Optical flow based system for detection of dynamic objects for uavs

Authors

  • A. Molchanov National Aerospace University “Kharkiv Aviation Institute”
  • V. Kortunov V National Aerospace University “Kharkiv Aviation Institute”

DOI:

https://doi.org/10.18372/2073-4751.1.12793

Keywords:

UAV, autopilot, optical flow, least squares method, the sum of absolute differences, detection of objects, avoidance of obstacles

Abstract

This work presents an optical flow based method for obstacle detection by using a single CCDcamera. Computed optical flow is used to detect dynamic obstacles in front of the camera and toadjust rotor's control to avoid them. The proposed system is based on optical flow estimation with weighted image blocks from the streamed video. Hardware simulation is performed to prove theapplicability of this system. Methods and algorithms described in this paper are versatile enough andcan be implemented for various vehicles with autonomous navigation system. The feasibility of theproposed system for UAVs is discussed

Author Biography

V. Kortunov V, National Aerospace University “Kharkiv Aviation Institute”

Doctor of Sciences

References

P. Chalimbaud, F. Berry, F. Marmoiton, and S. Alizon. Design of a hybrid visuoinertial smart sensor. In Proc. Workshop Integration Vision Inertial Sensors (in conjunction with IEEE Int. Conf. Robotics Automation), 2005.

X. Armangue, H. Araujo, and J. Salvi. Differential epipolar constraint in mobile robot egomotion estimation. In Proc. IEEE Int. Conf. Pattern Recognition, pages 599–602, 2002.

Q. Ke and T. Kanade. Transforming camera geometry to a virtual downwardlooking camera: Robust egomotion estimation and ground-layer detection. In IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), pages I–390– I–397, 2003.

M. Clauss, P. Bayerl, and H. Neumann. Segmentation of independently moving objects using a maximum-likelihood principle. In Proc. Autonome Mobile Systeme, 2005.

F. Woelk and R. Koch. Fast monocular Bayesian detection of independently moving objects by a moving observer. In Proc. DAGM Symposium, 2004.

B. K. P. Horn and B. G. Schunck, “Determining optical flow: a retrospective,” Artificial Intelligence, vol. 59, no. 1–2, pp. 81–87, 1993.

Molchanov A.A., Kortunov V.I. Review of motion parameters estimation methods from optical flow [in Russian]. Radioelectronic and computer systems, National aerospace university «Kharkov aviation insitute» named after M.E. Zhukovskiy, Ukraine, 2013(2), pp. 80-85.

Molchanov A.A., Kortunov V.I. Optical flow motion estimation method based on weighted imaging unit measurement [in Russian]. Information processing systems, Kharkiv University of Air Force University named after Ivan Kozhedub, Ukraine, 2015(1), pp. 26-31.

Published

2017-05-22

Issue

Section

Статті