(Knowledge-based Scene Interpretation)
Wintersemester 2006/7
Bernd Neumann
neumann@informatik.uni-hamburg.de
Aktuelles
| 21.11.06 |
Die Vorlesung am 21.11.06 findet
ausnahmsweise in B-201 statt. |
Lecture 1: Introduction
Contents overview, motivation, aims, problem areas
Lecture 2: Early work on scene interpretation
Badler, Tsotsos, Hogg, Nagel, Neumann
Lecture 3: Basic knowledge representation formalisms
Semantic Networks, Frames, Constraints, Relational Structures
Lecture 4: Conceptual units for scene interpretation
Aggregates, situation trees, scenarios
Lecture 5: Interface to low-level vision
Primitive symbols, grounding
Lecture 6: Modelling spatial and temporal relations
Fuzzy predicates, Allen, RCC8, constraints
Lecture 7: Interpretation procedures
Lecture 8: Logical framework
Model construction, Decription Logics
Lecture 9: Scene interpretation as configuration
Stepwise construction, SCENIC
Lecture 10: Probabilistic Guidance
Hierarchical Bayesian Networks
Lecture 11: Task orientation
Focus of attention, seeing and acting
Lecture 12: Case study
Real-time scenario recognition (Orion/INRIA)
Lecture 13: Application development
Criminal act recognition (Orion/INRIA)
Lecture 14: Summary and outlook
Image Processing, Analysis and Machine Vision
M. Sonka, V. Hlavac, R. Boyle
Chapman & Hall 1993Computer Vision
D.H. Ballard, C.M. Brown
Prentice-Hall 1982<>
Folien zur Vorlesung
Lecture 1: Introduction
Lecture 2: Early Work on Scene Interpretation
Lecture 3: Basic Knowledge Representation Formalisms
Lecture 4: Conceptual Units for Scene Interpretation
Lecture 5: Constraints
Lecture 6: Logics of Image Interpretation and Description Logics
Lecture 7: Using Description Logics for Scene Interpretation
Lecture 8: Scene Interpretation as Configuration
Lecture 9: Probabilistic Models for Scene Interpretation
Lecture 10: Mobile Robot Localization
Lecture 11: Case Study: Video-based Event Detection