Dialog Table is a shared interface where you use hand gestures to discover a museum's collection. Several people can gather around and together explore the table's movies, narratives and 3D journeys. The table provides an opportunity for people to discuss with each other their thoughts on what they have seen. Several teen beta-testers said they wanted their desk at home to work just like the table. The table can work in situations as varied as hospital kiosks, conference rooms, collaborative design stations, game rooms, bedrooms...Dialog Table was commissioned by the Walker Art Center through an international design competition to promote social interactions among visitors, to provide access to the Walker's multidisciplinary collections, and to facilitate learning about art. The table was designed by Marek Walczak, an artist and architect, Michael McAllister, an industrial designer and Jakub Segen, a leader in recognition systems. http://dialogtable.com.

A real-time visual recognition system, that enables a human conductor to control an electronic orchestra using gestures of a traditional conductor's baton, is described. The positions of the baton and conductor's hand are identified in a sequence of images from a pair of cameras, and tracked in 3D space. Gestures defining the musical beat are detected in the baton's trajectory, and conveyed to a sound synthesis system, as events that control the tempo and the phase of the music. Parameters that can enable the control of the volume of sound are computed from the range variations of the baton and the hand. The system's response is nearly instantaneous. The beat detection is reliable, and precise enough to be used by a professional conductor. It has been used to conduct an integrated electronic performance that combined a synthesized orchestra and animated ballet.

This paper describes a system that uses a camera and a point light source to track a user's hand in three dimensions. Using depth cues obtained from projections of the hand and its shadow, the system computes the 3D position and orientation of two fingers (thumb and pointing finger). The system recognizes one dynamic and two static gestures. Recognition and pose estimation are user independent and robust. The system operates at the rate of 60 Hz and can be used as an intuitive input interface to applications that require multi-dimensional control. Examples include 3D fly-thru's, object manipulation and computer games.

A video-based gesture recognition system can serve as a natural and accurate 3D user input device. We describe a two-camera system, that recognizes three gesture classes: two static and one dynamic. For one of these gestures (pointing), the system estimates five parameters of 3D pose: position and pointing direction. The recognition is robust, independent of the user and fast (60 Hz), and the estimated pose is very stable. We describe some of the interface applications that demonstrate the benefits of the system: control of a video game, piloting a virtual reality fly-through, and interaction with a 3D scene editor.

It% dwctibe u nouel malti-dimensionalhand ges-Pdre inier~ace system and iti use in interactive spatial erpplications.The system squires input Jtrtafrom ttto cameras that look at user's hand, ~ecogrrizes three gesti~res and tracks the hand in SD space.at the rate of 60 Rz.Five spatial parameters (position and orientation in 3D) are compatedjor indu finger and the thumb, which gives the user a simultaneous control of up to ten parameters of an application.11'edesctibe some of the applications that have 6e&ncon:tircted to dernonstiate the capabilities of this s~rstern.They include an interface to a video game, piloting a virtual fig-through over temain bg hand pointing, interacting with a 3D scene editor by 'grasping" and moving objects in space, and a portial wntrol of an articulated model of a human hand.The gesture interface makes the control of fhese application very intaitive, and simpler than using the cument input devices.

This paper describes a system for real-time tracking of people in video sequences. The input to the system is live or recorded video data acquired by a stationary camera in an environment where the primary moving objects are people. The output consists of trajectories which give the spatio-temporal coordinates of individual persons as they move in the environment. The system uses a new model-based approach to object tracking. It identifies feature points in each video frame, matches feature points across frames to produce feature "paths", then groups short-lived and partially overlapping feature paths into longer living trajectories representing motion of individual persons. The path grouping is based on a novel model-based algorithm for motion clustering. The system runs on an SGI Indy workstation at an average rate of 14 frames a second. The system has numerous applications since various statistics and indicators of human activity can be derived from the motion trajectories. Examples of these indicators described in the paper include people counts, presence and time spent in a region, traffic density maps and directional traffic statistics.

A tracking system outputs a separate motion trajectory for each moving object in a scene. The paper presents a problem of performance evaluation and performance metrics for real time systems that track people, or moving objects, in video sequences, and it proposes performance measurement methodology for such systems. Two approaches to measuring performance are presented. The first approach compares the computed motion trajectories to the reference trajectories. It enables a complete evaluation of tracking results, but reference trajectories it requires are difficult to get. The second, more practical approach identifies in the computed trajectories specific discrete events, such as line crossings, and compares sequences of these events to sequences of reference events, which are much easier to obtain than reference trajectories. These events can usually be chosen such that they reflect the application goal of a tracking system, e.g. counting people in an area. Precision of evaluation increases with density of events. Short event sequences measure the sensitivity and selectivity of a tracking method, i.e. how well it satisfies the "one person one trajectory" objective. Long sequences measure continuity of trajectories: how long a method can keep track of one person. The paper shows performance measurement results for a real time people tracking system developed by the authors.

A method of learning structural models of 2D shape from real data is described and demonstrated. These models can be used to classify nonrigid shapes, even if they are partially occluded, and to label their parts. The representation of a single shape is a layered graph whose vertices correspond to n-ary relations. A class of shapes is represented as a probability model whose outcome is a graph. The method is based on two types of learning: unsupervised learning used to discover relations, and supervised learning used to build class models. The class models are constructed incrementally, by matching and merging graphs representing shape instances. This process uses a fast graph-matching heuristic which seeks a simplest representation of a graph. An important feature is the self-generation of symbolic primitives by an unsupervised learning process. This feature makes it possible to apply the system to any set of shape data without adjustments, while other methods might require the user to provide a different set of primitives for each case.>

A method that enables a robot system to learn how to grasp an object is presented. The method combines an automatic grasp discovery process with a visual recognition technique. When an object is seen the first time, the system experiments with it, seeking a way of grasping and lifting the object by trial and error, using visual information and input from the robot gripper. A discovered grasp configuration is saved along with the object's shape. When the same object is presented again in a different position and orientation, and the system recognizes its shape, the grasp information is retrieved and transformed to match the position and orientation of the object, so it can be picked in the first trial. The approach makes fewer assumptions, and requires less prior information about objects, than nonlearning grasp-determination methods. The presented method was implemented in a system with a robot and a servo-controlled two-finger gripper. Several examples of its operation are reported.>

A method is presented which provides a criterion for detecting a change in the structure of a model generating a stochastic sequence. Models that can be represented by a sequence of predictive probability distributions are considered. The method is based on the transformation of the observed sequence\{x_{n}\}into a sequence of partial sums of the general innovations, computed for the sequence\{-\log f(x_{n}|x_{n-1},x_{n-2}, \cdots ,x_{0})\}. If no change occurs the transformed sequence behaves like a Wiener process, but its mean will exhibit a monotonic growth after the process changes. Based on the properties of this transformation, fixed sample size and sequential tests for the change are constructed. The technique is applied to test for a change in the mean vector in a sequence of (generally dependent) Gaussian random variables, a change of coefficients of an autoregressive process, and a change of distribution in a sequence of discrete independent identically distributed random variables.