Pattern Recognition

1. Front Matter

   PDF

2. Motion and Tracking

   1. A 3-Component Inverse Depth Parameterization for Particle Filter SLAM

      • Evren İmre, Marie-Odile Berger

      Pages 1-10

   2. An Efficient Linear Method for the Estimation of Ego-Motion from Optical Flow

      • Florian Raudies, Heiko Neumann

      Pages 11-20

   3. Localised Mixture Models in Region-Based Tracking

      • Christian Schmaltz, Bodo Rosenhahn, Thomas Brox, Joachim Weickert

      Pages 21-30

   4. A Closed-Form Solution for Image Sequence Segmentation with Dynamical Shape Priors

      • Frank R. Schmidt, Daniel Cremers

      Pages 31-40

   5. Markerless 3D Face Tracking

      • Christian Walder, Martin Breidt, Heinrich Bülthoff, Bernhard Schölkopf, Cristóbal Curio

      Pages 41-50

3. Pedestrian Recognition and Automotive Applications

   1. The Stixel World - A Compact Medium Level Representation of the 3D-World

      • Hernán Badino, Uwe Franke, David Pfeiffer

      Pages 51-60

   2. Global Localization of Vehicles Using Local Pole Patterns

      • Claus Brenner

      Pages 61-70

   3. Single-Frame 3D Human Pose Recovery from Multiple Views

      • Michael Hofmann, Dariu M. Gavrila

      Pages 71-80

   4. Dense Stereo-Based ROI Generation for Pedestrian Detection

      • Christoph Gustav Keller, David Fernández Llorca, Dariu M. Gavrila

      Pages 81-90

   5. Pedestrian Detection by Probabilistic Component Assembly

      • Martin Rapus, Stefan Munder, Gregory Baratoff, Joachim Denzler

      Pages 91-100

   6. High-Level Fusion of Depth and Intensity for Pedestrian Classification

      • Marcus Rohrbach, Markus Enzweiler, Dariu M. Gavrila

      Pages 101-110

4. Features

   1. Fast and Accurate 3D Edge Detection for Surface Reconstruction

      • Christian Bähnisch, Peer Stelldinger, Ullrich Köthe

      Pages 111-120

   2. Boosting Shift-Invariant Features

      • Thomas Hörnlein, Bernd Jähne

      Pages 121-130

   3. Harmonic Filters for Generic Feature Detection in 3D

      • Marco Reisert, Hans Burkhardt

      Pages 131-140

   4. Increasing the Dimension of Creativity in Rotation Invariant Feature Design Using 3D Tensorial Harmonics

      • Henrik Skibbe, Marco Reisert, Olaf Ronneberger, Hans Burkhardt

      Pages 141-150

   5. Training for Task Specific Keypoint Detection

      • Christoph Strecha, Albrecht Lindner, Karim Ali, Pascal Fua

      Pages 151-160

   6. Combined GKLT Feature Tracking and Reconstruction for Next Best View Planning

      • Michael Trummer, Christoph Munkelt, Joachim Denzler

      Pages 161-170

5. Single-View and 3D Reconstruction

   1. Non-parametric Single View Reconstruction of Curved Objects Using Convex Optimization

      • Martin R. Oswald, Eno Töppe, Kalin Kolev, Daniel Cremers

      Pages 171-180

   2. Discontinuity-Adaptive Shape from Focus Using a Non-convex Prior

      • Krishnamurthy Ramnath, Ambasamudram N. Rajagopalan

      Pages 181-190

This book constitutes the refereed proceedings of the 31st Symposium of the German Association for Pattern Recognition, DAGM 2009, held in Jena, Germany, in September 2009. The 56 revised full papers were carefully reviewed and selected from numerous submissions. The papers are organized in topical sections on motion and tracking; pedestrian recognition and automotive applications; features; single-view and 3D reconstruction; learning and classification; pattern recognition and estimation; stereo and multi-view reconstruction; image analysis and applications; and segmentation.

• 3d reconstruction
• 3d video
• algorithms
• classification
• depth camera
• face reconstruction
• face tracking
• image analysis
• image segmentation
• motion estimation
• optical flow
• pattern recognition
• scene classification
• stereo vision
• tof camera

• Digitale Bildverarbeitung, Universität Jena, Jena, Germany

  Joachim Denzler, Herbert Süße

• Fraunhofer-Institut für Angewandte Optik und Feinmechanik, Jena, Germany

  Gunther Notni

Policies and ethics