Adriana Braun

Using computer vision to simulate the motion of virtual agents

In this paper, we propose a new model to simulate the movement of virtual humans based on trajectories captured automatically from filmed video sequences. These trajectories are grouped into similar classes using an unsupervised clustering algorithm, and an extrapolated velocity field is generated for each class. A physically‐based simulator is then used to animate virtual humans, aiming to reproduce the trajectories fed to the algorithm and at the same time avoiding collisions with other agents. The proposed approach provides an automatic way to reproduce the motion of real people in a virtual environment, allowing the user to change the number of simulated agents while keeping the same goals observed in the filmed video. Copyright

Understanding people motion in video sequences using Voronoi diagrams: Detecting and classifying groups

This work describes a model for understanding people motion in video sequences using Voronoi diagrams, focusing on group detection and classification. We use the position of each individual as a site for the Voronoi diagram at each frame, and determine the temporal evolution of some sociological and psychological parameters, such as distance to neighbors and personal spaces. These parameters are used to compute individual characteristics (such as perceived personal space and comfort levels), that are analyzed to detect the formation of groups and their classification as voluntary or involuntary. Experimental results based on videos obtained from real life as well as from a crowd simulator were analyzed and discussed.

Eyes and Eyebrows Detection for Performance Driven Animation

Real-time localization of eyes and eyebrows in video sequences can find several applications in nowadays. However, this task is still a challenge, mainly if we consider images of low quality as those achieved by web cams. This paper describes a methodology to accurately detect meaningful feature points in eyes and eyebrows of people in frontal pose, in images captured by web cams. Also it discusses the mapping of the movement of the eyes of a real person to an avatar, in order to provide Performance Driven Animation (PDA). Furthermore, this paper presents obtained results and the limitations of the proposed methodology.

Reflecting user faces in avatars

This paper presents a model to generate personalized facial animations for avatars using Performance Driven Animation (PDA). This approach allows the users to reflect their face expressions in his/her avatar, considering as input a small set of feature points provided by Computer Vision (CV) tracking algorithms. The model is based on the MPEG-4 Facial Animation standard, and uses a hierarchy of the animation parameters to provide animation of face regions where it lacks CV data. To deform the face, we use two skin mesh deformation methods, which are computationally cheap and provide avatar animation in real time. We performed an evaluation with subjects in order to qualitatively evaluate our method. Results show that the proposed model can generate coherent and visually satisfactory animations.

Making Them Alive

This paper presents a model to reconstruct 3D virtual humans based on a single and spontaneous image. The main goal is to use computer vision and pattern recognition techniques to build coherent virtual humans according to an input picture. To achieve this goal we provide a semi-automatic process that includes 3D posture detection, segmentation of human body parts, and silhouette processing. Such information is used to generate a 3D virtual human, which can be further animated. The approach proposed in this paper aims to speed up the creation of 3D articulated characters, providing avatars based on pictures. Experimental results indicate that our approach is a good option for generating virtual humans from images based on a few mouse clicks.

VhCVE: A Collaborative Virtual Environment Including Facial Animation and Computer Vision

In this paper we present a platform called VhCVE, in which relevant issues related to Collaborative Virtual Environments applications are integrated. The main goal is to provide a framework where participants can interact with others by voice and chat. Also, manipulation tools such as a mouse using Computer Vision and Physics are included, as well as rendering techniques (e.g. light sources, shadows and weather effects). In addition, avatar animation in terms of face and body motion are provided. Results indicate that our platform can be used as a interactive virtual world to help communication among people.

Using computer vision to simulate the motion of virtual agents: Research Articles

In this article, a shape transformation technique is introduced for deforming objects based on a given deformation example. The example consists of two reference shapes representing two different states of an object. The reference shapes are assumed to morph from one state to the other. The evolution between the two reference shapes determines the shape transformation function. Any given objects can then be deformed by the same transformation. A continuous 4D Radial Basis Function is used to construct a density flow field (an extension of the optical flow in computer vision) representing the shape transformation of the example in 3-space. Objects embedded in the density flow field are deformed by moving vertices of the objects along the density flow vectors. Additional parameters are introduced to control the process of the deformation. This provides explicit control on the shape of the object obtained in the deformation process. Copyright

An Adaptive Methodology for Facial Expression Transfer

This work presents a methodology which aims to improve and automate the process of generating facial animation for interactive applications. We propose an adaptive and semiautomatic methodology, which allows to transfer facial expressions from a face mesh to another. The model has three main stages: rigging, expression transfer and animation, where the output meshes can be used as key poses for blendshape-based animation. The input of the model is a face mesh in neutral pose and a set of face data that can be provided from different sources, such as artist crafted meshes and motion capture data. The model generates a set of blendshapes corresponding to the input set, with minimum user intervention. We opted to use a simple rig structure in order to provide a trivial correspondence either with sparse facial feature points based systems or dense geometric data supplied by RGBD based systems. The rig structure can be refined on-the-fly to deal with different input geometric data according to the need. The main contribution of this work is an adaptive methodology which aims to create facial animations with few user intervention and capable or transferring expression details according to the need and/or amount of input data.

A rules-based model used to describe group dynamics for games

We present a rules-based model in which virtual agents have different individualities and can acquire social abilities as a function of rewards. Moreover, the agents can group with others they had interacted in past time, and these formed groups are characterized based on group cohesion (generated as a function of its members). One of the goals of this model aims to provide different group animation (density, formation and motion) based on group characteristics, consequently, the realism of the rules used in the model can impact the visual result. We propose an integration with a physics model in order to generate the required information to be used in these rules. Finally, some results and discussions about applying this methodology in a combat game are presented.

Preserving the Motion Features in Nonavoiding Collision Crowds

In current games, entire cities can be rendered in real time into massive virtual worlds. In addition to the enormous details of geometry, rendering, effects (e.g., particles), sound effects, and so on, nonplayable characters must also be animated and rendered, and they must interact with the environment and among themselves. Indeed, the computation time of all such data is expensive. Consequently, game designers should define priorities so that more resources can be allocated to generate better graphics, setting aside behavioral aspects. In huge environments, some of the actions/behaviors that should be processed can be nonvisible to the players (occluded) or even visible but far away. Normally, in such cases, the common decision is to turn off such processing. However, hidden enemy behaviors that are not processed can result in nonrealistic feedback to the player. In this article, we aim to provide a method to preserve the motion of nonvisible characters while maintaining a compromise with the needed computational time of background behaviors. We apply this idea specifically in crowd collision behavior, proposing nonavoiding collision crowds. Such crowds do not have collision avoidance behaviors but preserve their motion as typical crowds. We propose a mathematical technique to describe how people are affected by others, so collision avoidance methods are not necessarily computed (they can be turned off, which leads to a reduction in the required computational time). Results show that our method replicates the behavior well (velocities, densities, and time) when compared to a free-of-collision method.