Open Access Open Access  Restricted Access Subscription Access

Camera Locking Algorithm for Target Follower Function on Quadrotor

K. Muljowidodo, Mohammad A. Rasyid

Abstract


We present a design of vision based target follower system for mini unmanned vehicle, quadrotor. The proposed system is used to test the performance of quadrotor autopilot system for an autonomous task such as following a moving target. The system must be able to detect and lock
a moving target while a quadrotor follows the target movement. A camera is fixed in quadrotor facing to the ground to capture images of the moving target. Images is processed by a computer to acquire the position of the target relative to quadrotor position. Quadrotor is controlled so its position is always above the target. The target is recognized and detected by image processing using blob detection algorithm. A computer is used to do this image processing task. A simple target is used for this first experiment.

Full Text:

PDF

References


Bibby, C. Fast Feature with a Graphics Processing Unit Implementation. In

Paper, Dept of Engineering Science University of Oxford.

Fleyeh, H. Traffic and Road Sign Recognition. In thesis, Napier University, 2008.

D. G. Lowe. Distinctive image features from scale-invariant keypoints. In

International Journal of Computer Vision, 2004.

J. Matas, O. Chum, M. Urban, and T. Pajdla. Robust wide baseline stereo from maximally stable extremal regions. In Proc. of British Machine Vision

Conference, pages 384–396,2002.




DOI: http://dx.doi.org/10.21535%2FProICIUS.2010.v6.519

Refbacks

  • There are currently no refbacks.