Results 11 - 20 of 7,723

Neural Network-Based Face Detection

by Henry A. Rowley, Shumeet Baluja, Takeo Kanade - IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE , 1998
"... We present a neural network-based upright frontal face detection system. A retinally connected neural network examines small windows of an image and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We present ..."
Abstract - Cited by 1206 (22 self) - Add to MetaCart
We present a neural network-based upright frontal face detection system. A retinally connected neural network examines small windows of an image and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We present

Receiver-driven Layered Multicast

by Steven McCanne, Van Jacobson, Martin Vetterli , 1996
"... State of the art, real-time, rate-adaptive, multimedia applications adjust their transmission rate to match the available network capacity. Unfortunately, this source-based rate-adaptation performs poorly in a heterogeneous multicast environment because there is no single target rate — the conflicti ..."
Abstract - Cited by 737 (22 self) - Add to MetaCart
with a layered transmission system. By selectively forwarding subsets of layers at constrained network links, each user receives the best quality signal that the network can deliver. We and others have proposed that selective-forwarding be carried out using multiple IP-Multicast groups where each

A Model of Saliency-based Visual Attention for Rapid Scene Analysis

by Laurent Itti, Christof Koch, Ernst Niebur , 1998
"... A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented. Multiscale image features are combined into a single topographical saliency map. A dynamical neural network then selects attended locations in order of decreasing salie ..."
Abstract - Cited by 1748 (72 self) - Add to MetaCart
A visual attention system, inspired by the behavior and the neuronal architecture of the early primate visual system, is presented. Multiscale image features are combined into a single topographical saliency map. A dynamical neural network then selects attended locations in order of decreasing

Detecting Pedestrians Using Patterns of Motion and Appearance

by Paul Viola, Michael J. Jones, Daniel Snow - IN ICCV , 2003
"... This paper describes a pedestrian detection system that integrates image intensity information with motion information. We use a detection style algorithm that scans a detector over two consecutive frames of a video sequence. The detector is trained (using AdaBoost) to take advantage of both moti ..."
Abstract - Cited by 575 (3 self) - Add to MetaCart
This paper describes a pedestrian detection system that integrates image intensity information with motion information. We use a detection style algorithm that scans a detector over two consecutive frames of a video sequence. The detector is trained (using AdaBoost) to take advantage of both

Data networks

by L. Verger G, E. Gros D'aillon G, P. Major H, G. Németh H , 1992
"... a b s t r a c t In this paper we illustrate the core technologies at the basis of the European SPADnet project (www. spadnet.eu), and present the corresponding first results. SPADnet is aimed at a new generation of MRI-compatible, scalable large area image sensors, based on CMOS technology, that are ..."
Abstract - Cited by 2210 (5 self) - Add to MetaCart
, that are networked to perform gamma-ray detection and coincidence to be used primarily in (Time-of-Flight) Positron Emission Tomography (PET). The project innovates in several areas of PET systems, from optical coupling to single-photon sensor architectures, from intelligent ring networks to reconstruction

The Digital Michelangelo Project: 3D Scanning of Large Statues

by Marc Levoy, Szymon Rusinkiewicz, Brian Curless, Matt Ginzton, Jeremy Ginsberg, Kari Pulli, David Koller, Sean Anderson, Jonathan Shade, Lucas Pereira, James Davis, Duane Fulk , 2000
"... We describe a hardware and software system for digitizing the shape and color of large fragile objects under non-laboratory conditions. Our system employs laser triangulation rangefinders, laser time-of-flight rangefinders, digital still cameras, and a suite of software for acquiring, aligning, merg ..."
Abstract - Cited by 488 (8 self) - Add to MetaCart
, merging, and viewing scanned data. As a demonstration of this system, we digitized 10 statues by Michelangelo, including the well-known figure of David, two building interiors, and all 1,163 extant fragments of the Forma Urbis Romae, a giant marble map of ancient Rome. Our largest single dataset

ABSTRACT A Dynamic Operating System for Sensor Nodes

by Chih-chieh Han, Ram Kumar, Roy Shea, Eddie Kohler, Mani Srivastava
"... Sensor network nodes exhibit characteristics of both embedded systems and general-purpose systems. They must use little energy and be robust to environmental conditions, while also providing common services that make it easy to write applications. In TinyOS, the current state of the art in sensor no ..."
Abstract - Add to MetaCart
node operating systems, reusable components implement common services, but each node runs a single statically-linked system image, making it hard to run multiple applications or incrementally update applications. We present SOS, a new operating system for mote-class sensor nodes that takes a more

Face recognition by elastic bunch graph matching,

by Laurenz Wiskott , ‡ , Jean-Marc Fellous , § , Norbert Krüger , ¶ , Christoph Von Der Malsburg - IEEE Trans. Patt. Anal. Mach. Intell. , 1997
"... Abstract We present a system for recognizing human faces from single images out of a large database containing one image per person. The task is difficult because of image variation in terms of position, size, expression, and pose. The system collapses most of this variance by extracting concise fa ..."
Abstract - Cited by 367 (9 self) - Add to MetaCart
Abstract We present a system for recognizing human faces from single images out of a large database containing one image per person. The task is difficult because of image variation in terms of position, size, expression, and pose. The system collapses most of this variance by extracting concise

A Theory of Single-Viewpoint Catadioptric Image Formation

by Simon Baker, Shree K. Nayar - International Journal of Computer Vision , 1999
"... Conventional video cameras have limited fields of view which make them restrictive for certain applications in computational vision. A catadioptric sensor uses a combination of lenses and mirrors placed in a carefully arranged configuration to capture a much wider field of view. One important design ..."
Abstract - Cited by 236 (12 self) - Add to MetaCart
design goal for catadioptric sensors is choosing the shapes of the mirrors in a way that ensures that the complete catadioptric system has a single effective viewpoint. The reason a single viewpoint is so desirable is that it is a requirement for the generation of pure perspective images from the sensed

BraMBLe: A Bayesian Multiple-Blob Tracker

by M. Isard, J. MacCormick , 2001
"... Blob trackers have become increasingly powerful in recent years largely due to the adoption of statistical appearance models which allow effective background subtraction and robust tracking of deforming foreground objects. It has been standard, however, to treat background and foreground modelling a ..."
Abstract - Cited by 313 (1 self) - Add to MetaCart
as separate processes --- background subtraction is followed by blob detection and tracking --- which prevents a principled computation of image likelihoods. This paper presents two theoretical advances which address this limitation and lead to a robust multiple-person tracking system suitable for single
Results 11 - 20 of 7,723