Active Perception and Robot Vision

Intelligent robotics has become the focus of extensive research activity. This effort has been motivated by the wide variety of applications that can benefit from the developments. These applications often involve mobile robots, multiple robots working and interacting in the same work area, and operations in hazardous environments like nuclear power plants. Applications in the consumer and service sectors are also attracting interest. These applications have highlighted the importance of performance, safety, reliability, and fault tolerance. This volume is a selection of papers from a NATO Advanced Study Institute held in July 1989 with a focus on active perception and robot vision. The papers deal with such issues as motion understanding, 3-D data analysis, error minimization, object and environment modeling, object detection and recognition, parallel and real-time vision, and data fusion. The paradigm underlying the papers is that robotic systems require repeated and hierarchical application of the perception-planning-action cycle. The primary focus of the papers is the perception part of the cycle. Issues related to complete implementations are also discussed.

Motion Understanding Systems.- Reflections on Active (Machine) Vision.- Motion Parameter Estimation Using Correspondence Approach.- Active Vision Through Prediction-Error Minimization.- Representing Scenes Along a Route by a Moving Observer.- Gaze Behaviors for Robotics.- On Focus-of-Attention by Active Focusing.- Active Perception and 3D Object Recognition.- Symbolic Representation of Object Models.- Environment Models and Information Assimilation.- Scene Segmentation in the Framework of Active Perception.- A Neural Network Application for Classifying Surfaces.- Indexing via Color Histograms.- On the Design of Robot Vision Systems.- Parallel Vision.- Towards Parallel Processing of Multisensed Data.- Real-Time Vision for Autonomous and Teleoperated Control of Unmanned Vehicles.- Behavioral Knowledge in Sensor/Data Fusion Systems.- Group-Theoretic Approach to Motion Analysis for 3D Robotic Tracking.- Multi-Sensor Integration for Robots Interacting with Autonomous Objects.- Segmentation of Moving Objects.- Apparent Motions in Three-Dimensional Images.- Efficient Representation and High-Compression Coding of Image Sequences.- A New Paradigm for Computational Stereo.- Smoothing Range Data for Curvature Estimation.- Residual Analysis for Range Image Segmentation and Classification.- Using Curvature Information in the Decomposition and Representation of Planar Curves.- Investigation into Building an Invariant Surface Model from Sparse Data.- Form Features Recognition in a Multi-Level Representation Context.- Orientation and Spatial Occupancy Representations in Shape Analysis.- On Active Contour Models.- Templates and the Hough Transform.- Coefficient Focusing for the Moore-Penrose Associative Memory.- Object Detection in Noisy Images.- Active Feature Localization.- Haptic Perception with a Robot Hand: Requirements and Realization.- Visual Techniques for the Controlled Movement of Docking.- Towards the Development of a Multisensorial Vision System: An Adaptive Approach to the Low-Level Phase.- Attributed Parallel Rewriting in Vision.