Recent Developments in Computer Vision: Second Asian Conference on Computer Vision, ACCV `95, Singapore, December 5-8, 1995. Invited Session Papers

ISBN-13: 9783540607939 / Angielski / Miękka / 1996 / 612 str.

Stan Li;Dinesh Mital;Eam K. Teoh

Opis

This book contains the invited reviewed session papers solicited for presentation as key papers at the Second Asian Conference on Computer Vision, ACCV '95, held in December 1995 in Singapore.
The fifteen leading researchers acting as session organizers at the ACCV '95 solicited and reviewed a unique collection of 56 invited papers presented in this volume. Together, these papers competently reflect the state-of-the-art developments in computer vision and image processing; the author index of the volume reads like a who-is-who in the field. The papers are devoted to both theoretical and practical issues relevant to researchers and professionals in the area.

Spis treści

Digital libraries: Meeting place for high-level and low-level vision.- Computer vision in next generation image and video coding.- Video annotation: Computers watching video.- Video representations.- Analysis of left ventricular motion.- Applications of computer vision in space robotics.- Optical-flow estimation while preserving its discontinuities: A variational approach.- Space- and time-variant estimation approaches and the segmentation of the resulting optical flow fields.- Combining the hough transform and multiresolution MRF's for the robust motion estimation.- Direct model-based image motion segmentation for dynamic scene analysis.- Modeling structured environments using robot vision.- Design trade-offs for real-time block-matching motion estimation algorithms.- Pixel matching and motion segmentation in image sequences.- On the motion problem of a rigid planar patch and its invariance.- Virtual space teleconferencing: Real-time detection and reproduction of 3D face and body images.- High-performance tracking with TRICLOPS.- Developing an active observer.- Active stereo vision system with foveated wide angle lenses.- A control theoretical approach to active vision.- Active rangefinding and recognition with Cubicscope.- Real-time vision is not frame-rate image analysis.- Active vision based stereo vision.- Motion of a stereo rig: Strong, weak and self calibration.- Color stereo vision: Use of appearance constraint and epipolar geometry for feature matching.- Unifying stereo, motion and object recognition via epipolar geometry.- Constructing a visual memory in terms of uniqueness.- Statistical models & algorithms for tomography.- Shape statistics and image analysis.- Cluster Monte Carlo algorithms and their applications.- Gibbs sampler and maximum likelihood estimation for unsupervised image segmentations.- Lane boundary detection using deformable templates: Effects of image subsampling on detected lane edges.- Clique finding relaxation labeling networks.- Rectifying structural matching errors.- Parallel distributed relaxation labeling.- Subgraph isomorphism detection in polynomial time on preprocessed model graphs.- Line postprocessing using probabilistic relaxation and relative measurements.- Multiple-view geometry and photometry.- Euclidean 3D reconstruction from stereo sequences with variable focal lengths.- Characterizing the stability of 3D invariants derived from 3D translational symmetry.- MORSE: An architecture for 3D object recognition based on invariants.- Finding human faces with a Gaussian mixture distribution-based face model.- Handwriting recognition.- An integrated model for evaluating the amount of data required for reliable recognition.- 3D object recognition using bidirectional modular networks.- A region extension method for natural outdoor scene interpretation.- Image processing techniques for crowd density estimation using a reference image.- Autonomous road vehicle guidance in normal traffic.- Evaluation of image sequences from outdoor scenes: Selected problems and solutions.- Vehicle localisation and discrimination in outdoor traffic scenes.- SWIM: A prototype environment for visual media retrieval.- Video segment indexing through classification and interactive view-based query.- View-based techniques for searching for objects and textures.- Graph grammar based object recognition for image retrieval.- Similarity matching.- A document image analysis and recognition system for Japanese family registration.- Applying handwriting recognition to US census forms.