Computer Vision - Eccv 90: First European Conference on Computer Vision. Antibes, France, April 23-27, 1990. Proceedings

ISBN-13: 9783540525226 / Angielski / Miękka / 1990 / 620 str.

Olivier Faugeras

Opis

Contains a collection of papers on computer vision research in Europe, along with sections on image features, stereo and reconstruction, optical flow, motion, structure from motion, tracking, stereo and motion, features and shape, shape description, and recognition and matching.

Spis treści

On scale and resolution in the analysis of local image structure.- Optimal filter for edge detection methods and results.- Biased anisotropic diffusion—A unified regularization and diffusion approach to edge detection.- Hierarchical image analysis using irregular tessellations.- A bit plane architecture for an image analysis processor implemented with P.L.C.A. gate array.- Scale-space singularities.- Recursive filtering and edge closing: Two primary tools for 3D edge detection.- Edge contours using multiple scales.- Stereo integration, mean field theory and psychophysics.- A pyramidal stereovision algorithm based on contour chain points.- Parallel and deterministic algorithms from MRFs: Surface reconstruction and integration.- Parallel multiscale stereo matching using adaptive smoothing.- On the motion of 3D curves and its relationship to optical flow.- Structure-from-motion under orthographic projection.- Parallel computation of optic flow.- Obstacle detection by evaluation of optical flow fields from image sequences.- Extending the ‘Oriented smoothness constraint’ into the temporal domain and the estimation of derivatives of optical flow.- A comparison of stochastic and deterministic solution methods in Bayesian estimation of 2-D motion.- Motion determination in space-time images.- Ambiguity in reconstruction from image correspondences.- An optimal solution for mobile camera calibration.- Analytical results on error sensitivity of motion estimation from two views.- On the estimation of depth from motion using an anthropomrphic visual sensor.- The derivation of qualitative information in motion analysis.- Road following algorithm using a panned plan-view transformation.- 3D-vision-based robot navigation: First steps.- Dynamic world modeling using vertical line stereo.- Tracking in a complex visual environment.- Tracking line segments.- Measurement and integration of 3-D structures by tracking edge lines.- Estimation of 3D-motion and structure from tracking 2D-lines in a sequence of images.- The incremental rigidity scheme for structure from motion: The line-based formulation.- Object detection using model based prediction and motion parallax.- Detection and tracking of moving objects based on a statistical regularization method in space and time.- Vertical and horizontal disparities from phase.- Stereo correspondence from optic flow.- A model for the estimate of local velocity.- Direct evidence for occlusion in stereo and motion.- On the use of trajectory information to assist stereopsis in a dynamic environment.- Distributed learning of texture classification.- Fast shape from shading.- Inverse perspective of a triangle: New exact and approximate solutions.- Finding geometric and relational structures in an image.- Recovery of volumetric object descriptions from laser rangefinder images.- Extraction of deformable part models.- Toward a computational theory of shape: An overview.- Stabilized solution for 3-D model parameters.- Deformable templates for feature extraction from medical images.- Charting surface structure.- Projectively invariant representations using implicit algebraic curves.- Shape from contour using symmetries.- Using occluding contours for 3D object modeling.- Robust estimation of surface curvature from deformation of apparent contours.- Spatial localization of modelled objects of revolution in monocular perspective vision.- On the verification of hypothesized matches in model-based recognition.- Object recognition using local geometric constraints: A robust alternative to tree-search.- Simd geometric matching.- A 3D interpretation system based on consistent labeling of a set of propositions. Application to the interpretation of straight line correspondences.- Model-based object recognition by geometric hashing.- An analysis of knowledge representation schemes for high level vision.- Experiments on the use of the ATMS to label features for object recognition.- The combinatorics of heuristic search termination for object recognition in cluttered environments.- Combinatorial characterization of perspective projections from polyhedral object scenes.- Estimation of curvature in 3D images using tensor field filtering.- Transparent-motion analysis.- Snake growing.- Local cross-modality image alignment using unsupervised learning.- A heterogeneous vision architecture.- Spatial context in an image analysis system.- Object detection and identification by hierarchical segmentation.- Shading into texture and texture into shading: An active approach.- 3-D curve matching using splines.- The dynamic generalized hough transform.- The analysis of time varying image sequences.- On the use of motion concepts for top-down control in traffic scenes.- Final steps towards real time trinocular stereovision.- B-spline contour representation and symmetry detection.- Shape and mutual cross-ratios with applications to exterior, interior and relative orientation.- Using neural networks to learn shape decomposition by successive prototypication.- Adapting computer vision systems to the visual environment: Topographic mapping.- Stereo matching based on a combination of simple features used for matching in temporal image sequences.