Algorithm of measurement information processing for hardware and software complex capture and automatic tracking of unmanned aerial vehicle
A. V. Porfiriev, В. И. Сумин, Alexander Valerievich Dushkin · 2017
In this paper we developed the algorithm for the automatic tracking of unmanned aircraft for image sequence based on correlation filtering to improve the efficiency of conducting objective control and simulation in Matlab and C#. The measurement results showed good convergence of the theoretical and experimental data. The advantage of this approach is the possibility to use it in real-time through the application of fast direct and inverse Fourier transform; availability of the implementation in various environments for object-oriented programming such as Visual C#/C using the library of structures and algorithms EmguCV/OpenCV and the libraries of algorithms for fast discrete Fourier transform FFTWSharp/FFTW; the possibility of the approach implementing in the systems with reconfigurable integrated circuits based on programmable logic; “Field programmable gate array” (FPGA); the use of the adaptive approach in the program code design. For further improvement of the algorithm it is appropriate to work in the area of window tracking changes due to the deformation or removal of the object to reduce the computational cost.