Bioinspired Robotic Dual-Camera System for High-Resolution Vision
Oliver Tonet, Francesco Focacci, Marco Piccigallo, Lorenza Mattei, Claudio Quaglia, Giuseppe Megali, Barbara Mazzolai, Paolo Dario
- 发表年份
- 2008
- 引用次数
- 13
摘要
<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> Due to the limited resolution of both cameras and displays, acuity of artificial vision systems is currently well below the human eye. Visual acuity, in cameras as well as in animal eyes, can be increased by making smaller receptors or bigger eyes. In some applications, the size of the camera is constrained, so alternative solutions must be sought. This paper presents a robotic dual-camera vision system whose design is inspired by the visual system of jumping spiders (<emphasis emphasistype="italic">Salticidae</emphasis> family). The system is composed of a telephoto camera whose field of view (FOV) can be moved within the larger FOV of a wide-angle camera and allows to form a high-resolution image, i.e., an image with the FOV of the wide-angle camera, yet having the same resolution as the telephoto camera. We describe the design of the robotic system, the direct and inverse kinematics, and the image processing algorithms that allow to build the high-resolution image. Images from experiments are presented, together with a discussion on sources of errors and possible solutions. The system is particularly useful for fixed-camera monitoring or teleoperation applications, such as remote surveillance and minimally invasive surgery. The system achieves seven times higher resolution than typical commercial endoscopes. </para>
关键词
相关论文
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002