13.08.2018 Views

[Studies in Computational Intelligence 481] Artur Babiarz, Robert Bieda, Karol Jędrasiak, Aleksander Nawrat (auth.), Aleksander Nawrat, Zygmunt Kuś (eds.) - Vision Based Systemsfor UAV Applications (2013, Sprin

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

Object Track<strong>in</strong>g for Rapid Camera Movements<br />

<strong>in</strong> 3D Space<br />

<strong>Zygmunt</strong> <strong>Kuś</strong> and <strong>Aleksander</strong> <strong>Nawrat</strong><br />

Abstract. The solution of the camera head control problem was presented <strong>in</strong> the<br />

paper. The ma<strong>in</strong> goal of developed control algorithm is the object track<strong>in</strong>g <strong>in</strong><br />

rapid disturbance conditions. The changes of the helicopter position and orientation<br />

dur<strong>in</strong>g the time of disturbance result <strong>in</strong> los<strong>in</strong>g tracked object from the field of<br />

view. Due to this fact the helicopter control system uses not only the visual <strong>in</strong>formation.<br />

The essence of the proposed solution is to compute the object position<br />

only <strong>in</strong> such time <strong>in</strong>tervals when the object is <strong>in</strong> the center of the image. It allows<br />

the camera head regulators to compensate change of the camera position and set<br />

the camera towards the object. The proposed solution comprises of turn<strong>in</strong>g the<br />

camera head towards the trucked object <strong>in</strong> horizontal and vertical planes. The<br />

appropriate angles were computed on the basis of rangef<strong>in</strong>der data (distance between<br />

the camera and the object) and GPS and IMU data (the camera position and<br />

orientation). Furthermore, examples of the situation when the distortion changes<br />

the helicopter position <strong>in</strong> horizontal and vertical plane were presented <strong>in</strong> the paper.<br />

1 Introduction<br />

<strong>UAV</strong>s which are used to track terrestial objects have a wide range of use. Track<strong>in</strong>g<br />

of such objects results <strong>in</strong> problems with recognition and follow<strong>in</strong>g the object<br />

by the <strong>UAV</strong> [32]. One of the possible solutions of the latter is the use of the<br />

<strong>Zygmunt</strong> <strong>Kuś</strong> ⋅ <strong>Aleksander</strong> <strong>Nawrat</strong><br />

Silesian University of Technology, Institute of Automatic Control,<br />

Akademicka 16, 44-101 Gliwice, Poland<br />

e-mail: {zygmunt.kus,aleksander.nawrat}@polsl.pl<br />

<strong>Aleksander</strong> <strong>Nawrat</strong><br />

Ośrodek Badawczo-Rozwojowy Urządzeń Mechanicznych “OBRUM” sp. z o.o., ul.<br />

Toszecka 102, 44-117 Gliwice, Poland<br />

e-mail: anawrat@obrum.gliwice.pl<br />

A. <strong>Nawrat</strong> and Z. <strong>Kuś</strong> (Eds.): <strong>Vision</strong> <strong>Based</strong> Systems for <strong>UAV</strong> <strong>Applications</strong>, SCI <strong>481</strong>, pp. 57–76.<br />

DOI: 10.1007/978-3-319-00369-6_4 © Spr<strong>in</strong>ger International Publish<strong>in</strong>g Switzerland <strong>2013</strong>

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!