Tyler Computer Vision

From Surfaces to 3D Objects
Erscheinungsjahr 2011
ISBN: 978-1-4398-1713-1
Verlag: Taylor & Francis
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 292 Seiten

The typical computational approach to object understanding derives shape information from the 2D outline of the objects. For complex object structures, however, such a planar approach cannot determine object shape; the structural edges have to be encoded in terms of their full 3D spatial configuration. Computer Vision: From Surfaces to 3D Objects is the first book to take a full approach to the challenging issue of veridical 3D object representation. It introduces mathematical and conceptual advances that offer an unprecedented framework for analyzing the complex scene structure of the world.

An Unprecedented Framework for Complex Object Representation
Presenting the material from both computational and neural implementation perspectives, the book covers novel analytic techniques for all levels of the surface representation problem. The cutting-edge contributions in this work run the gamut from the basic issue of the ground plane for surface estimation through mid-level analyses of surface segmentation processes to complex Riemannian space methods for representing and evaluating surfaces.

State-of-the-Art 3D Surface and Object Representation
This well-illustrated book takes a fresh look at the issue of 3D object representation. It provides a comprehensive survey of current approaches to the computational reconstruction of surface structure in the visual scene.

Zielgruppe

Professionals in computer vision and graphics, computational modeling, pattern recognition, artificial intelligence, and image processing; computational neuroscientists; graduate students in computer science.

Autoren/Hrsg.

Tyler, Christopher W.

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Computer Vision

Inhaltsverzeichnis

Introduction: The Role of Mid-Level Surface Representation in 3D Object Encoding
Scene Statistics and 3D Surface Perception, Brian Potetz and Tai Sing Lee
Active Segmentation, Ajay Mishra and Yiannis Aloimonos
Mechanisms for Propagating Surface Information in 3D Reconstruction, James Coughlan
3D Surface Representation Using Ricci Flow, Wei Zeng, Feng Luo, Shing-Tung Yau, and David Xianfeng Gu
Cue Interpretation and Propagation: Flat versus Nonflat Visual Surfaces, Volodymyr Ivanchenko
Symmetry, Shape, Surfaces, and Objects, Tadamasa Sawada, Yunfeng Li, and Zygmunt Pizlo
Noncommutative Field Theory in the Primary Visual Cortex, Alessandro Sarti and Giovanna Citti
Contour-, Surface-, and Object-Related Coding in the Visual Cortex, Rüdiger von der Heydt
From Surfaces to Objects: A Neuroanalytic Approach, Christopher W. Tyler and Lora T. Likova
3D and Spatiotemporal Interpolation in Object and Surface Formation, Philip J. Kellman, Patrick Garrigan, and Evan Palmer
The Perceptual Representation of 3D Shape, James T. Todd
References
Index

Über Autor(innen)

Christopher W. Tyler is the director of the Brain Imaging Center at the Smith-Kettlewell Eye Research Institute. His current research encompasses brain imaging studies and mathematical modeling of the mechanisms of human stereoscopic depth, motion, and face perception as well as higher cognitive processing. He and his team have developed new methods to determine the dynamics of the neural population responses underlying brain imaging signals. By designing stimuli to probe specific neural sub-populations, this new methodology can be used to explore neural properties in the human brain and the changes in neural dynamics during the learning process.