Computer Vision - ECCV 2004 计算机视觉

出版时间：2004-6  出版社：北京燕山出版社  作者：Pajdla, Tomas; Matas, Jiri;  页数：613  

内容概要

The four-volume set comprising LNCS volumes 3021/3022/3023/3024 constitutes the refereed proceedings of the 8th European Conference on Computer Vision, ECCV 2004, held in Prague, Czech Republic, in May 2004.    The 190 revised papers presented were carefully reviewed and selected from a total of 555 papers submitted. The four books span the entire range of current issues in computer vision. The papers are organized in topical sections on tracking; feature-based object detection and recognition; geometry; texture; learning and recognition; information-based image processing; scale space, flow, and restoration; 2D shape detection and recognition; and 3D shape representation and reconstruction.

书籍目录

Learning and Recognition  A Constrained Semi-supervised Learning Approach to Data Association  Learning Mixtures of Weighted Tree-Unions by Minimizing Description Length  Decision Theoretic Modeling of Human Facial Displays  Kernel Feature Selection with Side Data Using a Spectral ApproachTracking II  Tracking Articulated Motion Using a Mixture of Autoregressive Models  Novel Skeletal Representation for Articulated Creatures  An Accuracy Certified Augmented Reality System for Therapy GuidancePosters III  3D Human Body Tracking Using Deterministic Temporal Motion Models  Robust Fitting by Adaptive-Scale Residual Consensus  Causal Camera Motion Estimation by Condensation and Robust Statistics Distance Measures  An Adaptive Window Approach for Image Smoothing and Structures Preserving  Extraction of Semantic Dynamic Content from Videos with Probabilistic Motion Models  Are Iterations and Curvature Useful for Tensor Voting?  A Feature-Based Approach for Determining Dense Long Range Correspondences  Combining Geometric-and View-Based Approaches for Articulated Pose Estimation  Shape Matching and Recognition-Informative Features  Generalized Histogram: Empirical Features for Image Matching  Using Generative Models and,Optimization of Low Dimensional  Recognizing Objects in Range Data Using Regional Point Descriptors  Shape Reconstruction from 3D and 2D Data Using PDE-Based Deformable Surfaces  Structure and Motion Problems for Multiple Rigidly Moving Cameras  Detection and Tracking Scheme for Line Scratch Removal in an Image Sequence  Color Constancy Using Local Color Shifts  Image Anisotropic Diffusion Based on Gradient Vector Flow Fields  ……Information-Based Image ProcessingAuthor Index