Search
Now showing items 11-20 of 60
Facial expression modeling using component AAM models - Gaming applications
(IEEE, 2009-10-23)
In this paper we provide preliminary results on a new modeling approach for improved determination of facial expressions from a low-resolution video stream. An initial proof-of-concept using an extension of an Active ...
FPGA based stereo imaging system with applications in computer gaming
(IEEE, 2009-10-23)
A real-time stereo imaging system is described. It incorporates dual image acquisition chains on a single FPGA device and is able to provide real-time synchronized video output from twin CMOS imaging sensors. The platform ...
Architecture for a Home Media Network Based on PTP-IP Connectivity Techniques
(IEEE, 2008-08-05)
PTP/IP functionality is extended to enable networked devices to be organized in a sequential media processing workflow. The additional device functionality necessary to support this network architecture is not unduly complex ...
Managing Digital Image Collections from your TV-Set: A State-of-Art Review
(IEEE, 2007-07-14)
The problem of managing growing digital image collections is discussed in the context of a home user. The use of a conventional television set as both a viewing and management tool is discussed. The problem of linking ...
Hardware implementation of a real-time 3D video acquisition system
(IEEE, 2010-07-15)
An implementation of a real-time 3D video acquisition system on a single FPGA is presented. Our approach is based on the use of stereo image sensors and can display real-time 3D video when combined with shutter glasses. ...
Appearance capturing and animation techniques for realistic, true-identity gaming avatars
(IEEE, 2009-10-23)
Making use of a class of 2D statistical face models known as active appearance models (AAMs), we investigate a technique for generating real-time animated avatars suitable for video gaming. We consider here a number of ...
Enhanced real-time face models from stereo imaging for gaming applications
(IEEE, 2009-10-23)
Techniques for improved 2D active appearance face models are presented. When these are applied to stereoscopic image pairs we show that sufficient information on image depth is obtained to generate an approximate 3D face ...
A crash course on patents for engineers
(IEEE, 2013-01-12)
Most engineers are aware of the existence of patents. Indeed the preparation of patent disclosures is an important aspect of most research engineering job functions. Yet for many engineers the world of patents remains ...
Getting more from your datasets: Data augmentation, annotation and generative techniques
(XPERI Inc., 2018-05-18)
Deep Learning for embedded vision requires large datasets. Indeed the more varied training data is, the more accurate the trained network. But, acquiring and accurately annotating datasets costs time and money. This talk ...
Hybrid Semi-Parallel Deep Neural Networks (SPDNN) – example methodologies and use cases
(XPERI Inc., 2018-05-23)
Deep neural networks (DNNs) are typically trained on specific datasets, optimized with particular discriminating capabilities. Often several different DNN topologies are developed solving closely related aspects of a ...