Active Visual Inference of Surface Shape
This monograph is devoted to the problem of inferring geometric information about arbitrarily curved surfaces from visual cues; this is a central problem in computer vision with immediate relevance for robot manipulation and navigation.The author develops computational theories and techniques relating visual information arising from viewer movements to the differential geometry of visible surfaces. The theories developed have been implemented and tested using a real-time tracking system based on deformable contours. Applications of the techniques to geometric modelling, obstacle avoidance, navigation, and object manipulation are presented.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Surface Shape from the Deformation of Apparent Contours
Deformation of Apparent Contours Implementation
5 other sections not shown
Other editions - View all
3D shape affine transformation algorithms analysis apparent contour B-spline snakes component of image Computer Vision concave control points convex cues curve normal curve tangent curved surfaces defined depth determine differential invariants direction edge ego-motion epipolar geometry epipolar parameterisation epipolar plane equations errors extremal boundary figure Gaussian curvature gradient image acceleration image contour image curvature image curve image measurements image motion image plane image position image sequence image velocity field inflection localisation magnitude moving normal component normal curvature object osculating plane parallax parameter curve perspective projection planar principal curvatures problem Proceedings qualitative radius of curvature recover relative image robust s-parameter scene shown smooth space curve spatio-temporal image specularities stereo structure from motion surface curvature surface curves surface geometry surface marking surface normal surface orientation surface shape tangent plane temporal derivative tion translational velocity vector viewer motion viewer translation viewpoint visible surfaces visual motion zero