Abstract: THE SCHEMA SYSTEM EMBODIES A KNOWLEDGE-BASED APPROACH TO SCENE INTERPRE- TATION. LOW-LEVEL ROUTINES ARE APPLIED TO EXTRACT IMAGE DESCRIPTORS CALLED TOKENS, AND THESE TOKENS ARE FURTHER ORGANIZED BY INTERMEDIATE-LEVEL ROUT- INES INTO MORE ABSTRACT STRUCTURES THAT CAN BE ASSOCIATED WITH OBJECT INST- ANCES. THE THOUSANDS OF TOKENS THAT ARE EXTRACTED FROM AN IMAGE CAN BE GROUPED IN A COMBINATORIALLY EXPLOSIVE MANNER. THEREFORE, KNOWLEDGE IN THE SCHEMA SYSTEM IS NOT LIMITED TO THE DESCRIPTIONS OF OBJECTS; IT INCLUDES INFORMATION ABOUT HOW EACH OBJECT CAN BE RECOGNIZED. OBJECT SCHEMAS CONTROL THE INVOCATION AND EXECUTION OF THE LOW-LEVEL AND INTERMEDIATE-LEVEL ROUT- INES WITH THE GOAL OF FORMING HYPOTHESES ABOUT OBJECTS IN THE SCENE. THE SYSTEM DESCRIBED PRODUCES IMAGE INTERPRETATIONS BASED ON TWO-DIMENSIONAL REASONING, ALTHOUGH NOTHING IN THE SYSTEM ORGANIZATION AND CONTROL STRATEG- IES PRECLUDE THE INCLUSION OF THREE-DIMENSIONAL INFORMATION. THE SCHEMA FRAMEWORK EXPLOITS COARSE-GRAINED PARALLELISM IN A COOPERA- TIVE INTERPRETATION PROCESS. SCHEMA INSTANCES RUN CONCURRENTLY, AND AN OB- JECT SCHEMA OFTEN HAS AVAILABLE A VARIETY OF STRATEGIES FOR IDENTIFICATION, EACH ONE INVOKING KNOWLEDGE SOURCES TO GATHER SUPPORT FOR THE PRESENCE OF A HYPOTHESIZED OBJECT. INTER-SCHEMA COMMUNICATION IS CARRIED OUT ASYNCHRON- OUSLY THROUGH A GLOBAL BLACKBOARD. IN THIS WAY SCHEMA INSTANCES COOPERATE TO IDENTIFY AND LOCATE THE SIGNIFICANT OBJECTS PRESENT IN THE SCENE.

Abstract: An object based data processing system including an extensible set of object types and a corresponding set of "object managers" wherein each object manager is a program for operating with the data stored in a corresponding type of object. The object managers in general support at least a standard set of operations. Any program can effect performance of these standard operations on objects of any type by making an "invocation" request. In response to an invocation request, object management services (which are available to all object managers) identifies and invokes an object manager that is suitable for performing the requested operation on the specified type of data. A mechanism is provided for linking data from one object into another object. A object catalog includes both information about objects and about links between objects. Data interchange services are provided for communicating data between objects of different types, using a set of standard data interchange formats. A matchmaker facility permits two processes that are to cooperate in a data interchange operation identify each other and to identify data formats they have in common. A facility is provided for managing shared data "resources", Customized versions of resources can be created and co-exist with standard resources. A resource retrieval function determines whether a customized or a standard resource is to be returned in response to each request for a resource.

Abstract: A computer having a file management system is presented. The file management system includes a plurality of application programs, a plurality of data files a plurality of class data structures and a plurality of object data structures. Each class data structure includes a reference to an application program within the plurality of application programs. Each object data structure includes a reference to a class data structure from the plurality of class data structures and a reference to at least one data file from the plurality of data files. The use of object data structures adds a layer between a user of the computer and data files. This allows for the computer to refer to an object data structure and access file associated therewith using a tag which is inaccessible to the user. The user refers to an object based on the physical location of the object on the screen. The user may also give the object data structure a name, which is wholly unconnected to the value of the tag. This allows a user to, for instance, give two objects in the same directory, the same name. Additionally, the file management system includes a plurality of link data structures, each link data structure including a reference to a first object data structure in the plurality of object data structures which serves a parent object of the link, and including a reference to a second object data structure in the plurality of object data structures which serves as a child object of the link. Child objects and parent objects are not necessarily the same for each link data structure.

Abstract: An improved stereolithography system for generating a three-dimensional object by creating a cross-sectional pattern of the object to be formed at a selected surface of a fluid medium capable of altering its physical state in response to appropriate synergistic stimulation by impinging radiation, particle bombardment or chemical reaction, information defining the object being specially tailored to provide built-in supports for the object, reduce curl and distortion, and increase resolution, strength, accuracy, speed and economy of reproduction, the successive adjacent laminae, representing corresponding successive adjacent cross-sections of the object, being automatically formed and integrated together to provide a step-wise laminar buildup of the desired object, whereby a three-dimensional object is formed and drawn from a substantially planar surface of the fluid medium during the forming process

Abstract: A system and method for producing highly realistic video images which depict the appearance of a simulated structure in an actual environment, and provides for accurate placement of the structure in the environment and matching of the perspective of the structure with that of the environment so that a highly realistic result is achieved The system includes a video input means, such as a video camera and video recorder, by which a video image of the actual environment may be captured A graphics processor unit receives the video image from the video input means and stores it in rasterized form Field data input means is provided for receiving field location data regarding the precise location of the captured video image and field perspective data regarding the perspective of the captured image Object data input means is also provided for receiving data, such as CAD data for example, for a three-dimensional model of a simulated object which is proposed to be included in the environment From the three-dimensional model of the object, a two-dimensional perspective representation of the object is generated, which accurately matches the perspective of the captured video image The thus generated two-dimensional perspective representation is then merged with the rasterized video image and accurately positioned at its proper location in the environment

Abstract: An evidence-based recognition technique is defined that identifies 3-D objects by looking for their notable features. This technique makes use of an evidence rule base, which is a set of salient or evidence conditions with corresponding evidence weights for various objects in the database. A measure of similarity between the set of observed features and the set of evidence conditions for a given object in the database is used to determine the identity of an object in the scene or reject the object(s) in the scene as unknown. This procedure has polynomial time complexity and correctly identifies a variety of objects in both synthetic and real range images. A technique for automatically deriving the evidence rule base from training views of objects is shown to generate evidence conditions that successfully identify new views of those objects. >

Abstract: In engineering applications, multiple copies of object descriptions have to coexist in a single database. A scheme is proposed that enables users to explicitly deal with these object versions. After introducing a basic version model, the problem of rerouting interobject references on the creation of new versions is solved by providing generic references and user-specific environments. Logical version clusters are introduced that allow for the meaningful grouping of versions. Some remarks on implementation and a comparison with other approaches are also included. >

Abstract: A system for computer vision is based upon an image sensor that maps an image to memory cells in association with a computer. An object orientation and position patch is attached to an object to be observed comprising a planar substantially coplanar and non-collinear reflective locations positioned upon the patch and a reflector having the reflective properties of the surface of a regular curved surface intersecting the planar surface. The computer has a task stored in main memory for detecting and quantifying a change in orientation and position of the object from the location of the image of the orientation and position patch.

Abstract: An identification system to identify objects from a remote interrogation station may be used with moving objects such as railroad cars. The system remotely programs and stores information on an object and remotely retrieves information from the object. An information and identity storage device is located on the object and at least one interrogation station is located remotely from the object.

Abstract: Object Lens allows unsophisticated computer users to create their own cooperative work applications using a set of simple, but powerful, building blocks. By defining and modifying templates for various semistructured objects, users represent many different kinds of information. By creating semiautonomous agents, users specify rules for automatically processing this information in different situations.The combination of these primitives provides a single consistent interface that integrates facilities for object-oriented databases, hypertext, electronic messaging, and rule-based intelligent agents. To illustrate the power of this combined approach, we describe several simple examples of applications (such as task tracking, intelligent message routing, and database retrieval) that we have developed in this framework.

Abstract: In this paper the reader is introduced to coordination in the workplace as an object of scientific study and computer automation. Diplans are the expressions of a new graphical language used to describe plans of operation in human organizations. With diplans, systems of constraint, which may or may not take the form of procedure definitions, can be specified. Among the special strengths of diplans is their ability to render explicit the interactive aspects of complex work distributed over many people and places—in other words, coordination. Diplans are central to coordination technology, a new approach to developing support for cooperative work on heterogeneous computer networks.

Abstract: A system for continuously establishing and indicating the location of a movable object comprises a first transmitter secured to the object for periodically transmitting, at a first predetermined frequency, first radio frequency signals representative of an identification code uniquely associated with the object. A plurality of receiver/repeater stations are positioned at spaced locations within a predetermined geographic area, each receiver/repeater station including a plurality of spaced receivers for receiving and demodulating the first radio frequency signals to provide an object identification code signal and a device associated with each first receiver for determining the strength of the received first radio frequency signal and for generating a strength signal for each receiver. Signal processor circuitry and a computer are centrally located within the predetermined geographic area in communication with the first receiver and the strength determining device for receiving the signals representative of the object identification code and the strength signals, for calculating the location of the object based upon the strength signals and for storing signals representative of the object identification code and the location of the object. A master tracking station is in communication with the signal processing circuitry and computer for each of a plurality of predetermined geographic areas. The master tracking station receives and stores the signals representative of the object identification code and the object location and provides a visual indication of the object identification code and object location.

Abstract: There are two major issues to address to achieve integration of an object-oriented programming system with a database system. One is the language issue: an object-oriented programming language must be augmented with semantic data modeling concepts to provide a robust set of data modeling concepts to allow modeling of entities for important real-world applications. Another is the computational-model issue: application programmers should be able to access and manipulate objects as though the objects are in an infinite virtual memory; in other words, they should not have to be aware of the existence of a database system in their computations with the data structures the programming language allows. This paper discusses these issues and presents the solutions which we have incorporated into the ORION object-oriented database system at MCC.

Abstract: The author provides a general introduction to computer vision. He discusses basic techniques and computer implementations, and also indicates areas in which further research is needed. He focuses on two-dimensional object recognition, i.e. recognition of an object whose spatial orientation, relative to the viewing direction is known. >

Abstract: A distributed digital data processing system includes a plurality of nodes which communicate over a network. A node maintains one or more objects, each of which may be a file, that is, an addressable unit in the system, such as a program, database, text file, or the like, or a directory which may contain one or more files or other directories. One node maintains a naming service which associates each object in the system with one or more protocol towers. Each protocol tower identifies the object name and a series of entries each identifying a name for each of the protocol layers, along with the communications parameters and address information, to be used in communicating with the object. When a node requires access to an object maintained by another node, it first retrieves from the naming service the protocol towers for the object. The node also maintains a tower identifying the names of each of the protocols over which it can communicate. The node then compares the protocol names in the retrieved protocol towers with the protocol names over which it can communicate. If the protocol names in a retrieved tower match the protocol names in the node's tower, the node uses the communications parameters and address information in future communications with the object. If the node is unable to identify a retrieved protocol tower which matches its supported tower or towers, it is unable to communicate with the object.

Abstract: Complex-log conformal mapping is combined with a distributed associative memory to create a system that recognizes objects regardless of changes in rotation or scale. Information recalled from the memorized database is used to classify an object, reconstruct the memorized version of the object, and estimate the magnitude of changes in scale or rotation. The system response is resistant to moderate amounts of noise and occlusion. Several experiments using real gray-scale images are presented to show the feasibility of the approach. >

Abstract: Apparatus and methods of verifying objects utilize an inherent randomly varying and detectable characteristics of a plurality of spaced apart, magnetizable magnetic regions affixed to the object. Detectability of the randomly varying magnetic characteristics can be enhanced by saturating the magnetic regions. A verification apparatus senses the randomly varying magnetic characteristics and compares it to a prestored representative profile previously created. Correspondence between the prestored profile and the currently read characteristics indicates an authentic object. Other objects can be rejected.

Abstract: A description is given of the development of a model-based vision system that utilizes hierarchies of both object structure and object scale. The focus of the research is to use these hierarchies to achieve robust recognition based on effective organization and indexing schemes for model libraries. The goal of the system is to recognize parameterized instances of nonrigid model objects contained in a large knowledge base, despite the presence of noise and occlusion. The approach presented is to develop an object shape representation that incorporates a component subpart hierarchy, to allow for efficient and correct indexing into an automatically generated model library as well as for relative parametrization among subparts, and a scale hierarchy, to allow for a general to specific recognition procedure. The implemented system uses a representation based on significant contour curvature changes and recognition engine based on geometric constraints of feature properties. Examples of the system's performance are given, followed by an analysis of the results. >

Abstract: First, we review recent efforts to demonstrate language competence in apes and dolphins. Then, with techniques originally devised by Herman in his artificial language studies with dolphins (Tursiops truncatus), we show that smaller brained sea lions (Zalophus californianus), like larger brained dolphins, are capable of comprehending signals about a relationship between two designated objects. The language we used consisted of signs designating properties of size, brightness, or location (modifiers), types of objects, and actions. The results of our experiments with two sea lions support Premack’s notion that Herman’s dolphins (as well as our sea lions) relied principally on two phrase structure rules to comprehend thousands of novel, unique messages that could be transmitted gesturally by a “blind” human signaler. One rule instructs the animal to perform an action directly on an object designated by an object signal and one or two optional modifiers. The instruction takes the form (Modifier) + Object + Action. The second rule instructs the animal to perform an action relative to two designated objects. The object to be transported and the goal object were assigned their particular roles by their position in the sign sequence. The relational instruction takes the form (Modifier) + Object A + (Modifier) + Object B + Action. Reversing the order of the two object signals in the string reversed the meaning of the message. For both sea mammals we found support for Herman’s notion that the critical constraint on the application of the second rule is memory for Object A (the goal item). The variables influencing memory for the goal item were: (a) the number of objects available, (b) bias for certain goal items, (c) whether the goal item was fixed in space, that is whether it was a transportable or nontransportable object, and (d) whether the goal item (Object A) and the transported item were reversed on successive trials. We conclude that both dolphins and sea lions can be taught to comprehend sentence-like instructions. The simplified language learned by these marine mammals depends on the following learned cognitive skills: (a) acquiring a repertoire of arbitrary conditional relations between signals and objects, (b) perceiving and conceptualizing objects and events within class and relational categories, and (c) acquiring a conditional sequential discrimination.

Abstract: This paper describes how ontological concepts can be used to model information systems. We view an information system as an object that is independent of its use or its technology of implementation. The main premise of the model is that an information system is a representation of a real-world system, and as such it should possess certain characteristics, We show how the model can be used to define various concepts such as real-time, batch, data processing, management reporting, decision support, controls, and decomposition. Furthermore, we show how the model may serve as the foundation of a theory of systems analysis and design. In particular, it provides a formal definition of information systems specifications and a normative model of decomposition.

Abstract: This paper presents a robotic perceptual system which utilizes passive vision and active touch. The task is one-fingered exploration of a single unmodeled object for apprehension— the determination of the features of the object and the rela tions among them. A two-stage exploration is utilized. Vision is first used in a feedforward manner to segment the object and to obtain its position. Touch is then used in a feedback mode to further explore the object. In designing this system, we have addressed several issues. The first concerns the way in which the robotic perceptual system should be structured. The model which we propose here is based upon theories of human perception. It consists of a highly modularized set of knowledge-based modules, each of which is domain specific and informationally encapsulated. Within the framework of this model, we have designed both vision and touch subsys tems. In each case, we have defined the primitives, features, and representations extracted and created by the system. ...

Abstract: Object models have an important part to play in the future of database systems, but progress is hampered by lack of agreement on their essential characteristics. Strong constraints on the design of a common model are exercised by the need to interface well with object models in programming languages, and the desirability of a smooth evolution from existing database technology.

Abstract: The authors show how the process of object class definition by generalization can be incorporated into object-oriented systems. Traditional message handling, which is mainly based on downward property inheritance, is revised and extended to upward property inheritance, so that a maximum of reusability of code and data can be achieved. Different types of semantic relationships that may hold between a generalization class's subclasses and their attributes are identified. The different semantic relationships can then be utilized to produce different default treatments of messages and upward property propagation.

Abstract: A replicated directory system based on a method called regeneration is designed and implemented. The directory system allows selection of arbitrary object to be replicated, choice of the number of replicas for each object, and placement of the copies on machines with independent failure modes. Copies can become inaccessible due to node crashes, but as long as a single copy survives, the replication level is restored by automatically replacing lost copies on other active machines. The focus is on a regeneration algorithm for replica replacement and its application to a replicated directory structure in the Eden local area network. A simple probabilistic approach is used to compare the availability provided by the algorithm to three other replication techniques. >

Abstract: Apparatus and method for obtaining three-dimensional information about an object, includes a first optical system, a projection device, a second optical system, and an image sensor. A plurality of pattern beams are radiated onto the object through the first optical system. Optical images formed by the pattern beams on the object are received by the image sensor through the second optical system to detect the positions of the received optical images. The distances from the detected positions of the optical images to a plurality of positions on the object are measured, thereby obtaining three-dimensional information about the object.

Abstract: A fast, efficient, algorithm that processes polyhedral cones from views of an object to produce an octree representation of the object is proposed. A polyhedral cone defined by both a viewpoint and a polygonal contour of the object in the image for each view always contains the object. Thus the common region of the cones for multiple views is considered to be an approximating one of the object. The octree representation controls all cubic regions in three-dimensional space as a set of nodes with a hierarchical description in positioning, and therefore is suitable for registration of the common region. The computational complexity of the algorithm is directly proportional to the common region surface area and exponentially proportional to the finest resolution level of the octree. The calculation time of the algorithm is determined for illustrative examples of three-dimensional objects. >

Abstract: The set-height of a complex object type is defined to be its level of nesting of the set construct. In a query of the complex object calculus which maps a database D to an output type T, an intermediate type is a type which is used by some variable of the query, but which is not present in D or T. For each k, i ≥ 0 we define CALCk,i to be the family of calculus queries mapping from and to types with set-height ≤ k and using intermediate types with set-height ≤ i In particular, CALC0,0 is the relational calculus, and CALC0,1 is equivalent to the family of second-order (relational) queriesSeveral results concerning these families of languages are obtained. A primary focus is on the families CALC0,i, which map relations to relations Upper bounds on the complexity of these families are provided, and it is shown that CALC0,3 has at least the complexity of exponential space. The CALC0,i hierarchy does not collapse, because for each i, CALC0,i is strictly less expressive than CALC0,i+2. The union ∪0≤iCALC0,i is strictly less expressive than the family of 'computable' database queries.The expressive power of queries from the complex object calculus interpreted using a semantics based on the use of arbitrarily large finite numbers of invented values is studied. Under this semantics, the expressive power of the relational calculus is not increased, and the CALC0,i hierarchy collapses at CALC0,1. We also consider queries which use a bounded number of invented values.