Showing papers on "Object model published in 2005"

Pictorial Structures for Object Recognition

Abstract: In this paper we present a computationally efficient framework for part-based modeling and recognition of objects. Our work is motivated by the pictorial structure models introduced by Fischler and Elschlager. The basic idea is to represent an object by a collection of parts arranged in a deformable configuration. The appearance of each part is modeled separately, and the deformable configuration is represented by spring-like connections between pairs of parts. These models allow for qualitative descriptions of visual appearance, and are suitable for generic recognition problems. We address the problem of using pictorial structure models to find instances of an object in an image as well as the problem of learning an object model from training examples, presenting efficient algorithms in both cases. We demonstrate the techniques by learning models that represent faces and human bodies and using the resulting models to locate the corresponding objects in novel images.

A sparse object category model for efficient learning and exhaustive recognition

Abstract: We present a "parts and structure" model for object category recognition that can be learnt efficiently and in a semi-supervised manner: the model is learnt from example images containing category instances, without requiring segmentation from background clutter. The model is a sparse representation of the object, and consists of a star topology configuration of parts modeling the output of a variety of feature detectors. The optimal choice of feature types (whose repertoire includes interest points, curves and regions) is made automatically. In recognition, the model may be applied efficiently in an exhaustive manner, bypassing the need for feature detectors, to give the globally optimal match within a query image. The approach is demonstrated on a wide variety of categories, and delivers both successful classification and localization of the object within the image.

Homography-based visual servo regulation of mobile robots

Abstract: A monocular camera-based vision system attached to a mobile robot (i.e., the camera-in-hand configuration) is considered in this paper. By comparing corresponding target points of an object from two different camera images, geometric relationships are exploited to derive a transformation that relates the actual position and orientation of the mobile robot to a reference position and orientation. This transformation is used to synthesize a rotation and translation error system from the current position and orientation to the fixed reference position and orientation. Lyapunov-based techniques are used to construct an adaptive estimate to compensate for a constant, unmeasurable depth parameter, and to prove asymptotic regulation of the mobile robot. The contribution of this paper is that Lyapunov techniques are exploited to craft an adaptive controller that enables mobile robot position and orientation regulation despite the lack of an object model and the lack of depth information. Experimental results are provided to illustrate the performance of the controller.

A method and a system relating to network management

Abstract: The present invention relates to a method for network management comprising configuration of control protocols between network elements in a network represented through a current, static, network element object model comprising a number of managed objects with attributes and instances and representing resources. It comprises the steps of : transforming the current network element object model to a machine readable and executable formal network element object model; identifying configuration tasks needed for the configuration of the relevant control protocols; modelling a formal configuration task model using information about the configuration tasks and the formal network element object model; building a formal configuration workflow model using the formal network element object model and the formal configuration task model, said formal configuration workflow model defining the relationships between different configuration tasks required for performing or completing a number of given actions or to achieve a number of given goals.

Realistic virtual grasping

Abstract: We present a physically-based approach to grasping and manipulation of virtual objects that produces visually realistic results, addresses the problem of visual interpenetration of hand and object models, and performs force rendering for force-feedback gloves in a single framework Our approach couples tracked hand configuration to a simulation-controlled articulated hand model using a system of linear and torsional spring-dampers We discuss an implementation of our approach that uses a widely-available simulation tool for collision detection and response We illustrate the resulting behavior of the virtual hand model and of grasped objects, and we show that the simulation rate is sufficient for control of current force-feedback glove designs We also present a prototype of a system we are developing to support natural whole-hand interactions in a desktop-sized workspace

System and method for 3d object recognition using range and intensity

Abstract: A system and method for performing object and class recognition that allows for wide changes of viewpoint and distance of objects is disclosed. The invention provides for choosing pose-invariant interest points of a three-dimensional (3D) image, and for computing pose-invariant feature descriptors of the image. The system and method also allows for the construction of three-dimensional (3D) object and class models from the pose-invariant interest points and feature descriptors of previously obtained scenes. Interest points and feature descriptors of a newly acquired scene may be compared to the object and/or class models to identify the presence of an object or member of the class in the new scene.

Automated three-dimensional alternative position viewer

Abstract: Computer-implemented method and apparatus for processing data representing a three-dimensional object model includes generating an image of a modeled object. The modeled object is formed from a number of different components that can be arranged in different positions, and the generated image depicts a change in a position of a first one of the components with respect to a second one of the components.

An architecture for biological information extraction and representation

Abstract: Motivations: Technological advances in biomedical research are generating a plethora of heterogeneous data at a high rate. There is a critical need for extraction, integration and management tools for information discovery and synthesis from these heterogeneous data. Results: In this paper, we present a general architecture, called ALFA, for information extraction and representation from diverse biological data. The ALFA architecture consists of: (i) a networked, hierarchical, hyper-graph object model for representing information from heterogeneous data sources in a standardized, structured format; and (ii) a suite of integrated, interactive software tools for information extraction and representation from diverse biological data sources. As part of our research efforts to explore this space, we have currently prototyped the ALFA object model and a set of interactive software tools for searching, filtering, and extracting information from scientific text. In particular, we describe BioFerret, a meta-search tool for searching and filtering relevant information from the web, and ALFA Text Viewer, an interactive tool for user-guided extraction, disambiguation, and representation of information from scientific text. We further demonstrate the potential of our tools in integrating the extracted information with experimental data and diagrammatic biological models via the common underlying ALFA representation. Contact: aditya_vailaya@agilent.com

Photogrammetric reconstruction of free-form objects with curvilinear structures

Abstract: The shapes of many natural or man-made objects have curve features. The images of such curves usually do not have sufficient distinctive features to apply conventional feature-based reconstruction algorithms. In this paper, we introduce a photogrammetric method for recovering free-form objects with curvilinear structures. Our method chooses to obtain the topology and geometry of a sparse 3D wireframe of the object first instead of directly recovering a surface or volume model. Surface patches covering the object are then constructed to interpolate the curves in this wireframe while satisfying certain heuristics such as minimal bending energy. The result is an object surface model with curvilinear structures from a sparse set of images. We can produce realistic texture-mapped renderings of the object model from arbitrary viewpoints. Reconstruction results on multiple real objects are presented to demonstrate the effectiveness of our approach.

Methods and systems for creating skins

Abstract: Methods and systems for creating and rendering skins are described. In one described embodiment skins can be defined as sets of script files, art files, media files, and text files. These files can be used to create new and different skin appearances, layouts and functionalities. The files are organized for use using a hierarchical tag-based data structure, an example of which is an XML data structure. The data structure is processed to provide an object model. The object model can be a scriptable object model that enables script to execute to provide an interactive, dynamic skin that can respond to internal and external events. In one embodiment, a computer architecture used for rendering the skin includes a layout manager that processes an intermediate representation of the XML data structure to provide the scriptable object model. Various components of the scriptable object model can include a script engine for receiving and executing script, and one or more rendering elements. Each rendering element represents a different skin element and can be individually configured to respond to script via the script engine. The inventive systems and techniques can provide a robust, dynamic skin that can be rendered and re-rendered at runtime.

Object model tree diagram

Abstract: A designer tool that facilitates design of an object model. The tool takes as input a computer-readable representation of a graph of objects (e.g., classes), and creates automatically one or more diagrams that depict these classes as editable trees showing their relationships and properties. These graphs naturally have a tree-like structure which is exploited by the approach. The design tool system includes a layout component that receives as input one or more of the graphs, and converts the one or more graphs into the editable treelike structure. The system further comprises a presentation component that presents the editable treelike structure as a treelike structure diagram, and facilitates user interaction therewith. The tool can be used for opening, editing and saving existing object model files or to create new ones.

Function-based object model for web page display in a mobile device

Abstract: By understanding a website author's intention through an analysis of the function of a website, website content can be adapted for presentation or rendering in a manner that more closely appreciates and respects the function behind the website A website's function is analyzed so that its content can be adapted to different client environments A function-based object model (FOM) identifies objects associated with a website, and analyzes those objects in terms of their functions Desktop oriented websites are adapted for mobile devices based on the FOM and on a mobile control intermediary language

RT-Component Object Model in RT-Middleware—Distributed Component Middleware for RT (Robot Technology)

Abstract: This paper proposes RT-component object model in RT-middleware for robot system integration "RT" means "robot technology", which is applied not only to industrial field but also to nonindustrial field such as human daily life support systems RT-middleware is a software infrastructure for RT systems We have studied modularization of RT elements at software level For that reason, RT-middleware, which promotes application of RT in various field, have been developed Robotic system development methodology and our RT-middleware concepts was discussed RT-component, which is a basic software unit of RT-middleware based system integration, is derived from that discussion Next, the object model and the interface definition of RT-component architecture was discussed Finally conclusion and future work are described

Feature-based design and material blending for free-form heterogeneous object modeling

Abstract: In this paper, a new feature-based method is proposed to represent and design heterogeneous objects. Material governing features are defined to control material composition inside the objects. Interrelations between the material governing features and material attributes are established in the design process and retained in the object model. Free-form B-spline functions are used to represent complex shapes of geometry and material features. A new material feature blending method is used to determine continuous material variation. To obtain the best material features, an optimization problem is constructed based on the object's functional requirements. Variant models are easily generated by changing the geometric and material features using the constraints between them. Implementation and examples are also presented in this paper.

Image generation method and device

Abstract: An image generation method for generating a viewpoint-modified image is carried out based on camera information sensed by one or a plurality of image sensing unit sensing an image around an image sensing unit-disposed object. The image generation method comprises displaying an image sensing unit-disposed object model on the viewpoint-modified image, detecting the change of the movable member of the image sensing unit-disposed object and transforming/displaying the relevant part of the image sensing unit-disposed object model in the viewpoint-modified image. The image generation method can also comprise transforming/displaying the virtual viewpoint position of the viewpoint-modified image, according to the amount of change of the movable member of the image sensing unit-disposed object.

Methods and system for controlling an image generator to define, generate, and view goemetric images of an object

Abstract: Methods, systems, and articles of manufacture consistent with the present invention allow a user operating on a data processing computer to view geometry of an object model produced by an image generator hosted on an image processing computer by allowing the user to define a zone associated with the object model, slices of each zone, and viewpoints associated with the slices, controlling the graphics image generator to produce geometric images of the object model in accordance with the zone, slices, and viewpoints, and selectively navigating the images in accordance with the zone, slices , and viewpoints.

A hierarchical representation for heterogeneous object modeling

Abstract: A hierarchical representation for heterogeneous object modeling is presented in this paper. To model a heterogeneous object, Boundary representation is used for geometry representation, and a novel Heterogeneous Feature Tree (HFT) structure is proposed to represent the material distributions. HFT structure hierarchically organizes the material variation dependency relationships and is intuitive in modeling different types of material gradations. Based on the HFT structure, a recursive material evaluation algorithm is proposed to dynamically evaluate the material compositions at a specific location. Such a hierarchical representation guarantees complex material gradations and the user's design intent can be intuitively represented. Example heterogeneous objects modeled with this scheme are provided and potential applications are discussed.

Exploiting relationships for object consolidation

Abstract: Data mining practitioners frequently have to spend significant portion of their project time on data preprocessing before they can apply their algorithms on real-world datasets. Such a preprocessing is required because many real-world datasets are not perfect, but rather they contain missing, erroneous, duplicate data and other data cleaning problems. It is a well established fact that, in general, if such problems with data are not corrected, applying data mining algorithm can lead to wrong results. The latter is known as the "garbage in, garbage out" principle. Given the significance of the problem, numerous data cleaning techniques have been designed in the past to address the aforementioned problems with data.In this paper, we address one of the data cleaning challenges, called object consolidation. This important challenge arises because objects in datasets are frequently represented via descriptions (a set of instantiated attributes), which alone might not always uniquely identify the object. The goal of object consolidation is to correctly consolidate (i.e., to group/determine) all the representations of the same object, for each object in the dataset. In contrast to traditional domain-independent data cleaning techniques, our approach analyzes not only object features, but also additional semantic information: inter-objects relationships, for the purpose of object consolidation. The approach views datasets as attributed relational graphs (ARGs) of object representations (nodes), connected via relationships (edges). The approach then applies graph partitioning techniques to accurately cluster object representations. Our empirical study over real datasets shows that analyzing relationships significantly improves the quality of the result.

3D object recognition

Abstract: A method, device, system, and computer program for object recognition of a 3D object of a certain object class using a statistical shape model for recovering 3D shapes from a 2D representation of the 3D object and comparing the recovered 3D shape with known 3D to 2D representations of at least one object of the object class.

Rich object model for diverse Auto-ID tags

Abstract: A system and method allowing one application to implement diverse AutoID tags interchangeably, by unifying all AutoID technologies into a single object model. The single object model interacts with all AutoID technologies, with only a lowest level device tailored to the specific AutoID technology, the single object model thereby persisting through the middleware, up to an application, carrying all necessary information from any AutoID technology. The single object model can interact with a tag many times, as necessary to complete an operation. A reader interface allows an application to communicate with multiple readers of diverse AutoID tags, and to communicate with individual servers communicating with individual readers of diverse AutoID tags. The reader interface also provides a single interface for hardware communication with a radio, for an application interacting with an entire network of readers, sensors, interpretation steps, product lookup, and information storage providing a single virtual reader.

The emergence of links between lexical acquisition and object categorization: a computational study

Abstract: Language is about symbols, and those symbols must be grounded in the physical world. Children learn to associate language with sensorimotor experiences during their development. In light of this, we first provide a computational account of how words are mapped to their perceptually grounded meanings. Moreover, the main part of this work proposes and implements a computational model of how word learning influences the formation of object categories to which those words refer. This model simulates the bi-directional relationship between word and object category learning: (1) object categorization provides mental representations of meanings that are mapped to words to form lexical items; (2) linguistic labels help object categorization by providing additional teaching signals; and (3) these two learning processes interplay with each other and form a developmental feedback loop. Compared with the method that performs these two tasks separately, our model shows promising improvements in both word-to-world mapp...

Object tracking with dynamic feature graph

Abstract: Two major problems for model-based object tracking are: 1) how to represent an object so that it can effectively be discriminated with background and other objects; 2) how to dynamically update the model to accommodate the object appearance and structure changes Traditional appearance based representations (like color histogram) fails when the object has rich texture In this paper, we present a novel feature based object representation attributed relational graph (ARG) for reliable object tracking The object is modeled with invariant features (SIFT) and their relationship is encoded in the form of an ARG that can effectively distinguish itself from background and other objects We adopt a competitive and efficient dynamic model to adoptively update the object model by adding new stable features as well as deleting inactive features A relaxation labeling method is used to match the model graph with the observation to gel the best object position Experiments show that our method can get reliable track even under dramatic appearance changes, occlusions, etc

Design and implementation of a Space-Time Intelligence System for disease surveillance

Abstract: Modeling chronic and infectious diseases entails tracking and describing individuals and their attributes (such as disease status, date of diagnosis, risk factors and so on) as they move and change through space and time. Using Geographic Information Systems, researchers can model, visualize and query spatial data, but their ability to address time has been limited by the lack of temporal referencing in the underlying data structures. In this paper, we discuss issues in designing data structures, indexing, and queries for spatio-temporal data within the context of health surveillance. We describe a space-time object model that treats modeled individuals as a chain of linked observations comprised of an ID, space-time coordinate, and time-referenced attributes. Movement models for these modeled individuals are functions that may be simple (e.g. linear, using vector representation) or more complex. We present several spatial, temporal, spatio-temporal and epidemiological queries emergent from the data model. We demonstrate this approach in a representative application, a simulation of the spread of influenza in a hospital ward.

Architecture, programming model and API'S

Abstract: The subject invention provides a system and/or a method that facilitates employing a model based at least upon a framework, wherein the model can be utilized to build an RFID application. A receiver component can receive data, wherein a model component can create a model based at least in part upon the received data that facilitates creating and/or executing the RFID application. The framework can be, but is not limited to, an entity, a framework class, a hierarchical framework of at least one class, an interface, an exception, a component architecture, a schema, an object model, and/or an API (Application Programming Interface). The model can be utilized to create, deploy, manage, and/or execute the RFID application to provide a generic operation and/or a business specific scenario.

Tracking objects in low frame rate videos

Abstract: A method tracks a moving object in a video acquired of a scene with a camera. A background model is maintained for each frame, and moving objects are detected according to changes in the background model. An object model is maintained for the moving object, and kernels are generated for the moving object. A mean-shift process is applied to each kernel in each frame to determine a likelihood of an estimated location of the moving object in each frame, according to the background models, the object model, and the mean shift kernels to track the moving object in the video.

Developing natural resource models using the object modeling system: feasibility and challenges

Abstract: Current challenges in natural resource management have created demand for integrated, flexible, and easily parameterized hydrologic models. Most of these monolithic models are not modular, thus modifications (e.g., changes in process representation) require considerable time, effort, and expense. In this paper, the feasibility and challenges of using the Object Modeling System (OMS) for natural resource model development will be explored. The OMS is a Java-based modeling framework that facilitates simulation model development, evaluation, and deployment. In general, the OMS consists of a library of science, control, and database modules and a means to assemble the selected modules into an application-specific modeling package. The framework is supported by data dictionary, data retrieval, GIS, graphical visualization, and statistical analysis utility modules. Specific features of the OMS that will be discussed include: 1) how to reduce duplication of effort in natural resource modeling; 2) how to make natural resource models easier to build, apply, and evaluate; 3) how to facilitate long-term maintainability of existing and new natural resource models; and 4) how to improve the quality of natural resource model code and ensure credibility of model implementations. Examples of integrating a simple water balance model and a large monolithic model into the OMS will be presented.

Extensible object-modelling mechanism

Abstract: An XML management system, comprising: a repository configured to store a manipulable object model capable of representing metadata about objects in a user's computing environment; user accessible means for manipulating said object model to modify properties of objects thus represented; and means for extending said object model to handle a new type of object by automatically generating descendent class(es) that are able to handle the new object within the object model and incorporating them into an XML management system runtime environment for participation in the object modelling process.

Methods, systems and media players for rendering different media types

Abstract: Methods and systems are described that assist media players in rendering different media types. In some embodiments, a unified rendering area is provided and managed such that multiple different media types are rendered by the media player in the same user interface area. This unified rendering area thus permits different media types to be presented to a user in an integrated and organized manner. An underlying object model promotes the unified rendering area by providing a base rendering object that has properties that are shared among the different media types. Object sub-classes are provided and are each associated with a different media type, and have properties that extend the shared properties of the base rendering object. In addition, an inventive approach to visualizations is presented that provides better synchronization between a visualization and its associated audio stream.