Ebook: Current Advancements in Stereo Vision

Издательство InTech, 2012, -236 pp.Computer vision is one of the most studied subjects of recent times with paramount focus on stereo vision. Lot of activities in the context of stereo vision are getting reported spanning over vast research spectrum including novel mathematical ideas, new theoretical aspects, state of the art techniques and diverse range of applications. The book is a new edition of stereo vision book series of INTECH Open Access Publisher and it presents diverse range of ideas and applications highlighting current research/technology trends and advances in the field of stereo vision. The topics covered in this book include fundamental theoretical aspects of robust stereo correspondence estimation, novel and robust algorithms, hardware implementation for fast execution and applications in wide range of disciplines.
The book consists of 10 chapters addressing different aspects of stereo vision. Research work presented in these chapters either tries to establish the correspondence problem from a unique perspective or establish new constraints to keep the estimation process robust. First four chapters discuss correspondence estimation problem from theoretical perspective. Particularly interesting approaches include neuromorphic engineering, probabilistic analysis and anisotropic reaction diffusion to address the problem of stereo correspondence problem. Stereo algorithm with anisotropic reaction-diffusion systems utilizing biologically motivated reaction-diffusion systems with anisotropic diffusion coefficients makes it an interesting addition to the book. Chapters 5 to 7 present techniques to estimate depth from single and multiple stereo views as well as current commercial trends in adopting this technology for enhanced visualisation throughout audio-visual communications.
Chapters 8 to 10 present the applications of stereo vision for mobile robotics and terrain mapping for autonomous navigation. This section also presents novel wavefront/systolic algorithms for very low power parallel implementation of Sum of Squared Differences (SSD) and Sum of Absolute Differences (SAD) for obstacle avoidance computations on an innovative MIMD parallel architecture.
In summary this book comprehensively covers almost all aspects of stereo vision and highlights the current trends. Diverse range of topics covered in this book, from fundamental theoretical aspects to novel algorithms and diverse range of applications, makes it equally essential for establishing researchers as well as experts in the field.Stereo Matching: From the Basis to Neuromorphic Engineering
Stereo Vision and Scene Segmentation
Probabilistic Analysis of Projected Features in Binocular Stereo
Stereo Algorithm with Anisotropic Reaction-Diffusion Systems
Depth Estimation – An Introduction
An Overview of Three-Dimensional Videos: 3D Content Creation, 3D Representation and Visualization
Generation of 3D Sparse Feature Models Using Multiple Stereo Views
Objects Detection and Tracking Using Points Cloud Reconstructed from Linear Stereo Vision
3D Probabilistic Occupancy Grid to Robotic Mapping with Stereo Vision
Wavefront/Systolic Algorithms for Implementation of Stereo Vision and Obstacle Avoidance Computations on a Very Low Power MIMD Many-Core Parallel Architecture: Applications for Mobile Systems and Wearable Visual Guidance