Showing papers on "Object model published in 2006"

Robust Fragments-based Tracking using the Integral Histogram

Abstract: We present a novel algorithm (which we call "Frag- Track") for tracking an object in a video sequence. The template object is represented by multiple image fragments or patches. The patches are arbitrary and are not based on an object model (in contrast with traditional use of modelbased parts e.g. limbs and torso in human tracking). Every patch votes on the possible positions and scales of the object in the current frame, by comparing its histogram with the corresponding image patch histogram. We then minimize a robust statistic in order to combine the vote maps of the multiple patches. A key tool enabling the application of our algorithm to tracking is the integral histogram data structure [18]. Its use allows to extract histograms of multiple rectangular regions in the image in a very efficient manner. Our algorithm overcomes several difficulties which cannot be handled by traditional histogram-based algorithms [8, 6]. First, by robustly combining multiple patch votes, we are able to handle partial occlusions or pose change. Second, the geometric relations between the template patches allow us to take into account the spatial distribution of the pixel intensities - information which is lost in traditional histogram-based algorithms. Third, as noted by [18], tracking large targets has the same computational cost as tracking small targets. We present extensive experimental results on challenging sequences, which demonstrate the robust tracking achieved by our algorithm (even with the use of only gray-scale (noncolor) information).

Towards Multi-View Object Class Detection

Abstract: We present a novel system for generic object class detection. In contrast to most existing systems which focus on a single viewpoint or aspect, our approach can detect object instances from arbitrary viewpoints. This is achieved by combining the Implicit Shape Model for object class detection proposed by Leibe and Schiele with the multi-view specific object recognition system of Ferrari et al. After learning single-view codebooks, these are interconnected by so-called activation links, obtained through multi-view region tracks across different training views of individual object instances. During recognition, these integrated codebooks work together to determine the location and pose of the object. Experimental results demonstrate the viability of the approach and compare it to a bank of independent single-view detectors

Multiple Object Class Detection with a Generative Model

Abstract: In this paper we propose an approach capable of simultaneous recognition and localization of multiple object classes using a generative model. A novel hierarchical representation allows to represent individual images as well as various objects classes in a single, scale and rotation invariant model. The recognition method is based on a codebook representation where appearance clusters built from edge based features are shared among several object classes. A probabilistic model allows for reliable detection of various objects in the same image. The approach is highly efficient due to fast clustering and matching methods capable of dealing with millions of high dimensional features. The system shows excellent performance on several object categories over a wide range of scales, in-plane rotations, background clutter, and partial occlusions. The performance of the proposed multi-object class detection approach is competitive to state of the art approaches dedicated to a single object class recognition problem.

The quarks of object-oriented development

Abstract: A two-construct taxonomy is used to define the essential elements of object orientation through analysis of existing literature.

Service-oriented infrastructure management

Abstract: A method for computing includes specifying a data processing system using a logical system definition, which defines logical system components having respective functionalities and a topology for interconnecting the logical system components. The logical system components are represented using respective logical objects in a hierarchical object model. Physical resources of a grid computer system are represented using physical objects in the hierarchical object model. The logical objects are automatically mapped to at least some of the physical objects, so as to allocate the physical resources to carry out the respective functionalities of the logical system components. The allocated physical resources are configured and activated so as to cause the grid computer system to function as the data processing system, in accordance with the logical system definition.

Modeling and Detection of Geospatial Objects Using Texture Motifs

Abstract: We propose the use of texture motifs, or characteristic spatially recurrent patterns, for modeling and detecting geospatial objects. A method is proposed for learning a texture-motif model from object examples and detecting objects based on the learned model. The model is learned in a two-layered framework: the first learns the constituent "texture elements" of the motif and, the second, the spatial distribution of the elements. In the experimental session, we demonstrate the model training and selection methodology for objects given a set of training examples. The utility of such models for detecting the presence or absence of geospatial objects in large aerial image datasets comprising tens of thousands of image tiles is then emphasized

Integrated Grasp Planning and Visual Object Localization For a Humanoid Robot with Five-Fingered Hands

Abstract: In this paper we present a framework for grasp planning with a humanoid robot arm and a five-fingered hand. The aim is to provide the humanoid robot with the ability of grasping objects that appear in a kitchen environment. Our approach is based on the use of an object model database that contains the description of all the objects that can appear in the robot workspace. This database is completed with two modules that make use of this object representation: An exhaustive offline grasp analysis system and a real-time stereo vision system. The offline grasp analysis system determines the best grasp for the objects by employing a simulation system, together with CAD models of the objects and the five-fingered hand. The results of this analysis are added to the object database using a description suited to the requirements of the grasp execution modules. A stereo camera system is used for a real-time object localization using a combination of appearance-based and model-based methods. The different components are integrated in a controller architecture to achieve manipulation task goals for the humanoid robot.

Prediction of moving object location based on frequent trajectories

Abstract: Recent advances in wireless sensors and position technology provide us with unprecedent amount of moving object data. The volume of geospatial data gathered from moving objects defies human ability to analyze the stream of input data. Therefore, new methods for mining and digesting of moving object data are urgently needed. One of the popular services available for moving objects is the prediction of the unknown location of an object. In this paper we present a new method for predicting the location of a moving object. Our method uses the past trajectory of the object and combines it with movement rules discovered in the moving objects database. Our original contribution includes the formulation of the location prediction model, the design of an efficient algorithm for mining movement rules, the proposition of four strategies for movement rule matching with respect to a given object trajectory, and the experimental evaluation of the proposed model.

Interactivity Via Mobile Image Recognition

Abstract: Systems and methods of interacting with a virtual space, in which a mobile device is used to electronically capture image data of a real-world object, the image data is used to identify information related to the real-world object, and the information is used to interact with software to control at least one of: (a) an aspect of an electronic game; and (b) a second device local to the mobile device. Contemplated systems and methods can be used to gaming, in which the image data can be used to identify a name of the real-world object, to classify the real-world object, identify the real-world object as a player in the game, to identify the real-world object as a goal object or as having some other value in the game, to use the image data to identify the real-world object as a goal object in the game.

Health-care related database middleware

Abstract: An exemplary embodiment providing for one or more improvements includes a database translation architecture that has an object model for defining a variety of health-related classes and a plurality of data bridge / data set pairs wherein each data bridge is coupled to the object model. A plurality of external components are coupled to all but one of the data bridge / data set pairs of the plurality of data bridge / data set pairs wherein the plurality of external components are operative to send and receive data in formats unique to each external component such that each format is translated to and from the object model by each corresponding data bridge / data set pair. Also included is a database coupled to a remaining data bridge / data set pair not coupled to an external component wherein the database is responsive to data queries from the object model as translated by the remaining data bridge / data pair and the database and operative to deliver requested data back to the object model through the remaining data bridge / data set pair which is in turn sent to an external component that originally initiated the data query.

High Accuracy Optical Flow Serves 3-D Pose Tracking : Exploiting Contour and Flow Based Constraints

Abstract: Tracking the 3-D pose of an object needs correspondences between 2-D features in the image and their 3-D counterparts in the object model. A large variety of such features has been suggested in the literature. All of them have drawbacks in one situation or the other since their extraction in the image and/or the matching is prone to errors. In this paper, we propose to use two complementary types of features for pose tracking, such that one type makes up for the shortcomings of the other. Aside from the object contour, which is matched to a free-form object surface, we suggest to employ the optic flow in order to compute additional point correspondences. Optic flow estimation is a mature research field with sophisticated algorithms available. Using here a high quality method ensures a reliable matching. In our experiments we demonstrate the performance of our method and in particular the improvements due to the optic flow.

Persistent authenticating mechanism to map real world object presence into virtual world object awareness

Abstract: A persistent authenticating mechanism to map real world object presence into virtual world object awareness are provided. The illustrative embodiments provide a mechanism by which the presence of a real world object is detected and, while the real world object's presence continues to be detected, it is made available for use in a virtual environment. The detection of the real world object provides an identifier of the object which is correlated with information regarding how to represent the object in the virtual environment, how the object may be utilized in relation to other objects in the virtual environment such that the real world object is modeled in the virtual environment, and the like. The detection of multiple real world objects may be performed and identification of each of the multiple objects may be used to determine how these objects may be utilized together in the virtual environment.

Object Detection and Recognition System

Abstract: During a training phase we learn parts of images which assist in the object detection and recognition task. A part is a densely represented area of an image of an object to which we assign a unique label. Parts contiguously cover an image of an object to give a part label map for that object. The parts do not necessarily correspond to semantic object parts. During the training phase a classifier is learnt which can be used to estimate belief distributions over parts for each image element of a test image. A conditional random field is used to force a global part labeling which is substantially layout-consistent and a part label map is inferred from this. By recognizing parts we enable object detection and recognition even for partially occluded objects, for multiple-objects of different classes in the same scene, for unstructured and structured objects and allowing for object deformation.

Generating a format translator

Abstract: Generating code is disclosed. A specification of one or more translation patterns is received. The one or more translation patterns are used to generate at least a portion of code associated with a translator. Using the one or more translation patterns to generate at least a portion of code associated with the translator results in the translator being configured to create a target object model. Creating the target object model includes populating one or more elements of the target object model in a processing order at least in part associated with an order of elements in the one or more translation patterns.

Protocol modelling: A modelling approach that supports reusable behavioural abstractions

Abstract: We describe a behavioural modelling approach based on the concept of a “Protocol Machine”, a machine whose behaviour is governed by rules that determine whether it accepts or refuses events that are presented to it. We show how these machines can be composed in the manner of mixins to model object behaviour and show how the approach provides a basis for defining reusable fine-grained behavioural abstractions. We suggest that this approach provides better encapsulation of object behaviour than traditional object modelling techniques when modelling transactional business systems. We relate the approach to work going on in model driven approaches, specifically the Model Driven Architecture initiative sponsored by the Object Management Group.

3-D Object Map Building Using Dense Object Models with SIFT-based Recognition Features

Abstract: This paper presents a method of object map building using object models created from image sequences captured by a single camera. Object map is a highly structured map, which is built by placing 3-D object models on the floor plane according to object recognition results. To increase the efficiency of object map building, we propose a framework to integrate dense shape and recognition features into an object model. Experimental results show that an object map of a room was built successfully using the proposed object models.

Latent Mixture Vocabularies for Object Categorization

Abstract: The visual vocabularyis an intermediate level representation which has been proven to be very powerful for addressing object categorization problems It is generally built by vector quantizing a set of local image descriptors, independently of the object model used for categorizing images We propose here to embed the visual vocabulary creation within the object model construction, allowing to make it more suited for object class discrimination We experimentally show that the proposed model outperforms approaches not learning such an adapted visual vocabulary

Unsupervised Learning of a Probabilistic Grammar for Object Detection and Parsing

Abstract: We describe an unsupervised method for learning a probabilistic grammar of an object from a set of training examples. Our approach is invariant to the scale and rotation of the objects. We illustrate our approach using thirteen objects from the Caltech 101 database. In addition, we learn the model of a hybrid object class where we do not know the specific object or its position, scale or pose. This is illustrated by learning a hybrid class consisting of faces, motorbikes, and airplanes. The individual objects can be recovered as different aspects of the grammar for the object class. In all cases, we validate our results by learning the probability grammars from training datasets and evaluating them on the test datasets. We compare our method to alternative approaches. The advantages of our approach is the speed of inference (under one second), the parsing of the object, and increased accuracy of performance. Moreover, our approach is very general and can be applied to a large range of objects and structures.

Ontologies and Object models in Object Oriented Software Engineering

Abstract: This paper is to clarify ontologies in knowledge base compare with object models in object oriented software engineering. Ontology itself has the concept which is the foundation of knowledge base; on the other hand The object model is the center of object oriented software engineering. Because ontologies are closely related to modern object-oriented software design, it is natural to adapt existing object-oriented software development methodologies for the task of ontology development. Selected approaches originate from research in artificial intelligence; knowledge representation and object modeling are presented in this paper. Some issues mentioned in this paper are related with their connection; some are addressed directly into the similarities or differences point of view of both. This paper also presents the available tools, methods, procedures which show the corporation with object modeling and ontologies.

Hybrid data object model

Abstract: Computer implemented method, system and computer usable program code for processing a data object, for example, for searching for, creating or updating a data object. A computer implemented method for processing a data object includes receiving a request for the data object. A static portion and a dynamic portion for the data object are determined, and an instruction for the static portion and an instruction for the dynamic portion are processed separately. To search for a data object, a result from processing an instruction for the static portion and a result from processing the instruction for the dynamic portion are merged to form a hybrid data object. To create or update a data object, a result from processing an instruction for the static portion and a result from processing the instruction for the dynamic portion is saved in a database.

Persistent authenticating system and method to map real world object presence into virtual world object awareness

Abstract: A persistent authenticating system and method to map real world object presence into virtual world object awareness are provided. The illustrative embodiments provide a mechanism by which the presence of a real world object is detected and, while the real world object's presence is continued to be detected, it is made available for use in a virtual environment. The detection of the real world object provides an identifier of the object which is correlated with information regarding how to represent the object in the virtual environment, how the object may be utilized in relation to other objects in the virtual environment such that the real world object is modeled in the virtual environment, and the like. The detection of multiple real world objects may be performed and identification of each of the multiple objects may be used to determine how these objects may be utilized together in the virtual environment.

Revealing the X/O impedance mismatch: changing lead into gold

Abstract: We take the term X/O impedance mismatch to describe the difficulty of the OO paradigm to accommodate XML processing by means of recasting it to typed OO programming. In particular, given XML types (say, XML schemas), it is notoriously difficult to map them automatically to object types (say, object models) that (i) reasonably compare to native object types typically devised by OO developers; (ii) fully preserve the intent of the original XML types; (iii) fully support round-tripping of arbitrary, valid XML data; and (iv) provide a general and convenient programming model for XML data hosted by objects. We reveal the X/O impedance mismatch in particular detail. That is, we survey the relevant differences between XML and objects in terms of their data models and their type systems. In this process, we systematically record and assess X-to-O mapping options. Our illustrations employ XSD (1.0) as the XML-schema language of choice and C# (1.0-3.0) as the bound of OO language expressiveness.

Multi Robot Object Tracking and Self Localization Using Visual Percept Relations

Abstract: In this paper we present a novel approach to estimating the position of objects tracked by a team of mobile robots and to use these objects for a better self localization. Modeling of moving objects is commonly done in a robo-centric coordinate frame because this information is sufficient for most low level robot control and it is independent of the quality of the current robot localization. For multiple robots to cooperate and share information, though, they need to agree on a global, allocentric frame of reference. When transforming the egocentric object model into a global one, it inherits the localization error of the robot in addition to the error associated with the egocentric model. We propose using the relation of objects detected in camera images to other objects in the same camera image as a basis for estimating the position of the object in a global coordinate system. The spatial relation of objects with respect to stationary objects (e.g., landmarks) offers several advantages: a) Errors in feature detection are correlated and not assumed independent. Furthermore, the error of relative positions of objects within a single camera frame is comparably small, b) The information is independent of robot localization and odometry. c) As a consequence of the above, it provides a highly efficient method for communicating information about a tracked object and communication can be asynchronous, d) As the modeled object is independent from robo-centric coordinates, its position can be used for self localization of the observing robot. We present experimental evidence that shows how two robots are able to infer the position of an object within a global frame of reference, even though they are not localized themselves and then use this object information for self- localization

A grasp planning for picking up an unknown object for a mobile manipulator

Abstract: This paper describes a grasp planning for a mobile manipulator which works in real environment. Mobile robot studies up to now that manipulate an object in real world practically use ID tag on an object or an object model which is given to the robot in advance. The authors aim to develop a mobile manipulator that can acquire an object model through video images and can manipulate the object. In this approach, the robot can manipulate an unknown object autonomously. A grasp planning proposed in this paper can find a stable grasp pose from the automatically generated model which contains redundant data and the shape error of the object. Experiments show the effectiveness of the proposed method

Image generation device, image generation method, and image generation program

Abstract: The image generation device includes distance calculation means for calculating a distance between a space model and an imaging device arrangement object model which is a model such as a vehicle having a camera mounted, according to viewpoint conversion image data generated by viewpoint conversion means, captured image data representing captured image, a space model, or mapped space data. When displaying an image viewed from an arbitrary virtual viewpoint in the 3D space, the image display format is changed according to the distance calculated by the distance calculation means. When displaying a monitoring object such as a vicinity of a vehicle, a shop, a house or a city as an image viewed from an arbitrary virtual viewpoint in the 3D space, it is possible to display the monitoring object in such a manner that the relationship between the vehicle and the image of the monitoring object can be understood intuitionally.

Learning Object Shape: From Drawings to Images

Abstract: We consider the important challenge of recognizing a variety of deformable object classes in images. Of fundamental importance and particular difficulty in this setting is the problem of "outlining" an object, rather than simply deciding on its presence or absence. A major obstacle in learning a model that will allow us to address this task is the need for hand-segmented training images. In this paper we present a novel landmark-based, piecewise-linear model of the shape of an object class. We then formulate a learning approach that allows us to learn this model with minimal user supervision. We circumvent the need for hand-segmentation by transferring the shape "essence" of an object from drawings to complex images. We show that our method is able to automatically and effectively learn and localize a variety of object classes.

Virtual multidimensional datasets for enterprise software systems

Abstract: Techniques are described for specifying virtual datasets within an enterprise software system. A computer-implemented system, for example, includes an enterprise planning system and a computing device coupled to the enterprise planning system via a network connection. The computing device includes an object store that stores a dataset, an application programming interface (API) that defines an operation for specifying the virtual dataset from the dataset, and an object model that stores a virtual dataset to the object store in response to receiving the operation defined by the API. The computing device further includes a plurality of applications that utilize the virtual dataset for a further operation defined by the API without resolving the virtual dataset. Because virtual dataset may be utilized without first resolving them, the virtual datasets may require less storage space within a memory, may automatically remain synchronous with the underlying dataset, and may quickly layer to more readily perform complicated operations.

Subordinate class recognition using relational object models

Abstract: We address the problem of sub-ordinate class recognition, like the distinction between different types of motorcycles. Our approach is motivated by observations from cognitive psychology, which identify parts as the defining component of basic level categories (like motorcycles), while sub-ordinate categories are more often defined by part properties (like 'jagged wheels'). Accordingly, we suggest a two-stage algorithm: First, a relational part based object model is learnt using unsegmented object images from the inclusive class (e.g., motorcycles in general). The model is then used to build a class-specific vector representation for images, where each entry corresponds to a model's part. In the second stage we train a standard discriminative classifier to classify subclass instances (e.g., cross motorcycles) based on the class-specific vector representation. We describe extensive experimental results with several subclasses. The proposed algorithm typically gives better results than a competing one-step algorithm, or a two stage algorithm where classification is based on a model of the sub-ordinate class.

Comparing the performance of object databases and ORM tools

Abstract: The currently popular distributed, n-tiered, object-oriented application architecture provokes many design debates. Designs of such applications are often divided into logical 'tiers' -- usually user interface, business logic and domain object, or data, tiers, each with their own design issues. In particular, the latter contains data that needs to be stored and retrieved from permanent storage. Decisions need to be made as to the most appropriate way of doing this -- the choices are usually whether to use an object database, to communicate directly with a relational database, or to use object-relational mapping (ORM) tools to allow objects to be translated to and from relational form.Most often, depending on the perceived profile of the application, architects make these decisions using rules of thumb derived from particular experience or the design patterns literature. Examples include: object-oriented databases ease programming, relational databases ease report generation and data mining; object-oriented databases are good for navigation around an object model, relational databases are good for sequential processing and complex queries; if you are writing an application from scratch, use an object database, if you need to integrate to various sources of legacy data, use an ORM tool. Although helpful, these rules are often highly context-dependent and are often misapplied.Research into the nature and magnitude of 'design forces' in this area has resulted in a series of benchmarks, intended to allow architects to more clearly understand the implications of design decisions concerning object persistence. In this paper, the performance of selected open source object persistence tools is investigated, to attempt to clarify the myths surrounding the performance of the different options. In particular, we compare Hibernate, representative of the ORM stable, and db4o, representative of object-oriented databases. The OO7 benchmark is used to compare the speed of execution of a suite of typical persistence-related operations in both candidates. We then propose some preliminary explanations of the sometimes surprising results.