<p>The goal of this project is to implement a system to analyse an audio signal containing speech, and produce a classifcation of lip shape categories (visemes) in order to synchronize the lips of a computer generated face with the speech. </p><p>The thesis describes the work to derive a method that maps speech to lip move- ments, on an animated face model, in real time. The method is implemented in C++ on the PC/Windows platform. The program reads speech from pre-recorded audio files and continuously performs spectral analysis of the speech. Neural networks are used to classify the speech into a sequence of phonemes, and the corresponding visemes are shown on the screen. </p><p>Some time delay between input speech and the visualization could not be avoided, but the overall visual impression is that sound and animation are synchronized.</p>

<p>The possibility to use real-time computer vision in video sequences gives many opportunities for a system to interact with the environment. Possible ways for interaction are e.g. augmented reality like in the MATRIS project where the purpose is to add new objects into the video sequence, or surveillance where the purpose is to find abnormal events.</p><p>The increase of the speed of computers the last years has simplified this process and it is now possible to use at least some of the more advanced computer vision algorithms that are available. The computational speed of computers is however still a problem, for an efficient real-time system efficient code and methods are necessary. This thesis deals with both problems, one part is about efficient implementations using single instruction multiple data (SIMD) instructions and one part is about robust tracking.</p><p>An efficient real-time system requires efficient implementations of the used computer vision methods. Efficient implementations requires knowledge about the CPU and the possibilities given. In this thesis, one method called SIMD is explained. SIMD is useful when the same operation is applied to multiple data which usually is the case in computer vision, the same operation is executed on each pixel.</p><p>Following the position of a feature or object in a video sequence is called tracking. Tracking can be used for a number of applications. The application in this thesis is to use tracking for pose estimation. One way to do tracking is to cut out a small region around the feature, creating a patch and find the position on this patch in the other frames. To find the position, a measure of the difference between the patch and the image in a given position is used. This thesis thoroughly investigates the sum of absolute difference (SAD) error measure. The investigation involves different ways to improve the robustness and to decrease the average error. One method to estimate the average error, the covariance of the position error is proposed. An estimate of the average error is needed when different measurements are combined.</p><p>Finally, a system for camera pose estimation is presented. The computer vision part of this system is based on the result in this thesis. This presentation contains also a discussion about the result of this system.</p> / Report code: LIU-TEK-LIC-2007:5. The report code in the thesis is incorrect.

<p>Many efforts have been carried out to provide transmission reliability in the history of communication systems. As the demand for real-time applications increased, providing a reliable communication in a timely manner for such applications is strongly desired. Considering timing constraints makes the issue of achieving reliability more difficult. This thesis concentrates on providing reliability for real-time communication in embedded networks by achieving a timing analysis and using the ARQ concept. What is carried out in this thesis is providing retransmission in a real-time manner for embedded networks according to application request. The thesis work focuses on one packet retransmission over a point to point link, but the concept is rich and can be extended to cover application request in real-time embedded networks. Two methods have been fulfilled, and a simulation has been done on the timing analysis focusing on the performance in accepting real-time traffic in the form of separate channels for each application request. The protocol combines ARQ and a scheduling algorithm as a base to support retransmission for hard real-time applications in embedded networks.</p>

<p>Ethernet technology is being accepted by industrial community due to its open standardization </p><p>and low cost. To meet the requirements of industrial applications, a switched Ethernet </p><p>network with hard real time guarantees using relative deadlines is presented as a first step to </p><p>verify the functionality. The goal of the project was primarily to implement a real-time </p><p>switched Ethernet with EDF (Earliest Deadline First) scheduling algorithm. </p><p>In this project, the function simulations of real-time switched Ethernet with distributed control </p><p>software have been implemented, by using a standard switch with priority-queues and the </p><p>distributed software, as well as EDF-scheduled TDMA (Time Division Medium Access). The </p><p>network topology is the star type. There is no extra hardware added into the switch and the </p><p>nodes. All functions are implemented by software and the setting in the switch. </p><p>The project focuses on hard real-time service guarantees but soft real-time traffic and non </p><p>real-time traffic, as well as real time administration are also taken into the consideration. </p><p>Our simulations show that 100 percent of the network usage could be scheduled and the result </p><p>of deterministic real-time properties of the system are achieved as expected.</p>

<p>Future parallel computer systems for embedded real-time applications,where each node in itself can be a parallel computer, are predicted to havevery high bandwidth demands on the interconnection network. Otherimportant properties are time-deterministic latency and guarantees to meetdeadlines. In this thesis, a fiber-optic passive optical star network with amedium access protocol for packet switched communication in distributedreal-time systems is proposed. By using WDM (Wavelength DivisionMultiplexing), multiple channels, each with a capacity of several Gb/s, areobtained.</p><p>A number of protocols for WDM star networks have recently been proposed.However, the area of real-time protocols for these networks is quiteunexplored. The protocol proposed in this thesis is based on TDMA (TimeDivision Multiple Access) and uses a new distributed slot-allocationalgorithm with real-time properties. Services for both guarantee-seekingmessages and best-effort messages are supported for single destination,multicast, and broadcast transmission. Slot reserving can be used toincrease the time-deterministic bandwidth, while still having an efficientbandwidth utilization due to a simple slot release method.</p><p>By connecting several clusters of the proposed WDM star network by abackbone star, thus forming a star-of-stars network, we get a modular andscalable high-bandwidth network. The deterministic properties of thenetwork are theoretically analyzed for both intra-cluster and inter-clustercommunication, and computer simulations of intra-cluster communicationare reported. Also, an overview of high-performance fiber-opticcommunication systems is presented.</p>

No description available.

We review MIT research in manufacturing systems engineering, and we describe current and possible future research activities in this area. This includes advances in decomposition techniques, optimization, token-based control systems analysis, multiple part types, inspection location, data collection and several other topics. / Singapore-MIT Alliance (SMA)

Home networking is becoming an attractive application not only for the Internet access but also for home automation. Being a high-speed and dominant standard presently, HomePlug has an important role in home LAN connecting to the Internet. For industrial applications, the Power Line Communication also has significant advances. However, the PHY/MAC technology provided by HomePlug still cannot be employed with some critical features such as real time performance, implications in the event of link and node loss. In this paper, the characteristics of HomePlug PHY/MAC, the property of power line channel, as well as the noise features of power line are analyzed. Based on HomePlug, a model of high level real-time protocol applied to industrial environment is proposed. The protocol simultaneously belongs to layer two and three, and can support real-time implementation with no loss and small delay according to the requirement in PLC networks, for targeting to develop a real time network with high speed power line media and advanced modulation. / Singapore-MIT Alliance (SMA)

This paper describes a trainable system capable of tracking faces and facialsfeatures like eyes and nostrils and estimating basic mouth features such as sdegrees of openness and smile in real time. In developing this system, we have addressed the twin issues of image representation and algorithms for learning. We have used the invariance properties of image representations based on Haar wavelets to robustly capture various facial features. Similarly, unlike previous approaches this system is entirely trained using examples and does not rely on a priori (hand-crafted) models of facial features based on optical flow or facial musculature. The system works in several stages that begin with face detection, followed by localization of facial features and estimation of mouth parameters. Each of these stages is formulated as a problem in supervised learning from examples. We apply the new and robust technique of support vector machines (SVM) for classification in the stage of skin segmentation, face detection and eye detection. Estimation of mouth parameters is modeled as a regression from a sparse subset of coefficients (basis functions) of an overcomplete dictionary of Haar wavelets.

The application of augmented reality (AR) technology for assembly guidance is a novel approach in the traditional manufacturing domain. In this paper, we propose an AR approach for assembly guidance using a virtual interactive tool that is intuitive and easy to use. The virtual interactive tool, termed the Virtual Interaction Panel (VirIP), involves two tasks: the design of the VirIPs and the real-time tracking of an interaction pen using a Restricted Coulomb Energy (RCE) neural network. The VirIP includes virtual buttons, which have meaningful assembly information that can be activated by an interaction pen during the assembly process. A visual assembly tree structure (VATS) is used for information management and assembly instructions retrieval in this AR environment. VATS is a hierarchical tree structure that can be easily maintained via a visual interface. This paper describes a typical scenario for assembly guidance using VirIP and VATS. The main characteristic of the proposed AR system is the intuitive way in which an assembly operator can easily step through a pre-defined assembly plan/sequence without the need of any sensor schemes or markers attached on the assembly components. / Singapore-MIT Alliance (SMA)