Computer Vision - ECCV 2002 7th European Conference on Computer Vision, Copenhagen, Denmark, May 28-31, 2002, Proceedings, Part III /

• Συγγραφή απο Οργανισμό/Αρχή: SpringerLink (Online service)
• Άλλοι συγγραφείς: Heyden, Anders (Επιμελητής έκδοσης, http://id.loc.gov/vocabulary/relators/edt), Sparr, Gunnar (Επιμελητής έκδοσης, http://id.loc.gov/vocabulary/relators/edt), Nielsen, Mads (Επιμελητής έκδοσης, http://id.loc.gov/vocabulary/relators/edt), Johansen, Peters (Επιμελητής έκδοσης, http://id.loc.gov/vocabulary/relators/edt)
• Μορφή: Ηλεκτρονική πηγή Ηλ. βιβλίο
• Γλώσσα: English
• Έκδοση: Berlin, Heidelberg : Springer Berlin Heidelberg : Imprint: Springer, 2002.
• Έκδοση: 1st ed. 2002.
• Σειρά: Lecture Notes in Computer Science, 2352
• Θέματα: Optical data processing.; Computer graphics.; Pattern recognition.; Artificial intelligence.; Image Processing and Computer Vision.; Computer Graphics.; Pattern Recognition.; Artificial Intelligence.

 Premiering in 1990 in Antibes, France, the European Conference on Computer Vision, ECCV, has been held biennially at venues all around Europe. These conferences have been very successful, making ECCV a major event to the computer vision community. ECCV 2002 was the seventh in the series. The privilege of organizing it was shared by three universities: The IT University of Copenhagen, the University of Copenhagen, and Lund University, with the conference venue in Copenhagen. These universities lie ¨ geographically close in the vivid Oresund region, which lies partly in Denmark and partly in Sweden, with the newly built bridge (opened summer 2000) crossing the sound that formerly divided the countries. We are very happy to report that this year's conference attracted more papers than ever before, with around 600 submissions. Still, together with the conference board, we decided to keep the tradition of holding ECCV as a single track conference. Each paper was anonymously refereed by three different reviewers. For the nal selection, for the rst time for ECCV, a system with area chairs was used. These met with the program chairsinLundfortwodaysinFebruary2002toselectwhatbecame45oralpresentations and 181 posters.Also at this meeting the selection was made without knowledge of the authors'identity. 

 Shape -- 3D Statistical Shape Models Using Direct Optimisation of Description Length -- Approximate Thin Plate Spline Mappings -- DEFORMOTION Deforming Motion, Shape Average and the Joint Registration and Segmentation of Images -- Region Matching with Missing Parts -- Stereoscopic Vision I -- What Energy Functions Can Be Minimized via Graph Cuts? -- Multi-camera Scene Reconstruction via Graph Cuts -- A Markov Chain Monte Carlo Approach to Stereovision -- A Probabilistic Theory of Occupancy and Emptiness -- Texture Shading and Colour / Grouping and Segmentation / Object Recognition -- Texture Similarity Measure Using Kullback-Leibler Divergence between Gamma Distributions -- All the Images of an Outdoor Scene -- Recovery of Reflectances and Varying Illuminants from Multiple Views -- Composite Texture Descriptions -- Constructing Illumination Image Basis from Object Motion -- Diffuse-Specular Separation and Depth Recovery from Image Sequences -- Shape from Texture without Boundaries -- Statistical Modeling of Texture Sketch -- Classifying Images of Materials: Achieving Viewpoint and Illumination Independence -- Estimation of Multiple Illuminants from a Single Image of Arbitrary Known Geometry -- The Effect of Illuminant Rotation on Texture Filters: Lissajous's Ellipses -- On Affine Invariant Clustering and Automatic Cast Listing in Movies -- Factorial Markov Random Fields -- Evaluation and Selection of Models for Motion Segmentation -- Surface Extraction from Volumetric Images Using Deformable Meshes: A Comparative Study -- DREAM2S: Deformable Regions Driven by an Eulerian Accurate Minimization Method for Image and Video Segmentation -- Neuro-Fuzzy Shadow Filter -- Parsing Images into Region and Curve Processes -- Yet Another Survey on Image Segmentation: Region and Boundary Information Integration -- Perceptual Grouping from Motion Cues Using Tensor Voting in 4-D -- Deformable Model with Non-euclidean Metrics -- Finding Deformable Shapes Using Loopy Belief Propagation -- Probabilistic and Voting Approaches to Cue Integration for Figure-Ground Segmentation -- Bayesian Estimation of Layers from Multiple Images -- A Stochastic Algorithm for 3D Scene Segmentation and Reconstruction -- Normalized Gradient Vector Diffusion and Image Segmentation -- Spectral Partitioning with Indefinite Kernels Using the Nyström Extension -- A Framework for High-Level Feedback to Adaptive, Per-Pixel, Mixture-of-Gaussian Background Models -- Multivariate Saddle Point Detection for Statistical Clustering -- Parametric Distributional Clustering for Image Segmentation -- Probabalistic Models and Informative Subspaces for Audiovisual Correspondence -- Volterra Filtering of Noisy Images of Curves -- Image Segmentation by Flexible Models Based on Robust Regularized Networks -- Principal Component Analysis over Continuous Subspaces and Intersection of Half-Spaces -- On Pencils of Tangent Planes and the Recognition of Smooth 3D Shapes from Silhouettes -- Estimating Human Body Configurations Using Shape Context Matching -- Probabilistic Human Recognition from Video -- SoftPOSIT: Simultaneous Pose and Correspondence Determination -- A Pseudo-Metric for Weighted Point Sets -- Shock-Based Indexing into Large Shape Databases -- EigenSegments: A Spatio-Temporal Decomposition of an Ensemble of Images -- On the Representation and Matching of Qualitative Shape at Multiple Scales -- Combining Simple Discriminators for Object Discrimination -- Probabilistic Search for Object Segmentation and Recognition -- Real-Time Interactive Path Extraction with On-the-Fly Adaptation of the External Forces -- Matching and Embedding through Edit-Union of Trees -- A Comparison of Search Strategies for Geometric Branch and Bound Algorithms -- Face Recognition from Long-Term Observations -- Stereoscopic Vision II -- Helmholtz Stereopsis: Exploiting Reciprocity for Surface Reconstruction -- Minimal Surfaces for Stereo -- Finding the Largest Unambiguous Component of Stereo Matching.