A Drogue Detection Method for Vision-Based Autonomous Aerial Refueling - Multimedia and Signal Processing - page 323

We can see that the drogue is the moving object versus the tanker aircraft during
short period. Our algorithm is to decompose the image sequences generating a
background and the clear drogue region. The proposed method can align the image
sequences for drogue detection in the presence of camera shake under complex
background. The proposed method is able to distinguish drogue from backgrounds
without any background modeling procedure.

4 Conclusion

This paper proposed a drogue detection method for vision-based AAR. The moving
objects are detected as the sparse terms by decomposition. The approach is based on
recent advances in efficient matrix rank minimization that come with theoretical
guarantees. The experiments carried on real AAR video demonstrated that our
proposed method is effective. This approach will be ideal for drogue detection under
complex and uncontrolled scenes. The drawback of the vision-based techniques is the
assumption that all the landmarks are always visible and functional. How to design
reliable feature or landmarks in low visibility conditions, such as in a dark night or in
a foggy environment, will be considered in our future work.

Acknowledgments . This work is supported by the Aviation Science Funds
No.20105153022.

References

1. Mao, W., Eke, F.O.: A survey of the dynamics and control of aircraft during aerial
refueling. Nonlinear Dynamics and Systems Theory 8(4), 375-388 (2008)
2. Chen, C.-I., Stettner, R.: Drogue tracking using 3D flash lidar for autonomous aerial
refueling. In: Proc. SPIE, vol. 8037, p. 80370Q (2011)
3. Valasek, J., Gunnam, K., Kimmett, J., et al.: Vision-based sensor and navigation system
for autonomous air refueling. Journal of Guidance, Control, and Dynamics 28(5), 832-844
(2005)
4. James, D., Theresa, S., John, V., et al.: Boom and receptacle autonomous air refueling
using a visual pressure snake optical sensor. Journal of Guidance, Control, and
Dynamics 30(6), 1753-1769 (2007)
5. Mahboubi, Z., Zico Kolter, J., Wang, T., et al.: Camera-based localization for autonomous
UAV formation flight. In: Proceedings of the AIAA @ Infotech Conference (2011)
6. Giampiero, C., Marcello, R.N., Mario, L.F.: Simulation environment for machine vision
based aerial refueling for UAVs. IEEE Trans. on Aerospace and Electronic Systems 45(1),
138-151 (2009)
7. Tandale, M.D., Bowers, R., Valasek, J.: Trajectory tracking controller for vision-based
probe and drogue autonomous aerial refueling. Journal of Guidance, Control, and
Dynamics 29(4), 846-857 (2006)
8. Soujanya, V., Giampiero, C., Marcello, R., et al.: Addressing corner detection issues for
machine vision based UAV aerial refueling. Machine Vision and Applications 18(5), 261-
273 (2007)