Romero Tori

Mutual occlusion between real and virtual elements in Augmented Reality based on fiducial markers

Augmented Reality (AR) systems which use optical tracking with fiducial marker for registration have had an important role in popularizing this technology, since only a personal computer with a conventional webcam is required. However, in most these applications, the virtual elements are shown only in the foreground a real element does not occlude a virtual one. The method presented enables AR environments based on fiducial markers to support mutual occlusion between a real element and many virtual ones, according to the elements position (depth) in the environment.

Design and Implementation of a Flexible Hand Gesture Command Interface for Games Based on Computer Vision

This paper describes a command interface for games based on hand gestures defined by postures, movement and location. The large variety of gestures thus possible increases usability by allowing a better match between gesture and action. The system uses computer vision requiring no sensors or markers on the user or background. The analysis of requirements for games, the architecture and implementation are discussed, as well as the results of several tests to evaluate how well each requirement is met.

Integrating the Wii controller with enJine: 3D interfaces extending the frontiers of a didactic game engine

The goal of the work described here is to integrate a 3D input device, the Wii controller, and enJine, a didactic engine, motivated by the growing use of 3D interfaces. This article discusses how this increases enJines didactic and technological potential, and details the adopted solution as a layered architecture. Two interaction styles were tested with the implemented solution. Test results show a variety of data about the controller, confirming that this solution works as desired and that using it to modify a game so it can use the WiiMote as its input device is a simple task.

Game and interactivity in computer science education Video presentations are available on the citation page

Interactive computer graphics and games are powerful tools that can be used in the educational process. Much research shows that the learning process is highly enhanced when this kind of approach is used in computer science teaching, not only because of the motivation they engender, but also because high end results can be easily generated with relatively little effort.In fact, both interactive and game tools are growing in importance for supporting computer science learning, since they are capable of covering many of the typical topics included in the curriculum: Linear Algebra, Artificial Intelligence, Computer Graphics, Network, Real Time Simulations, Human Computer Interaction, Software Engineering, among other important topics.

Subjective Video Quality Assessment in Segmentation for Augmented Reality Applications

Video segmentation to extract a person in foreground has been a common task in many Augmented Reality (AR) applications. In natural environments which the background color and the light environment are not constant the segmentation method must be able to extract the element of the interest in these conditions. However, methods for segmentation in natural environment are more error prone than the traditional ones which are based on a constant color elimination. Thus, in order to use them in a large number of applications it is necessary to know how the segmentation errors are perceived by the users in order to focus on development of algorithms which avoid the more perceptible ones. In this work a video quality subjective assessment method was applied to obtain the AR users opinions about videos with different misclassified pixels rates. The results showed that segmentation errors are perceived by AR applications users. However, the video quality was not related with the number of the misclassified pixels. In addiction, it was noted that when the errors concentrated in the element of the interest increase the score of the associated video decreases.

Robot Arena: An augmented reality platform for game development

Nowadays electronic games are of great importance to the economic sector, to computing, and to academic research, and not are limited to entertainment applications only. Augmented reality is one of the new frontiers to be explored in the search for innovation in gameplay and in interactive interfaces of electronic games. This article presents the research, development, and testing of an infrastructure, called Robot Arena, for the development of innovative games using the spatial augmented reality and new interfaces that this technology brings. Based on horizontal interfaces with elements of hardware and software, Robot ARena has a flexible architecture that enables different ways of interaction and visualization. Another aspect planned for this project is the control and communication of robots, which can be used as avatars in games. A Robot ARena prototype was implemented, tested, and used in the development of two game prototypes, FootBot ARena and TanSpace, which bring new challenges to the infrastructure, such as exploration of the influence of virtual objects on real objects and the application of tangible interfaces.

Interaction in Collaborative Educational Virtual Environments

The collaborative educational virtual environment supposes the active participation of students and teachers, interacting highly and aiming at knowledge exchange and creation of new abilities. The learning becomes a process in which one assists the other to reach the objective, by exchanging experiences, dialogues, discussion of ideas, accomplishments of the group, and individual activities that can be shared with the group, allowing the creation of knowledge based on collective involvement. In this context, this paper describes and discusses the aspects and methods of interaction between students and teachers in collaborative educational virtual environments and presents an application based on the Virtual Teacher Project.

Simulation of soft tissue deformation: A new approach

An approach is presented in this paper, combining methods and models that are efficient enough to simulate elastic deformation, obtaining equilibrium between visual and haptic realism. Many medical training computational applications manipulate 3D objects that represent organs and human tissues. These representations, in function of the training requirements for which they are meant, may include parameter such as shape, topology, color, volume texture and, in certain cases, physical properties such as elasticity and stiffness. Based on this model, visual and/or haptic outputs are generated for users, and need to be realistic. In other words, they need to provide the learner with sensations close enough to those they would have if the training were provided with real life objects. However, its computational cost is too high to simultaneously provide visual and haptic realism in real-time. The results from deformation response time are compatible with those required for haptic interaction and the visual results from using meshes composed of a large number of polygons.

Virtual Reality-Based System for Training in Dental Anesthesia

This paper presents the development and preliminary evaluation of a Virtual Reality-based system for training in dental anesthesia. The development focused the simulation of an anesthesia procedure task. The evaluation involved graphic and haptic issues and had the presence of experts in the dentistry area. The assessment aimed at attributes that may influence the human-computer interaction, hindering realism, an important challenge in systems of this type. The attributes selected were: the update rate, the appearance of the virtual models and the number of viewpoints of the virtual environment, as well as the characteristics of the haptic device. Despite constraints were found, in the perception of the experts, the system may provide realism and help with the training of certain tasks.

Bilayer segmentation augmented with future evidence

This paper presents an algorithm that augments a previous model known in the literature for the automatic segmentation of monocular videos into foreground and background layers. The original model fuses visual cues such as color, contrast, motion and spatial priors within a Conditional Random Field. Our augmented model makes use of bidirectional motion priors by exploiting future evidence. Although our augmented model processes more data, it does so with the same time performance of the original model. We evaluate the augmented model within ground truth data and the results show that the augmented model produces better segmentation.