Computer Vision Systems: 7th International Conference on Computer Vision Systems, ICVS 2009 Liège, Belgium, October 13-15, 2009, Proceedings(5815 Lecture Notes in Computer Science)

This book constitutes the refereed proceedings of the 7th International Conference on Computer Vision Systems, ICVS 2009, held in Liege, Belgium, October 13-15, 2009. The 21 papers for oral presentation presented together with 24 poster presentations and 2 invited papers were carefully reviewed and selected from 96 submissions. The papers are organized in topical sections on human-machine-interaction, sensors, features and representations, stereo, 3D and optical flow, calibration and registration, mobile and autonomous systems, evaluation, studies and applications, learning, recognition and adaption.

Table of Contents:
Human-Machine Interaction.- Recognizing Gestures for Virtual and Real World Interaction.- Multimodal Speaker Recognition in a Conversation Scenario.- FaceL: Facile Face Labeling.- Automatic Assessment of Eye Blinking Patterns through Statistical Shape Models.- Open-Set Face Recognition-Based Visitor Interface System.- Cascade Classifier Using Divided CoHOG Features for Rapid Pedestrian Detection.- Sensors, Features and Representations.- Boosting with a Joint Feature Pool from Different Sensors.- A Multi-modal Attention System for Smart Environments.- Individual Identification Using Gait Sequences under Different Covariate Factors.- Using Local Symmetry for Landmark Selection.- Combining Color, Depth, and Motion for Video Segmentation.- Stable Structural Deformations.- Demand-Driven Visual Information Acquisition.- Stereo, 3D and Optical Flow.- A Real-Time Low-Power Stereo Vision Engine Using Semi-Global Matching.- Feature-Based Stereo Vision Using Smart Cameras for Traffic Surveillance.- Development and Long-Term Verification of Stereo Vision Sensor System for Controlling Safety at Railroad Crossing.- Generation of 3D City Models Using Domain-Specific Information Fusion.- Bio-inspired Stereo Vision System with Silicon Retina Imagers.- A Fast Joint Bioinspired Algorithm for Optic Flow and Two-Dimensional Disparity Estimation.- Calibration and Registration.- GPU-Accelerated Nearest Neighbor Search for 3D Registration.- Visual Registration Method for a Low Cost Robot.- Automatic Classification of Image Registration Problems.- Practical Pan-Tilt-Zoom-Focus Camera Calibration for Augmented Reality.- Mobile and Autonomous Systems.- Learning Objects and Grasp Affordances through Autonomous Exploration.- Integration of Visual Cues for Robotic Grasping.- A Hierarchical System Integration Approach with Application to Visual Scene Exploration for Driver Assistance.- Real-Time Traversable Surface Detection by Colour Space Fusion and Temporal Analysis.- Saliency-Based Obstacle Detection and Ground-Plane Estimation for Off-Road Vehicles.- Performance Evaluation of Stereo Algorithms for Automotive Applications.- Evaluation, Studies and Applications.- White-Box Evaluation of Computer Vision Algorithms through Explicit Decision-Making.- Evaluating the Suitability of Feature Detectors for Automatic Image Orientation Systems.- Interest Point Stability Prediction.- Relevance of Interest Points for Eye Position Prediction on Videos.- A Computer Vision System for Visual Grape Grading in Wine Cellars.- Inspection of Stamped Sheet Metal Car Parts Using a Multiresolution Image Fusion Technique.- Who’s Counting? Real-Time Blackjack Monitoring for Card Counting Detection.- Learning, Recognition and Adaptation.- Increasing the Robustness of 2D Active Appearance Models for Real-World Applications.- Learning Query-Dependent Distance Metrics for Interactive Image Retrieval.- Consistent Interpretation of Image Sequences to Improve Object Models on the Fly.- Nonideal Iris Recognition Using Level Set Approach and Coalitional Game Theory.- Incremental Video Event Learning.- A System for Probabilistic Joint 3D Head Tracking and Pose Estimation in Low-Resolution, Multi-view Environments.- Robust Tracking by Means of Template Adaptation with Drift Correction.- A Multiple Hypothesis Approach for a Ball Tracking System.- Fast Vision-Based Object Recognition Using Combined Integral Map.