Издательство Springer, 2006, -349 pp.During the last decade of the twentieth century, computer vision made considerable progress towards consolidation of its fundaments, in particular regarding the treatment of geometry for the evaluation of stereo image pairs and of multi-view image recordings. Scientists thus began to look at basic computer vision solutions – irrespective of the well perceived need to perfect these further – as components which should be explored in a larger context. In 2000, Horst Forster, Head of Division in the Information Society Directorate- General of the European Commission, through his contacts with many computer vision researchers throughout Europe, sensed their readiness to cooperate for the exploration of new grounds in a direction subsequently to become known as ‘cognitive vision.’ Horst Forster succeeded in convincing the European Commission to stimulate cooperation in this direction by funding a four-year program, which encountered an unexpectedly broad response. It has been a privilege for us to have had a glimpse at the unobtrusive, effective engagement of Horst Forster to advance scientific cooperation within the European Union. It is a particular pleasure for us to thank Colette Maloney, who closely cooperated with Horst Forster throughout the past by accompanying the many projects funded under the cognitive vision programme. Her constant encouraging support, her practically instant response to a seemingly endless series of calls for help in organizational and financial matters, and her deep commitment to advancing scientific research in this topical area across Europe made collaboration with her a truly memorable experience. As part of the efforts to further strengthen cooperation between research groups from different countries, a seminar was organized at Schloss Dagstuhl in Germany during October 26–30, 2003. Scientists active in related are as were invited from across the world. This seminar was co-sponsored by ECVision, the Cognitive Vision network of excellence under the leadership of David Vernon. The support from ECVision was instrumental to the organization of this seminar and the creation of this volume. Presentations and associated vivid discussions at the seminar were gradually transformed into a set of contributions to this volume. The editors thank the authors for their considerable efforts to draft, refine, and cross-reference these contributions.Introductory Remarks Part I Foundations of Cognitive Vision Systems The Space of Cognitive Vision Cognitive Vision Needs Attention to Link Sensing with Recognition Organization of Architectures for Cognitive Vision Systems Cognitive Vision Systems: From Ideas to Specifications Part II Recognition and Categorization A System for Object Class Detection Greedy Kernel Principal Component Analysis Many-to-Many Feature Matching in Object Recognition Integrating Video Information over Time. Example: Face Recognition from Video Interleaving Object Categorization and Segmentation Part III Learning and Adaptation Learning an Analysis Strategy for Knowledge-Based Exploration of Scenes Part IV Representation and Inference Things That See: Context-Aware Multi-modal Interaction Hierarchies Relating Topology and Geometry Cognitive Vision: Integrating Symbolic Qualitative Representations with Computer Vision On Scene Interpretation with Description Logics Part V Control and Systems Integration A Framework for Cognitive Vision Systems or Identifying Obstacles to Integration Visual Capabilities in an Interactive Autonomous Robot Part VI Conclusions On Sampling the Spectrum of Approaches Toward Cognitive Vision Systems
Чтобы скачать этот файл зарегистрируйтесь и/или войдите на сайт используя форму сверху.