Introductory Techniques for 3-D Computer VisionSenior/Graduate level courses on computer vision, robot vision and image processing in electrical and computer engineering, mathematics, and computer science departments, and an essential reference for researchers and scientists in the field of computer vision. An applied introduction to modern computer vision, focusing on a set of computational techniques for 3-D imaging. Covers a wide range of fundamental problems encountered within computer vision and provides detailed algorithmic and theoretical solutions for each. Each chapter concentrates on a specific problem and solves it by building on previous results. |
Common terms and phrases
3-D objects 3-D points algorithm Appendix assume assumptions calibration pattern camera model camera reference frame Chapter components computer vision constraints contour coordinates corresponding cross-ratio curvature curve defined derivatives descriptors detection digital images discussion distance edge detector eigenspace eigenvalues ellipse epipolar geometry epipole equations essential matrix estimate extrinsic feature-based Figure focal length Further Readings Gaussian geometric given identified image brightness image center image features image gradient image lines image plane image points Image Processing implementation input intensity images intrinsic parameters invariants iteration Kalman filter kernel linear matching measurements method motion field noise normal Notice object models obtained optical flow output p₁ pair patches pixel planar Problem Statement projection matrix projective transformation range images recognition reconstruction reference frame reflectance map rotation matrix sampling scene segments shape from shading singular value solution solve spatial stereo system surface T₂ translation vector weak-perspective