of the drone. Information about location of the tracked object is then used to guide the drone using the proportional-integral-derivative (PID) controller. The method was implemented in software FollowMe.
引用
收藏
页码:35 / 41
页数:7
相关论文
共 8 条
  • [1] [Anonymous], 1981, INT C ARTIFICIAL INT
  • [2] Chi-Tinh Dang, 2013, 2013 International Conference on Control, Automation and Information Sciences (ICCAIS), P146, DOI 10.1109/ICCAIS.2013.6720545
  • [3] Kalal Z., 2011, THESIS
  • [4] King M., 2010, Process Control: A Practical Approach
  • [5] Matzner F., 2014, THESIS
  • [6] Pestana J., 2013, P AM CONTR C ACC, P1886
  • [7] Szeliski R, 2011, TEXTS COMPUT SCI, P1, DOI 10.1007/978-1-84882-935-0
  • [8] Vyskovsky A., 2014, THESIS