Inmaculada Coma

Augmented mirror: interactive augmented reality system based on kinect

In this paper we present a virtual character controlled by an actor in real time, who talks with an audience through an augmented mirror. The application, which integrates video images, the avatar and other virtual objects within an Augmented Reality system, has been implemented using a mixture of technologies: two kinect systems for motion capture, depth map and real images, a gyroscope to detect head movements, and control algorithms to manage avatar emotions.

Towards a simulation-based tuning of motion cueing algorithms

Abstract This paper deals with the problem of finding the best values for the parameters of Motion Cueing Algorithms (MCA). MCA are responsible for controlling the movements of robotic motion platforms used to generate the gravito-inertial cues of vehicle simulators. The values of their multiple parameters, or coefficients, are hard to establish and they dramatically change the behaviour of MCA. The problem has been traditionally addressed in a subjective, partially non-systematic, iterative, time-consuming way, by seeking pilot/driver feedback on the generated motion cues. The aim of this paper is to introduce a different approach to solve the problem of MCA tuning, by making use of a simulated motion platform; a series of (human-based) objective metrics relating to the performance of MCA are measured using this simulated device. This simulation-based approach allows for automatic tuning of the MCA, by using a genetic algorithm that is proposed to analyse the results obtained from multiple simulations of the MCA with different parameters. This algorithm is designed to efficiently optimize the simulated MCA parameter space. The proposed solution is assessed with the classical washout MCA, performing a series of tests to validate the correctness of this approach and the suitability of the proposed method to the solution of the MCA tuning problem. Results show that this approach can be an alternative to the traditional subjective tuning method in certain situations, mainly because it provides suitable values for the MCA parameters in a shorter time period, albeit subjective tuning is preferred when time to perform the MCA tuning is not an issue.

Motion-cuing algorithms: characterization of users' perception.

Objective: The aim of this study was to characterize the human response to motion-cuing algorithms (MCAs) by comparing users’ perception to several proposed objective indicators. Background: Other researchers have proposed several MCAs, but few improvements have been achieved lately. One of the reasons for this lack of progress is that fair comparisons between different algorithms are hard to achieve, for their evaluation needs to be performed with humans and the tuning process is slow. Method: This characterization is performed by means of a comparison of the subjective perception of vehicle simulation users (90 participants) against several proposed objective indicators that try to measure MCA performance. Two motion platforms (3 and 6 degrees of freedom [DoF]) and two vehicle simulators (a driving simulator and a speedboat simulator) were tested using the classical washout algorithm, considered to be the main reference in MCA literature. Results: Results show that users are more sensitive to correlation and delay with respect to the expected motion rather than its magnitude and that specific force is more of a factor than angular speed in the driving simulator. The opposite happens in the speedboat simulator. Conclusions: Human drivers’ reaction to MCA is mainly characterized by the normalized Pearson correlation between output and input signals of the algorithm. This finding validates the main MCA strategy that consists of downscaling the signals and slightly distorting their frequency spectrum. The 6-DoF simulator is perceived as a modest improvement of the 3-DoF platform. Applications: These results set the basis for future automatic tuning, evaluation, and comparison of MCA in motion platforms.

Towards an extensible simulator of real motion platforms

Abstract The limitations of a real motion platform will not normally be discovered until it is completely built and tested. Late identification of its limitations imposes the necessity of a redesign of the motion platform. This, in turn, incurs important and significant economic costs for the manufacturer. Note that any change in the original design of the motion platform requires an investment in resources, money and time in order to perform the re-design of the platform. The main contribution of this paper is to address this problem by creating a virtual motion platform (VMP). This virtual motion platform is a computer-based simulation of a real motion platform which produces the same outputs as the real platform when it receives the same inputs. The VMP has been designed to easily replace the real platform in order to avoid damage to the real system, avoid the potential for human injuries and reduce costs, among other advantages. The model is extensible, enabling the simulation of different kinds of real motion platforms in real-time. The VMP has been validated against a real system implementation. This prototype has been validated against two real motion platforms that we have in our labs: a T3R3 (6DoF) and a T1R2 (3DoF) platform. Extensive empirical tests have been performed and the results show that the VPM exhibits a deviation of less than 3% with respect to the real motion platform, which is a really reasonable result considering the complexity of the simulation. We have also demonstrated that our simulation is capable of running faster than real-time being able to perform batch simulations on many different design iterations.

A novel dynamic multi-model relevance feedback procedure for content-based image retrieval

This paper deals with the problem of image retrieval in large databases with a big semantic gap by a relevance feedback procedure. We present a novel algorithm for modelling the userss preferences in the content-based image retrieval system.The proposed algorithm considers the probability of an image belonging to the set of those sought by the user, and estimates the parameters of several local logistic regression models whose inputs are the low-level image features. A Principal Component Analysis method is applied to the original vector to reduce its high dimensionality. The relevance probabilities predicted by these local models are combined by means of a weighted average. These weights are obtained according to the variance explained by the group of principal components used for each local model. These models are dynamically estimated in each iteration of the relevance feedback algorithm until the user is satisfied.This novel procedure has been tested in a collection with a large semantic gap, the Wikipedia collection. Two types of experiments have been performed, one with an automatic user and another with a typical user. The method is compared to some recent similar approaches in literature, obtaining very good performance in terms of the MAP evaluation measure.

Combining traditional and indirect augmented reality for indoor crowded environments. A case study on the Casa Batlló museum

Abstract Mobile audio-guides are currently being used in museums to enhance the visitors’ experience. Over the past few years, some Augmented Reality (AR) solutions have been explored in this context, making it possible to provide augmented visual and sonic stimuli through the use of smartphones. However, the special conditions of museums (e.g. artificial markers cannot be used, small, crowded rooms, etc.) and the limited computational capacity of smartphones mean that there are important restrictions in the use of this technology. In this paper we introduce a novel mobile augmented guide for the Casa Batllo museum (Barcelona, Spain) which is based on a combination of traditional and indirect AR. Through the proposed solution, we further explore the use of indirect AR for the interior of buildings as, at present, this technology is usually used for outdoor environments. The developed application is currently being used by Casa Batllo visitors. Retrieval of user experience shows some of the benefits of the proposed solution and opens the door for other similar solutions in museums.

Locally constrained synthetic LoDs generation for natural terrain meshes

Terrain representation is a basic topic in the field of interactive graphics. The amount of data required for a good quality of the terrain offers an important challenge to developers of such systems. For users of these applications, the accuracy of geographical data is generally less important than its natural visual appearance. This makes it possible to maintain a limited geographical database for the system and to extend it generating synthetic data. The evaluation of the intrinsic properties of the terrain (i.e. fractal dimension, roughness, etc.) may be used as the basis for generating extra data accomplishing the same patterns discovered in the actual information. However, it is also interesting to point out that in most natural landscapes, it is usual to have human or natural changes in the basic properties of some areas, i.e. a road or a river. This fact can make it more difficult for synthetic data generation to be free of visual artifacts within these areas. In this paper, we combine fractal and wavelet theories to provide extra data which keeps the natural properties of actual information available. New levels of detail for the terrain are obtained by applying an inverse Wavelet Transform to a set of values randomly generated, thus maintaining the coherence of statistical properties with the original geographical data. Combined with this approach, the use of energy reduction masks has been added in order to avoid undesired visual artifacts in those special areas for which the general terrain properties are no longer valid.

A Multi-Projector Calibration Method for Virtual Reality Simulators with Analytically Defined Screens

The geometric calibration of projectors is a demanding task, particularly for the industry of virtual reality simulators. Different methods have been developed during the last decades to retrieve the intrinsic and extrinsic parameters of projectors, most of them being based on planar homographies and some requiring an extended calibration process. The aim of our research work is to design a fast and user-friendly method to provide multi-projector calibration on analytically defined screens, where a sample is shown for a virtual reality Formula 1 simulator that has a cylindrical screen. The proposed method results from the combination of surveying, photogrammetry and image processing approaches, and has been designed by considering the spatial restrictions of virtual reality simulators. The method has been validated from a mathematical point of view, and the complete system—which is currently installed in a shopping mall in Spain—has been tested by different users.

Intelligent eye: location-based multimedia information for mobile phones

This paper describes Intelligent Eye, a mobile phone interactive leisure guide that offers location-based multimedia information. The information offered is related to the users position, so the main goal of this work is the development of an efficient system to detect where the user is pointing his/her camera at by means of a content-based image retrieval algorithm (CBIR). The CBIR procedure uses color histograms in the HS color space extracted from images, and employs Kullback-Leibler divergence as the similarity measure. Intelligent Eye can be used in a wide range of camera-equipped mobile phones; however, efficiency is improved if GPS data is available. In order to outperform other systems we have made use of a video stream in the classification process instead of using still images. Moreover, the image database can be populated dynamically by means of a feedback procedure with images taken by users. We report preliminary results of the prototype working with real images obtaining a hit classification rate of 96%.

A reconfigurable immersive workbench and wall-system for designing and training in 3D environments

Virtual and Augmented Reality have been widely used in many scientific fields for the last two decades in order to visualize complex data and information. Although both techniques are oriented to show users complex 3D environments by means of an intuitive and easy mechanism, they use to become useless to manipulate the information in an intuitive and realistic way. In this paper, we present SOROLLA, a new concept of workbench designed for virtual and augmented reality purposes and specially oriented to the fields of teleeducation and engineering. Unlike other proposals, SOROLLA not only allows an easy utilization and configuration, but also shows a cost-effective immersive visualization system based on off-the-shelf elements. The initial results using our workbench and wall-system show that both efficiency and user satisfaction are higher than the ones obtained using conventional devices.