Affiliation:
1. Beihang University
2. Air Force Armament Research Academy
Abstract
This paper presents a real-time optical flow algorithm for a vision-based guidance of an unmanned aerial vehicle (UAV). The optical flow algorithm detects a moving target, and obtains the optical position and optical flow vectors of the target from the image sequence. Then, a vision-based guidance of the UAV is designed to follow the moving target. Additionally, the control law of the imaging seeker uses visual information from the image sequence for target tracking. The method was tested on a 3 degree of freedom (3DOF) dual-rotor UAV with a video camera and the result proved the effectiveness of this method.
Publisher
Trans Tech Publications, Ltd.
Reference5 articles.
1. Manchester, A. Savkin, Optical-flow based Precision Missile Guidance inspired by Honeybee Navigation, Proceedings of the 42nd IEEE Conference on Decision and Control, (2003).
2. M. V. Srinivasan, S. W. Zhang, J. Chahl, E. Barth, and S. Venkatesh, How honeybees make grazing handings on flat surfaces, Biological Cybernetics, vol. 83. pp.171-183, (2000).
3. W. M. Jeffrey, Detection of aircraft in video sequences using a predictive optical flow algorithm, Society of Photo-Optical Instrumentation Engineers, 1999, 38(3): 523–530.
4. G Sasa, S Loncaric, Spatio-temporal image segmentation using optical flow and clustering algorithm, " First Int, l Workshop on Image and Signal Processing and Analysis, Pula, Croatia, 2000, pp.63-68.
5. W. Jacques, Line-of-Sight Rate Estimation and Linearizing Control of an Imaging Seeker in a Tactical Missile Guided by Proportional Navigation, IEEE Trans. Contr. syst. technol., vol. 10(4), pp.556-567, July, (2002).