A large body of work in image processing and computer vision over the last 10 or 15 years has been concerned with the estimation of motion of pixels between pairs of images. As can be seen from the contents of this book, the motivation of this work is actually quite diverse, with intended applications ranging from data compression to registration of remotely sensed data to robotics and vehicle navigation. In tandem with this diversity of motivation is a diversity of representation of motion information: from optical flow, to affine or other parametric transformations, to 3-D egomotion plus range or other structure. The purpose of this chapter is to describe a common framework within which all of these computations can be represented.
The lower Reuleaux pairs are introduced. These are essentially surfaces which are invariant under some subgroup of rigid body motions. Such a surface can be the matting surface for a mechanical joint. In this way the basic mechanical joints used in robots can be classified. These surfaces turn out to have other applications in robotics. In robot gripping they are exactly the surfaces that cannot be immobilised using frictionless fingers. In robot vision the symmetries of these surfaces are motions which cannot be detected.
Robot Vision B K P Horn Ebook Download
DOWNLOAD: https://miimms.com/2vAaVk
2ff7e9595c
Yorumlar