A comprehensive survey of computer vision-based human motion capture literature from the past two decades is presented. The focus is on a general overview based on a taxonomy of system functionalities, broken down into four processes: initialization, tracking, pose estimation, and recognition. Each process is discussed and divided into subprocesses and/or categories of methods to provide a reference to describe and compare the more than 130 publications covered by the survey. References are included throughout the paper to exemplify important issues and their relations to the various methods. A number of general assumptions used in this research field are identified and the character of these assumptions indicates that the research field is still in an early stage of development. To evaluate the state of the art, the major application areas are identified and performances are analyzed in light of the methods

. This paper presents a new approach to model general interactions between virtual human agents and objects in virtual worlds. The proposed framework is designed to deal with many of the possible interactions that may arise while simulating a virtual human performing common tasks in a virtual environment. The idea is to include within the object description, all the necessary information to describe how to interact with it. For this, a feature modeling approach is used, by means of a graphical user interface program, to identify object interaction features. Moving parts, functionality instructions and interaction locations are examples of some considered features. Following this approach, the control of the simulation is decentralized from the main animation control, in the sense that some local instructions on how to deal with the object are encapsulated within the object itself. To illustrate the approach, some examples are shown and discussed. 1 Introduction The necessity to model...

This paper shows a new approach to model and control interactive objects for simulations with virtual human agents when real time interactivity is essential. A general conceptualization is made to model objects with behaviors that can provide: information about their functionality, changes in appearance from parameterized deformations, and a complete plan for each possible interaction with a virtual human. Such behaviors are described with simple primitive commands, following the actual trend of many standard scene graph file formats that connects language with movements and events to create interactive animations. In our case, special attention is given to correctly interpret object behaviors in parallel: situation that arrives when many human agents interact at the same time with one same object. Keywords: Virtual Humans, Virtual Environments, Object Modeling, Object Interaction, Script Languages, Parameterized Deformations. 1 Introduction The necessity to have interactive obje...

The purpose of this paper is to show the importance of Virtual Humans in Virtual Reality and to identify the main problems to solve to create believable Virtual Humans.

In this paper, we present SimHuman, a platform for the generation of real-time 3D environments with virtual agents. SimHuman is highly dynamic and configurable, as it is not based on fixed scenes and models, and has an embedded physically based modelling engine. Its agents can use features such as path finding, inverse kinematics and planning to achieve their goals. The paper explains in detail design and implementation issues and presents the architecture of the system as well as an illustrative example.

Video analysis of human dynamics is an important area of research devoted to detecting people and understanding their dynamic physical behavior in a complex environment that can be used for biometric applications. This paper provides a detailed survey of the various studies in areas related to the tracking of people and body parts such as face, hands, fingers, legs, etc., and modeling behavior using motion analysis. 1.

Gesture and speech are two very important behaviors for virtual humans. They are not isolated from each other but generally employed simultaneously in the service of the same intention. An underlying PaT-Net parallel finite-state machine may be used to coordinate them both. Gesture selection is not arbitrary. Typical movements correlated with specific textual elements are used to select and produce gesticulation online. This enhances the expressiveness of speaking virtual humans.

Virtual humans are being increasingly used in different domains. Virtual human modeling requires to consider aspects belonging to different levels of abstractions. For example, at lower levels, one has to consider aspects concerning the geometric definition of the virtual human model and appearance while, at higher levels, one should be able to define how the virtual human behaves into an environment. H-Anim, the standard for representing humanoids in X3D/VRML worlds, is mainly concerned with low-level modeling aspects. As a result, the developer has to face the problem of defining the virtual human behavior and translating it into lower levels (e.g. geometrical and kinematic aspects). In this paper, we propose VHA (Virtual Human Architecture), a software architecture that allows one to easily manage an interactive H-Anim virtual human into X3D/VRML worlds. The proposed solution allows the developer to focus mainly on high-level aspects of the modeling process, such as the definition of the virtual human behavior.

To my son to remind me of my dreams; to my husband to support me in pursuing my dreams; to my mother to guide me towards my dreams; to my family and friends to tell me to believe in my dreams; to my colleagues to help me realize my dreams on professional level.

Abstract. The use of Virtual Environments as a user interface is essential for certain types of applications, both in education and entertainment. These worlds are even more attractive for the user when they are neither static nor pre-scripted, but have dynamic characteristics and are populated by autonomous entities, also called virtual agents. There has been a lot of research concerning visualization, animation and behavior of virtual agents, but there are no generic architectures, methodologies and tools for the development of intelligent virtual environments, i.e. 3D environments with autonomous virtual agents. In this paper, we present SimHuman, a tool for the construction of virtual worlds with autonomous entities, targeted for a specific group of applications, such as simple simulation systems, virtual environments, educational applications, multimedia presentations, etc. It consists of a programming library and two utilities and it is highly dynamic and configurable, as it is not based on fixed scenes and models. It has embedded characteristics such as Inverse Kinematics, Physically Based Modeling, Collision Detection and Response, and Vision. SimHuman incorporates some important features for designing and building virtual environments and turns out to be an effective tool for interactive 3D applications with virtual agents.