Interface issues in the ESCHER visual database editor

Presentation at the 1997 Dagstuhl Seminar "Evaluation of Multimedia Information Retrieval", Norbert Fuhr, Keith van Rijsbergen, Alan F. Smeaton (eds.), Dagstuhl Seminar Report 175, 14.04. - 18.04.97 (9716). - Abstract: This presentation will introduce ESCHER, a database editor which supports visualization in non-standard applications in engineering, science, tourism and the entertainment industry. It was originally based on the extended nested relational data model and is currently extended to include object-relational properties like inheritance, object types, integrity constraints and methods. It serves as a research platform into areas such as multimedia and visual information systems, QBE-like queries, computer-supported concurrent work (CSCW) and novel storage techniques. In its role as a Visual Information System, a database editor must support browsing and navigation. ESCHER provides this access to data by means of so called fingers. They generalize the cursor paradigm in graphical and text editors. On the graphical display, a finger is reflected by a colored area which corresponds to the object a finger is currently pointing at. In a table more than one finger may point to objects, one of which is the active finger and is used for navigating through the table. The talk will mostly concentrate on giving examples for this type of navigation and will discuss some of the architectural needs for fast object traversal and display. ESCHER is available as public domain software from our ftp site in Kassel. The portable C source can be easily compiled for any machine running UNIX and OSF/Motif, in particular our working environments IBM RS/6000 and Intel-based LINUX systems. A porting to Tcl/Tk is under way.

Acoustic adaptation in cross database audio visual SHMM training for phonetic spoken term detection

Visual information in the form of lip movements of the speaker has been shown to improve the performance of speech recognition and search applications. In our previous work, we proposed cross database training of synchronous hidden Markov models (SHMMs) to make use of external large and publicly available audio databases in addition to the relatively small given audio visual database. In this work, the cross database training approach is improved by performing an additional audio adaptation step, which enables audio visual SHMMs to benefit from audio observations of the external audio models before adding visual modality to them. The proposed approach outperforms the baseline cross database training approach in clean and noisy environments in terms of phone recognition accuracy as well as spoken term detection (STD) accuracy.

Cross database training of audio-visual hidden Markov models for phone recognition

Speech recognition can be improved by using visual information in the form of lip movements of the speaker in addition to audio information. To date, state-of-the-art techniques for audio-visual speech recognition continue to use audio and visual data of the same database for training their models. In this paper, we present a new approach to make use of one modality of an external dataset in addition to a given audio-visual dataset. By so doing, it is possible to create more powerful models from other extensive audio-only databases and adapt them on our comparatively smaller multi-stream databases. Results show that the presented approach outperforms the widely adopted synchronous hidden Markov models (HMM) trained jointly on audio and visual data of a given audio-visual database for phone recognition by 29% relative. It also outperforms the external audio models trained on extensive external audio datasets and also internal audio models by 5.5% and 46% relative respectively. We also show that the proposed approach is beneficial in noisy environments where the audio source is affected by the environmental noise.

Complete-linkage clustering for voice activity detection in audio and visual speech

We propose a novel technique for conducting robust voice activity detection (VAD) in high-noise recordings. We use Gaussian mixture modeling (GMM) to train two generic models; speech and non-speech. We then score smaller segments of a given (unseen) recording against each of these GMMs to obtain two respective likelihood scores for each segment. These scores are used to compute a dissimilarity measure between pairs of segments and to carry out complete-linkage clustering of the segments into speech and non-speech clusters. We compare the accuracy of our method against state-of-the-art and standardised VAD techniques to demonstrate an absolute improvement of 15% in half-total error rate (HTER) over the best performing baseline system and across the QUT-NOISE-TIMIT database. We then apply our approach to the Audio-Visual Database of American English (AVDBAE) to demonstrate the performance of our algorithm in using visual, audio-visual or a proposed fusion of these features.

Managing Industrial Simulator Visual Databases Using Geographic Information Systems

Geographic Information Systems are developed to handle enormous volumes of data and are equipped with numerous functionalities intended to capture, store, edit, organise, process and analyse or represent the geographically referenced information. On the other hand, industrial simulators for driver training are real-time applications that require a virtual environment, either geospecific, geogeneric or a combination of the two, over which the simulation programs will be run. In the final instance, this environment constitutes a geographic location with its specific characteristics of geometry, appearance, functionality, topography, etc. The set of elements that enables the virtual simulation environment to be created and in which the simulator user can move, is usually called the Visual Database (VDB). The main idea behind the work being developed approaches a topic that is of major interest in the field of industrial training simulators, which is the problem of analysing, structuring and describing the virtual environments to be used in large driving simulators. This paper sets out a methodology that uses the capabilities and benefits of Geographic Information Systems for organising, optimising and managing the visual Database of the simulator and for generally enhancing the quality and performance of the simulator.

Generación y Gestión Optimizadas de la Base de Datos de un Visual para su Implementación en un Simulador de Formación

Los Sistemas de Información Geográfica están desarrollados para gestionar grandes volúmenes de datos, y disponen de numerosas funcionalidades orientadas a la captura, almacenamiento, edición, organización, procesado, análisis, o a la representación de información geográficamente referenciada. Por otro lado, los simuladores industriales para entrenamiento en tareas de conducción son aplicaciones en tiempo real que necesitan de un entorno virtual, ya sea geoespecífico, geogenérico, o combinación de ambos tipos, sobre el cual se ejecutarán los programas propios de la simulación. Este entorno, en última instancia, constituye un lugar geográfico, con sus características específicas geométricas, de aspecto, funcionales, topológicas, etc. Al conjunto de elementos que permiten la creación del entorno virtual de simulación dentro del cual se puede mover el usuario del simulador se denomina habitualmente Base de Datos del Visual (BDV). La idea principal del trabajo que se desarrolla aborda un tema del máximo interés en el campo de los simuladores industriales de formación, como es el problema que presenta el análisis, la estructuración, y la descripción de los entornos virtuales a emplear en los grandes simuladores de conducción. En este artículo se propone una metodología de trabajo en la que se aprovechan las capacidades y ventajas de los Sistemas de Información Geográfica para organizar, optimizar y gestionar la base de datos visual del simulador, y para mejorar la calidad y el rendimiento del simulador en general. ABSTRACT Geographic Information Systems are developed to handle enormous volumes of data and are equipped with numerous functionalities intended to capture, store, edit, organise, process and analyse or represent the geographically referenced information. On the other hand, industrial simulators for driver training are real-time applications that require a virtual environment, either geospecific, geogeneric or a combination of the two, over which the simulation programs will be run. In the final instance, this environment constitutes a geographic location with its specific characteristics of geometry, appearance, functionality, topography, etc. The set of elements that enables the virtual simulation environment to be created and in which the simulator user can move, is usually called the Visual Database (VDB). The main idea behind the work being developed approaches a topic that is of major interest in the field of industrial training simulators, which is the problem of analysing, structuring and describing the virtual environments to be used in large driving simulators. This paper sets out a methodology that uses the capabilities and benefits of Geographic Information Systems for organising, optimising and managing the visual Database of the simulator and for generally enhancing the quality and performance of the simulator.

Contextual visual localization: cascaded submap classification, optimized saliency detection, and fast view matching

In this paper, we present a novel coarse-to-fine visual localization approach: contextual visual localization. This approach relies on three elements: (i) a minimal-complexity classifier for performing fast coarse localization (submap classification); (ii) an optimized saliency detector which exploits the visual statistics of the submap; and (iii) a fast view-matching algorithm which filters initial matchings with a structural criterion. The latter algorithm yields fine localization. Our experiments show that these elements have been successfully integrated for solving the global localization problem. Context, that is, the awareness of being in a particular submap, is defined by a supervised classifier tuned for a minimal set of features. Visual context is exploited both for tuning (optimizing) the saliency detection process, and to select potential matching views in the visual database, close enough to the query view.

Feature Selection for Pose Invariant Lip Biometrics

For the first time in this paper the authors present results showing the effect of out of plane speaker head pose variation on a lip biometric based speaker verification system. Using appearance DCT based features, they adopt a Mutual Information analysis technique to highlight the class discriminant DCT components most robust to changes in out of plane pose. Experiments are conducted using the initial phase of a new multi view Audio-Visual database designed for research and development of pose-invariant speech and speaker recognition. They show that verification performance can be improved by substituting higher order horizontal DCT components for vertical, particularly in the case of a train/test pose angle mismatch.

An Investigation Into Features For Multi-View Lipreading

For the first time in this paper we present results showing the effect of speaker head pose angle on automatic lip-reading performance over a wide range of closely spaced angles. We analyse the effect head pose has upon the features themselves and show that by selecting coefficients with minimum variance w.r.t. pose angle, recognition performance can be improved when train-test pose angles differ. Experiments are conducted using the initial phase of a unique multi view Audio-Visual database designed specifically for research and development of pose-invariant lip-reading systems. We firstly show that it is the higher order horizontal spatial frequency components that become most detrimental as the pose deviates. Secondly we assess the performance of different feature selection masks across a range of pose angles including a new mask based on Minimum Cross-Pose Variance coefficients. We report a relative improvement of 50% in Word Error Rate when using our selection mask over a common energy based selection during profile view lip-reading.

Development of a hand-gesture recognition system for human-computer interaction

The aim of this Master Thesis is the analysis, design and development of a robust and reliable Human-Computer Interaction interface, based on visual hand-gesture recognition. The implementation of the required functions is oriented to the simulation of a classical hardware interaction device: the mouse, by recognizing a specific hand-gesture vocabulary in color video sequences. For this purpose, a prototype of a hand-gesture recognition system has been designed and implemented, which is composed of three stages: detection, tracking and recognition. This system is based on machine learning methods and pattern recognition techniques, which have been integrated together with other image processing approaches to get a high recognition accuracy and a low computational cost. Regarding pattern recongition techniques, several algorithms and strategies have been designed and implemented, which are applicable to color images and video sequences. The design of these algorithms has the purpose of extracting spatial and spatio-temporal features from static and dynamic hand gestures, in order to identify them in a robust and reliable way. Finally, a visual database containing the necessary vocabulary of gestures for interacting with the computer has been created.

Recognising audio-visual speech in vehicles using the AVICAR database

Interacting with technology within a vehicle environment using a voice interface can greatly reduce the effects of driver distraction. Most current approaches to this problem only utilise the audio signal, making them susceptible to acoustic noise. An obvious approach to circumvent this is to use the visual modality in addition. However, capturing, storing and distributing audio-visual data in a vehicle environment is very costly and difficult. One current dataset available for such research is the AVICAR [1] database. Unfortunately this database is largely unusable due to timing mismatch between the two streams and in addition, no protocol is available. We have overcome this problem by re-synchronising the streams on the phone-number portion of the dataset and established a protocol for further research. This paper presents the first audio-visual results on this dataset for speaker-independent speech recognition. We hope this will serve as a catalyst for future research in this area.

Measuring Visual Consistency in 3D Rendering Systems

One of the major challenges facing a present day game development company is the removal of bugs from such complex virtual environments. This work presents an approach for measuring the correctness of synthetic scenes generated by a rendering system of a 3D application, such as a computer game. Our approach builds a database of labelled point clouds representing the spatiotemporal colour distribution for the objects present in a sequence of bug-free frames. This is done by converting the position that the pixels take over time into the 3D equivalent points with associated colours. Once the space of labelled points is built, each new image produced from the same game by any rendering system can be analysed by measuring its visual inconsistency in terms of distance from the database. Objects within the scene can be relocated (manually or by the application engine); yet the algorithm is able to perform the image analysis in terms of the 3D structure and colour distribution of samples on the surface of the object. We applied our framework to the publicly available game RacingGame developed for Microsoft(R) Xna(R). Preliminary results show how this approach can be used to detect a variety of visual artifacts generated by the rendering system in a professional quality game engine.

Lip detection for audio-visual speech recognition in-car environment

Acoustically, car cabins are extremely noisy and as a consequence audio-only, in-car voice recognition systems perform poorly. As the visual modality is immune to acoustic noise, using the visual lip information from the driver is seen as a viable strategy in circumventing this problem by using audio visual automatic speech recognition (AVASR). However, implementing AVASR requires a system being able to accurately locate and track the drivers face and lip area in real-time. In this paper we present such an approach using the Viola-Jones algorithm. Using the AVICAR [1] in-car database, we show that the Viola- Jones approach is a suitable method of locating and tracking the driver’s lips despite the visual variability of illumination and head pose for audio-visual speech recognition system.