P. Maes, T. Darrel, B. Blumberg, S. Pentland. "The ALIVE system : Full-Body Interaction with Animated Autonomous Agent". M.I.T. Media Laboratory Perceptual Computing Technical Report No. 257, Jan. 1994.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....have applied GP to finding things in images. The most directly related to the work proposed here is by Martin, and is described above. Also similar is work by Johnson [10] which uses GP to learn visual routines [19] that were used to determine human actions in the ALIVE virtual environment [15]. The learned routines ran over silhouette images of a human, and detected things like hand position. The system uses a specialized LISP like language, similar to that used by Martin, and is capable of learning complex programs (on the order of hundreds of expressions) Koza [12] used GP to learn ....

Pattie Maes, Trevor Darrell, Bruce Blumberg, and Sandy Pentland. The ALIVE system: Full-body interaction with animated autonomous agents. In Proceedings of the Computer Animation Conference, Geneva, Switzerland. IEEE Press, 1995.

....via a touchscreen interface, large display walls are usually passive output devices with no intrinsic input capability aside from an external keyboard, mouse, or remote control. Various researchers have used computer vision with very large projection walls for experiments in augmented reality [2] and interactive dance [3] but most of this work concentrates on tracking activity in a extended room, rather than monitoring precise gesture at the surface of the screen itself. Close up interaction at large display walls, however, is a very interesting hybrid between the private dialog that one ....

Maes, P. et al . 1997. "The ALIVE System: Full-body interaction with animated autonomous agents," Multimedia Systems, vol.5, no.2, pp.105-112.

....to a planar floor. Pfinder provides a modular interface to client applications. Several clients can be serviced in parallel, and clients can attach and detach without affecting the vision routines. Pfinder is a descendant of the vision routines originally developed for the ALIVE system [15], which performed person tracking but had no explicit model of the person and required a controlled background. Pfinder is a more general, and more accurate method for segmentation, tracking and interpretation. Fig. 4 shows the image of a user as seen by the camera, together with the Pfinder blob ....

Maes, P. et. al. 1997. The ALIVE System: Full-body interaction with animated autonomous agents. ACM Multimedia Systems, Vol. 5, pp. 105-112.

....for their compromising constraints and or relatively disappointing overall performance. They can broadly be divided into non contact approaches and those that require contact with the user. The most familiar non contact interface is video, using one or more cameras to determine the users actions [1]. The canonical problemswith video are To be published in the Special Issue on Input Devices, IEEE Computer Graphics and Applications, May 1998 the difficulty in obtaining estimates faster than standard video ....

Maes, P. et. al., The ALIVE System: Full-body interaction with animated autonomous agents. ACM Multimedia Systems, Vol. 5, 1997, pp. 105-112.

....and even a fire hydrant) The magic mirror paradigm is attractive because it provides a set of domain constraints which are restrictive enough to allow simple vision routines to succeed, but is sufficiently unencumbered that is can be used by real people without training or a special apparatus. [13] One agent the user can interact with in ALIVE is a puppet that tries to act like a small child. The user can interact with the agent using certain hand gestures, which are interpreted in the context of the particular situation. For example, when the user points away and thereby sends the puppet ....

....is interpreted to mean that the user no longer wants the puppet to go away, and so the puppet will smile and return to the user. In this manner, the gestures employed by the user can have rich meaning which varies on the previous history, the agents internal needs and the current situation. [13] 4 Conclusion The preceding examples illustrate successful interfaces built for a wide range of application domains from animation to artistic expression to information browsing. They all differ in the mappings they employ between sensed features, and application control. However, they all have ....

Pattie Maes, Bruce Blumberg, Trevor Darrell, and Alex Pentland. The alive system: Full-body interaction with animated autonomous agents. ACM Multimedia Systems, 5:105--112, 1997.

....are often used to curtail the amount of data needed for analysis. Several systems that address whole body systems have been developed in the past. These include gait recognition and analysis systems [27, 14, 32, 42] ballet step recognition [5] body capture [1] real time interface systems [38, 23], and numerous others. Greater accuracy and detail can be gained by focusing attention on the body part of interest. Recent experimentation with active focus of attention systems is attracting interest to this topic [9] In the case of ASL, the hands and head are of the most interest. 2.2 ....

....machine recognition of ASL are discussed. 3.1 Hand Recovery With multimedia computers being packaged with video cameras, interest in human gesture recognition has grown. A large variety of interfaces have been proposed, using video driven gestures for mouse control [12] full body interactions [19, 23, 5], expression tracking [11] conducting music [24] and electronic presentation [38] Due to their expressiveness, the hands have been a point of focus for many gesture recognition systems. Tracking the natural hand in real time using camera imagery is difficult, but successful systems have been ....

[Article contains additional citation context not shown here]

Pattie Maes, Trevor Darrell, Bruce Blumberg, and Alex Pentland. The ALIVE system: full-body interaction with animated autonomous agents. MIT Media Lab Perceptual Computing Group Technical Report No. 257, Massachusetts Institute of Technology, 1994.

....These items are far more encumbering than would be a single item that performed all of the tasks that each was meant to do. Other developments, such as ubiquitous computing [1] have attempted to bring computing seamlessly into our daily lives. Ubiquitous multimedia computing and smart spaces [2] 3][4] would seem to suggest a future world in which we re surrounded with computing, as well as cameras, microphones, and other forms of perceptual intelligence during all facets of our daily lives. There are two problems with smart spaces: 1) Not all environments will ever be so equipped. Even if ....

Maes, Darrell, Blumberg, and Pentland. The alive system: Full-body interaction with animated autonomous agents. TR 257, M.I.T. Media Lab Perceptual Computing Section, Cambridge, Ma, 1994.

....also on my left. video image of the camera is superimposed with computer graphic objects) is a mediated reality zone, while the periphery (e.g. the user s own feet which can be seen by looking straight down) is outside this mediation zone. The Artificial Life Interactive Video Environment (ALIVE) [Maes et al. 1994] is similar to Myron Krueger s environment. In the ALIVE, a user sees him her self in a magic mirror created by displaying a left right reversed video image from a camera above the screen. Virtual objects, appear, for example, a virtual dog will come over and greet the user. ALIVE is also a ....

Maes, Darrell, Blumberg, and Pentland (1994). The alive system: Full-body interaction with animated autonomous agents. TR 257, M.I.T. Media Lab Perceptual Computing Section, Cambridge, Ma.

....and even a fire hydrant) The magic mirror model is attractive because it provides a set of domain constraints which are restrictive enough to allow simple vision routines to succeed, but is su#ciently unencumbered that is can be used by real people without training or a special apparatus. [8] ALIVE employed a gesture language that allowed the user to press buttons in the world or communicate wishes to the agents. ALIVE also employed audio perception. A commercial speech recognizer was used to turn speech events into commands for the agents. In this way speech provided a redundant ....

Pattie Maes, Bruce Blumberg, Trevor Darrell, and Alex Pentland. The alive system: Full-body interaction with animated autonomous agents. ACM Multimedia Systems, 5:105--112, 1997.

....of the Cog robot [Bro96] and the infrared sensors on the mobile robots of Mataric [Mat94] are typical of real world sensors. Synthetic vision techniques attempt to extract salient features from a physical scene rendered from the viewpoint of the creature; examples include the ALIVE system of Maes [MDBP94, MDBP96] and the artificial fish of Tu and Terzopolous [TT94] In direct sensing, creatures gain information by directly interrogating the world or an object within the world include; this is the approach taken by the boids of Reynolds [Rey87] and many video games. One of the important contributions of ....

Pattie Maes, Trevor Darrell, Bruce Blumberg, and Alex Pentland. The ALIVE system: full-body interaction with animated autonomous agents. MIT Media Lab Perceptual Computing Group Technical Report No. 257, Massachusetts Institute of Technology, 1994.

....and even a re hydrant) The magic mirror model is attractive because it provides a set of domain constraints which are restrictive enough to allow simple vision routines to succeed, but is suciently unencumbered that is can be used by real people without training or a special apparatus. [8] ALIVE employed a gesture language that allowed the user to press buttons in the world or communicate wishes to the agents. ALIVE also employed audio perception. A commercial speech recognizer was used to turn speech events into commands for the agents. In this way speech provided a redundant ....

Pattie Maes, Bruce Blumberg, Trevor Darrell, and Alex Pentland. The alive system: Full-body interaction with animated autonomous agents. ACM Multimedia Systems, 5:105-112, 1997.

....to implementation, with consequences for the reliability and scope of the reminders which can be delivered. Examples of the way location context may be acquired include GPS receivers (outdoors only) 6] tagged environments and portable sensors[9] wearable tags and smart environments[11, 5], computer vision[1, 10] and combinations of other types of sensors[4] Each of these techniques have speci c strengths and weaknesses, the most important being the degree of infrastructure dependence. Being able to condition reminders on location is a powerful addition to a proactive reminder ....

....phone, or a high risk task like crossing the street. The diculty is that recognizing user actions (or environmental conditions) generally requires high bandwidth sensing and sophisticated analysis. Computer vision techniques have been shown to be e ective in identifying user location and action [5, 1], but only recently has it become possible to do this type of sensing and analysis in an easily portable or wearable package, independent of outside infrastructure, with reasonable battery life and performance. The goal of the Memory Glasses project is to produce an activity location time based ....

Pattie Maes, Bruce Blumberg, Trevor Darrell, and Alex Pentland. The alive system: Full-body interaction with animated autonomous agents. ACM Multimedia Systems, 5:105-112, 1997.

....Improvisational Theater Space. Improvisational Theater provides us with an ideal playground for an IVE controlled stage in which embodied human actors and Media Actors [29] generate an emergent story through interaction among themselves and the public. Media Actors are semi autonomous agent based [18] text, images, movie clips, and audio. These are used to augment the play by expressing the actor s inner thoughts, memory, or imagery, or by playing other segments of the script. Among the wide variety of Theater styles and plays we have chosen to stage Improv (Improvisational Theater) This is ....

....even a fire hydrant) 10 The magic mirror paradigm is attractive because it provides a set of domain constraints which are restrictive enough to allow simple vision routines to succeed, but is sufficiently unencumbered that is can be used by real people without training or a special apparatus. [18] One agent the user can interact with in ALIVE is a puppet that tries to act like a small child. The user can interact with the agent using certain hand gestures, which are interpreted in the context of the particular situation. For example, when the user points away and thereby sends the puppet ....

[Article contains additional citation context not shown here]

Pattie Maes, Bruce Blumberg, Trevor Darrell, and Alex Pentland. The alive system: Full-body interaction with animated autonomous agents. ACM Multimedia Systems, 5:105--112, 1997.

....and to recover from errors. The central tracking and description algorithms, however, can equally well be applied to tracking vehicles or animals, and in fact we have done informal experiments in these areas. Pfinder is a descendant of the vision routines originally developed for the ALIVE system [9], which performed person tracking but had no explicit model of the person and required a controlled background. Pfinder is a more general, and more accurate, method for person segmentation, tracking, and interpretation. 2 Background The notion of grouping atomic parts of a scene together to form ....

....etc. and static gestures (e.g. standing, sitting, pointing, etc. 7.2 Gesture Control for ALIVE, SURVIVE In many applications it is desirable to have an interface that is controlled by gesture rather than by a keyboard or mouse. One such application is the Artificial Life IVE (ALIVE) system[9]. ALIVE utilizes Pfinder s support map polygon to define alpha values for video compositing (placing the user in a scene with some artificial life forms in real time) Pfinder s gesture tags and feature positions are used by the artificial life forms to make decisions about how to interact with ....

Pattie Maes, Bruce Blumberg, Trevor Darrell, and Alex Pentland. The alive system: Full-body interaction with animated autonomous agents. ACM Multimedia Systems, 5:105--112, 1997. (a) (b) (c) (d)

....a particular video game. The set of routines is fairly small and fixed, allowing a programmer to work them out by hand. Another example (and the one on which we will focus) is the simple vision system used by the ALIVE (Artificial Life Interactive Video Environment) virtual environment project [Maes et al. 1995, Maes et al. 1993] In this system, a user can interact in real time with a computer graphics creature using gestures which are interpreted by a vision system. The system employs a set of hand coded low level heuristics for solving specific visual tasks involved in processing live camera input ....

Pattie Maes, Trevor Darrell, Bruce Blumberg, and Sandy Pentland. The ALIVE System: Full-body Interaction with Animated Autonomous Agents. In Proceedings of the Computer Animation Conference, Geneva, Switzerland. IEEE Press, 1995.

....a different meaning in the virtual world, the system must be able to recognize when the user is performing a particular movement. This interpretation of human action is a goal shared by a large number of applications in the IVE space. Among them is the wireless virtual reality system, ALIVE [6]. In order for the dog in this system, Silas T. Dog, to understand the intentions of the human user, a real time system called pfinder (personfinder) was developed [12] that tracks the user s head, hands and body. While the user s distance from the camera and x y coordinates are determined by ....

P. Maes, B. Blumberg, T. Darrell, and A. Pentland. The ALIVE system: full-body interaction with animated autonomous agents. In ACM Multimedia Systems, in press.

....video game. The set of routines is fairly small and fixed, allowing a programmer to work them out by hand. Another similar example (and the one which we will focus on) is the simple vision system used by the ALIVE (Artificial Life Interactive Video Environment) virtual environment project [ Maes et al. 1994, Maes et al. 1993 ] In this system, a user can interact in real time with a computer graphics creature using gestures which are interpreted by a vision system. This system employed a set of hand coded low level heuristics for solving specific simple visual tasks involved in efficiently ....

....than simulated ones. 3 The Problem Find the Hands The simple image processing application we focus on for the preliminary study is that of finding the hands in the bitmap silhouette of a person. A solution to this problem was actually necessary for the ALIVE virtual environment project [ Maes et al. 1994 ] see Section 3.1) For ALIVE, a visual routine was written by hand for this task, applied when hand location was desired. We restrict the problem slightly for this study, to see if genetic programming can solve subgoals of the overall task. Specifically, we ask that the genetic programming ....

P. Maes, T. Darrell, B. Blumberg, and S. Pentland. The alive system: Full-body interaction with animated autonomous agents. Submitted for publication, 1994.

No context found.

P. Maes, T. Darrel, B. Blumberg, S. Pentland. "The ALIVE system : Full-Body Interaction with Animated Autonomous Agent". M.I.T. Media Laboratory Perceptual Computing Technical Report No. 257, Jan. 1994.

No context found.

P. Maes et al., "The Alive System: Full-Body Interaction with Animated Autonomous Agents," ACM Multimedia Systems, Vol. 5, No.2, 1997, pp. 105-112.

No context found.

Maes, P. Darrel, T., Blumberg B. and Pentland, A. (1994), "The ALIVE system : Full-Body Interaction with Animated Autonomous Agent". M.I.T. Media Laboratory Perceptual Computing Technical Report No. 257.

No context found.

P. Maes, T. Darrel, B. Blumberg and S. Pentland. "The ALIVE system : Full-Body Interaction with Animated Autonomous Agent". M.I.T. Media Laboratory Perceptual Computing Technical Report No. 257, Jan. 1994.

No context found.

P. Maes, T. Darrel, B. Blumberg, S. Pentland. "The ALIVE system : Full-Body Interaction with Animated Autonomous Agent". M.I.T. Media Laboratory Perceptual Computing Technical Report No. 257, Jan. 1994.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC