From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

The GPU Gems series features a collection of the most essential algorithms required by Next-Generation 3D Engines.Martin Mittring, Lead Graphics Programmer, CrytekThis third volume of the best-selling GPU Gems series provides a snapshot of todays latest Graphics Processing Unit (GPU) programming techniques. The programmability of modern GPUs allows developers to not only distinguish themselves from one another but also to use this awesome processing power for non-graphics applications, such as physics simulation, financial analysis, and even virus detectionparticularly with the CUDA architecture. Graphics remains the leading application for GPUs, and readers will find that the latest algorithms create ultra-realistic characters, better lighting, and post-rendering compositing effects. Major topics includeGeometryLight and ShadowsRenderingImage EffectsPhysics SimulationGPU ComputingContributors are from the following corporations and universities:3DfactoAdobe SystemsAppleBudapest University of Technology and EconomicsCGGVeritasThe Chinese University of Hong KongCornell UniversityCrytekCzech Technical University in PragueDartmouth CollegeDigital Illusions Creative EntertainmentEindhoven University of TechnologyElectronic ArtsHavokHelsinki University of TechnologyImperial College LondonInfinity WardJuniper NetworksLaBRIINRIA, University of Bordeauxmental imagesMicrosoft ResearchMove InteractiveNCsoft CorporationNVIDIA CorporationPerpetual EntertainmentPlaylogic Game FactoryPolytimeRainbow StudiosSEGA CorporationUFRGS (Brazil)Ulm UniversityUniversity of California, DavisUniversity of Central FloridaUniversity of CopenhagenUniversity of GironaUniversity of Illinois at Urbana-ChampaignUniversity of North Carolina Chapel HillUniversity of TokyoUniversity of WaterlooSection Editors include NVIDIA engineers: Cyril Zeller, Evan Hart, Ignacio Castao, Kevin Bjorke, Kevin Myers, and Nolan Goodnight.The accompanying DVD includes complementary examples and sample programs.

GPU Gems 3

User-worn sensing units composed of inertial and magnetic sensors are becoming increasingly popular in various domains, including biomedical engineering, robotics, virtual reality, where they can also be applied for real-time tracking of the orientation of human body parts in the three-dimensional (3D) space. Although they are a promising choice as wearable sensors under many respects, the inertial and magnetic sensors currently in use offer measuring performance that are critical in order to achieve and maintain accurate 3D-orientation estimates, anytime and anywhere. This paper reviews the main sensor fusion and filtering techniques proposed for accurate inertial/magnetic orientation tracking of human body parts; it also gives useful recipes for their actual implementation.

/pdf/estimating-three-dimensional-orientation-of-human-body-parts-2hnncq4qjn.pdf

Estimating Three-Dimensional Orientation of Human Body Parts by Inertial/Magnetic Sensing

A system that has a remote control, e.g., a wand, equipped with a relative motion sensor that outputs data indicative of a change in position of the wand. The system also has one or more light sources and a photodetector that detects their light and outputs data indicative of the detected light. The system uses one or more controllers to determine the absolute position of the wand based on the data output by the relative motion sensor and by the photodetector. The data enables determination of the absolute pose of the wand, which includes the absolute position of a reference point chosen on the wand and the absolute orientation of the wand. To properly express the absolute parameters of position and/or orientation of the wand a reference location is chosen with respect to which the calculations are performed. The system is coupled to a display that shows an image defined by a first and second orthogonal axes such as two axes belonging to world coordinates (X o ,Y o ,Z o ). The one or more controllers are configured to generate signals that are a function of the absolute position of the wand in or along a third axis for rendering the display. To simplify the mapping of a real three-dimensional environment in which the wand is operated to the cyberspace of the application that the system is running, the third axis is preferably the third Cartesian coordinate axis of world coordinates (X o ,Y o ,Z o ).

Computer interface employing a manipulated object with absolute pose detection component and a display

The present invention relates to interfaces and methods for producing input for software applications based on the absolute pose of an item manipulated or worn by a user in a three-dimensional environment. Absolute pose in the sense of the present invention means both the position and the orientation of the item as described in a stable frame defined in that three-dimensional environment. The invention describes how to recover the absolute pose with optical hardware and methods, and how to map at least one of the recovered absolute pose parameters to the three translational and three rotational degrees of freedom available to the item to generate useful input. The applications that can most benefit from the interfaces and methods of the invention involve 3D virtual spaces including augmented reality and mixed reality environments.

Deriving input from six degrees of freedom interfaces

http://homepages.cwi.nl/~robertl/papers/1998/fgcs1/paper.pdf

A survey of computational steering environments

We describe a novel optical tracker algorithm for the tracking of interaction devices in virtual and augmented reality. The tracker uses invariant properties of marker patterns to efficiently identify and reconstruct the pose of these interaction devices. Since invariant properties are sensitive to noise in the 2D marker positions, an offline training session is used to determine deviations in these properties. These deviations are taken into account when searching for the patterns once the tracker is used.

Optical tracking using projective invariant marker pattern properties

The traditional cycle in simulation is to prepare input, execute a simulation, and to visualize the results as a post-processing step. However, more insight and a higher productivity can be achieved if these activities are done simultaneously. This is the underlying idea of Computational Steering: researchers change parameters of their simulation on the y and immediately receive feedback on the eeect. In this paper the Computational Steering Environment, CSE , is described. We discuss the requirements of computational steering environment, its relation with high performance computing and networking, and show an application of its use.

Computational steering

Computational steering is the ultimate goal of interactive simulation: researchers change parameters of their simulation and immediately receive feedback on the effect. We present a general and flexible graphics tool that is part of an environment for computational steering developed at CWI. It enables the researcher to interactively develop his own interface with the simulation. This interface is constructed with 3D parametrized geometric objects. The properties of the objects are parametrized to output data and input parameters of the simulation. The objects visualize the output of the simulation, while the researcher can steer the simulation by direct manipulation of the objects. Several applications of 3D computational steering are presented.

3D computational steering with parametrized geometric objects

We present an affordable optical head tracking system for desktop-like VR/AR environments The generic and specific head tracking requirements for these type of environments are de ned, as well as the relaxations such environments put on head tracking systems The presented head tracker is based on two low-cost, commodity FireWire cameras that track a simple 3D dot pattern It is shown that the tracker provides high accuracy, an update rate of 30 updates per second, a low computational load, and a moderate delay of 66 ms It is competitive to commercially available, moderate-cost head tracking systems yet for substantially lower costs

Jurriaan D. Mulder

Papers

A survey of computational steering environments

Optical tracking using projective invariant marker pattern properties

Computational steering

3D computational steering with parametrized geometric objects

An affordable optical head tracking system for desktop VR/AR systems