Showing papers on "Object (computer science) published in 2004"

Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories

Abstract: Current computational approaches to learning visual object categories require thousands of training images, are slow, cannot learn in an incremental manner and cannot incorporate prior information into the learning process. In addition, no algorithm presented in the literature has been tested on more than a handful of object categories. We present an method for learning object categories from just a few training images. It is quick and it uses prior information in a principled way. We test it on a dataset composed of images of objects belonging to 101 widely varied categories. Our proposed method is based on making use of prior information, assembled from (unrelated) object categories which were previously learnt. A generative probabilistic model is used, which represents the shape and appearance of a constellation of features belonging to the object. The parameters of the model are learnt incrementally in a Bayesian manner. Our incremental algorithm is compared experimentally to an earlier batch Bayesian algorithm, as well as to one based on maximum-likelihood. The incremental and batch versions have comparable classification performance on small training sets, but incremental learning is significantly faster, making real-time learning feasible. Both Bayesian methods outperform maximum likelihood on small training sets.

Combined Object Categorization and Segmentation With an Implicit Shape Model

Abstract: We present a method for object categorization in real-world scenes. Following a common consensus in the field, we do not assume that a figure- ground segmentation is available prior to recognition. However, in contrast to most standard approaches for object class recognition, our approach automati- cally segments the object as a result of the categorization. This combination of recognition and segmentation into one process is made pos- sible by our use of an Implicit Shape Model, which integrates both into a common probabilistic framework. In addition to the recognition and segmentation result, it also generates a per-pixel confidence measure specifying the area that supports a hypothesis and how much it can be trusted. We use this confidence to derive a nat- ural extension of the approach to handle multiple objects in a scene and resolve ambiguities between overlapping hypotheses with a novel MDL-based criterion. In addition, we present an extensive evaluation of our method on a standard dataset for car detection and compare its performance to existing methods from the literature. Our results show that the proposed method significantly outper- forms previously published methods while needing one order of magnitude less training examples. Finally, we present results for articulated objects, which show that the proposed method can categorize and segment unfamiliar objects in differ- ent articulations and with widely varying texture patterns, even under significant partial occlusion.

Learning to detect objects in images via a sparse, part-based representation

Abstract: We study the problem of detecting objects in still, gray-scale images. Our primary focus is the development of a learning-based approach to the problem that makes use of a sparse, part-based representation. A vocabulary of distinctive object parts is automatically constructed from a set of sample images of the object class of interest; images are then represented using parts from this vocabulary, together with spatial relations observed among the parts. Based on this representation, a learning algorithm is used to automatically learn to detect instances of the object class in new images. The approach can be applied to any object with distinguishable parts in a relatively fixed spatial configuration; it is evaluated here on difficult sets of real-world images containing side views of cars, and is seen to successfully detect objects in varying conditions amidst background clutter and mild occlusion. In evaluating object detection approaches, several important methodological issues arise that have not been satisfactorily addressed in the previous work. A secondary focus of this paper is to highlight these issues, and to develop rigorous evaluation standards for the object detection problem. A critical evaluation of our approach under the proposed standards is presented.

Media player system

Abstract: An object of the present invention is to provide a media player system. Certain aspects of the A media player system relates docking station (178) that allows a media player (174) to communicate with other media devices. Another aspect of the media player system relates to a wireless media player system that includes one or more media devices that can receive (404A) wirelessly connecting the hand held media player and the information that can send information over a wireless connection (406). Another aspect of the media player system pertains to a method of connecting a hand held media player to another device wirelessly. The method includes selecting a media item on the hand held media player, selecting one or more remote recipients on the hand held media player, locally the media item to the hand held media player, said wirelessly It comprises transmitting the selected remote recipients. Another aspect of the media player system relates handheld music player that includes a transmitter for transmitting information over a wireless connection. Wherein the transmitter is configured to at least transmit a continuous music feed a receiver capable of receiving information from the transmitter in the wireless connection to one or more personal tuning devices including, respectively.

Revisiting Snodgrass and Vanderwart's object pictorial set : the role of surface detail in basic-level object recognition

Abstract: Theories of object recognition differ to the extent that they consider object representations as being mediated only by the shape of the object, or shape and surface details, if surface details are part of the representation. In particular, it has been suggested that color information may be helpful at recognizing objects only in very special cases, but not during basic-level object recognition in good viewing conditions. In this study, we collected normative data (naming agreement, familiarity, complexity, and imagery judgments) for Snodgrass and Vanderwart's object database of 260 black-and-white line drawings, and then compared the data to exactly the same shapes but with added gray-level texture and surface details (set 2), and color (set 3). Naming latencies were also recorded. Whereas the addition of texture and shading without color only slightly improved naming agreement scores for the objects, the addition of color information unambiguously improved naming accuracy and speeded correct response times. As shown in previous studies, the advantage provided by color was larger for objects with a diagnostic color, and structurally similar shapes, such as fruits and vegetables, but was also observed for man-made objects with and without a single diagnostic color. These observations show that basic-level 'everyday' object recognition in normal conditions is facilitated by the presence of color information, and support a 'shape + surface' model of object recognition, for which color is an integral part of the object representation. In addition, the new stimuli (sets 2 and 3) and the corresponding normative data provide valuable materials for a wide range of experimental and clinical studies of object recognition.

The template update problem

Abstract: Template tracking dates back to the 1981 Lucas-Kanade algorithm. One question that has received very little attention, however, is how to update the template so that it remains a good model of the tracked object. We propose a template update algorithm that avoids the "drifting" inherent in the naive algorithm.

Contour-based object tracking with occlusion handling in video acquired using mobile cameras

Abstract: We propose a tracking method which tracks the complete object regions, adapts to changing visual features, and handles occlusions. Tracking is achieved by evolving the contour from frame to frame by minimizing some energy functional evaluated in the contour vicinity defined by a band. Our approach has two major components related to the visual features and the object shape. Visual features (color, texture) are modeled by semiparametric models and are fused using independent opinion polling. Shape priors consist of shape level sets and are used to recover the missing object regions during occlusion. We demonstrate the performance of our method in real sequences with and without object occlusions.

Conditional Random Fields for Object Recognition

Abstract: We present a discriminative part-based approach for the recognition of object classes from unsegmented cluttered scenes. Objects are modeled as flexible constellations of parts conditioned on local observations found by an interest operator. For each object class the probability of a given assignment of parts to local features is modeled by a Conditional Random Field (CRF). We propose an extension of the CRF framework that incorporates hidden variables and combines class conditional CRFs into a unified framework for part-based object recognition. The parameters of the CRF are estimated in a maximum likelihood framework and recognition proceeds by finding the most likely class under our model. The main advantage of the proposed CRF framework is that it allows us to relax the assumption of conditional independence of the observed data (i.e. local features) often used in generative approaches, an assumption that might be too restrictive for a considerable number of object classes.

Photo-based mobile deixis system and related techniques

Abstract: A mobile deixis device includes a camera to capture an image and a wireless handheld device, coupled to the camera and to a wireless network, to communicate the image with existing databases to find similar images. The mobile deixis device further includes a processor, coupled to the device, to process found database records related to similar images and a display to view found database records that include web pages including images. With such an arrangement, users can specify a location of interest by simply pointing a camera-equipped cellular phone at the object of interest and by searching an image database or relevant web resources, users can quickly identify good matches from several close ones to find an object of interest.

Methods and apparatus for enabling transaction relating to digital assets

Abstract: Methods and apparatus are described which enable transactions in electronic networks relating to digital assets, e.g., digital goods or services, through the use of title objects. A title object may have a number of elements and attributes which identify one or more digital assets and define access rights to the corresponding digital asset(s).

The Object Primer: Agile Model-Driven Development with UML 2.0

Abstract: Scott Ambler, award-winning author of Building Object Applications that Work, Process Patterns, and More Process Patterns, has revised his acclaimed first book, The Object Primer. Long prized by both students and professionals as the best introduction to object-oriented technology, this book is now completely up-to-date, with all modeling notation rewritten in the just-released UML 2.0. All chapters have been revised to take advantage of Agile Modeling (AM), which is presented in the new chapter 2 along with other important new modeling techniques. Review questions at the end of each chapter allow readers to test their newly acquired knowledge. In addition, Ambler takes time to reflect on the lessons learned over the past few years by discussing the proven benefits and drawbacks of the technology. This is the perfect book for any software development professional or student seeking an introduction to the concepts and terminology of object technology. Previous Edition Pb (2001): 0-521-78519-7 Scott W. Ambler is a senior object consultant with Ronin International, Inc. and a popular speaker at conferences worldwide. He has worked with OO technology since 1990 as a business architect, system analyst, system designer, mentor, Smalltalk/C++/Java developer, and OO software process manager. He is a member of the IEEE Computer Society, the ACM, and Mensa.

Mapping tool graphical user interface

Abstract: A graphical user interface and method for creating a mapping between a source object and a destination or target object are provided. The user interface includes a source screen region which displays a graphical representation of a source object, a target screen region which displays a graphical representation of a target object, and a mapping screen region which allows a user to create a mapping between the graphical representation of the source object and the graphical representation of the target object using graphical mapping indicia. The methodology includes displaying a graphical representation of a source object in a source screen region, displaying a graphical representation of a target object in a target screen region, creating a mapping between the graphical representation of the source object and the graphical representation of the target object in a mapping screen region using graphical mapping indicia, and displaying the mapping in the mapping screen region. The source and target objects may be schemas, spreadsheets, documents, databases, or other information sources, and the graphical mapping indicia may include link indicia and/or function objects linking nodes in the target object with nodes in the source object. The mapping may be compiled into code used by a runtime engine to translate source documents into target documents.

FreeLing: An Open-Source Suite of Language Analyzers

Abstract: Basic language processing such as tokenizing, morphological analyzers, lemmatizing, PoS tagging, chunking, etc. is a need for most NL applications such as Machine Translation, Summarization, Dialogue systems, etc. A large part of the effort required to develop such applications is devoted to the adaptation of existing software resources to the platform, programming language, format or API of the nal system. In LREC’02, we presented the object architecture that we are currently using (Carreras and Padr· o, 2002), which enables the quick and easy integration of basic language analyzers in any NLP application. Now we present a suite of analysis tools based on that architecture, which is distributed under Lesser General Public License (LGPL) (Free Software Foundation, 1999). The rst release of the suite will include morphological analyzer and Part-of-Speech tagger for English, Spanish, and Catalan.

Interaction between objects and a virtual environment display

Abstract: An interactive table has a display surface on which a physical object is disposed. A camera within the interactive table responds to infrared (IR) light reflected from the physical object enabling a location of the physical object on the display surface to be determined, so that the physical object appear part of a virtual environment displayed thereon. The physical object can be passive or active. An active object performs an active function, e.g., it can be self-propelled to move about on the display surface, or emit light or sound, or vibrate. The active object can be controlled by a user or the processor. The interactive table can project an image through a physical object on the display surface so the image appears part of the object. A virtual entity is preferably displayed at a position (and a size) to avoid visually interference with any physical object on the display surface.

Prediction and indexing of moving objects with unknown motion patterns

Abstract: Existing methods for peediction spatio-temporal databases assume that objects move according to linear functions. This severely limits their applicability, since in practice movement is more complex, and individual objects may follow drastically diffferent motion patterns. In order to overcome these problems, we first introduce a general framework for monitoring and indexing moving objects, where (i) each boject computes individually the function that accurately captures its movement and (ii) a server indexes the object locations at a coarse level and processes queries using a filter-refinement mechanism. Our second contribution is a novel recursive motion function that supports a broad class of non-linear motion patterns. The function does not presume any a-priori movement but can postulate the particular motion of each object by examining its locations at recent timestamps. Finally. we propse an efficient indexing scheme that faciliates the processing of predicitive queries without false misses.

Policy-based management of a redundant array of independent nodes

Abstract: An archive cluster application runs in a distributed manner across a redundant array of independent nodes. Each node preferably runs a complete archive cluster application instance. A given nodes provides a data repository, which stores up to a large amount (e.g., a terabyte) of data, while also acting as a portal that enables access to archive files. Each symmetric node has a set of software processes, e.g., a request manager, a storage manager, a metadata manager, and a policy manager. The request manager manages requests to the node for data (i.e., file data), the storage manager manages data read/write functions from a disk associated with the node, and the metadata manager facilitates metadata transactions and recovery across the distributed database. The policy manager implements one or more policies, which are operations that determine the behavior of an “archive object” within the cluster. The archive cluster application provides object-based storage. Preferably, the application permanently associates metadata and policies with the raw archived data, which together comprise an archive object. Object policies govern the object's behavior in the archive. As a result, the archive manages itself independently of client applications, acting automatically to ensure that all object policies are valid.

Apparatus and method performing audio-video sensor fusion for object localization, tracking, and separation

Abstract: An apparatus for tracking and identifying objects includes an audio likelihood module which determines corresponding audio likelihoods for each of a plurality of sounds received from corresponding different directions, each audio likelihood indicating a likelihood a sound is an object to be tracked; a video likelihood module which receives a video and determines video likelihoods for each of a plurality of images disposed in corresponding different directions in the video, each video likelihood indicating a likelihood that the image is an object to be tracked; and an identification and tracking module which determines correspondences between the audio likelihoods and the video likelihoods, if a correspondence is determined to exist between one of the audio likelihoods and one of the video likelihoods, identifies and tracks a corresponding one of the objects using each determined pair of audio and video likelihoods.

User interface for displaying selectable software functionality controls that are contextually relevant to a selected object

Abstract: An improved user interface is provided for displaying selectable functionality controls that identifies the context of the object to which the user interface is relevant, which contains rich functionality controls for applying contextually relevant functionality to a selected object, and which may be efficiently switched to a different context for applying a different set of functionalities to a different or neighboring editable object. A context menu of functionalities is displayed adjacent to a selected object where the menu of functionalities includes functionalities associated with editing the selected object. The context menu includes an identification of the object context and a control for selectively changing the context and associated functionalities of the menu to a different object context for displaying a different set of functionalities associated with the different context.

Semantic object synchronous understanding implemented with speech application language tags

Abstract: A speech understanding system includes a language model comprising a combination of an N-gram language model and a context-free grammar language model. The language model stores information related to words and semantic information to be recognized. A module is adapted to receive input from a user and capture the input for processing. The module is further adapted to receive SALT application program interfaces pertaining to recognition of the input. The module is configured to process the SALT application program interfaces and the input to ascertain semantic information pertaining to a first portion of the input and output a semantic object comprising text and semantic information for the first portion by accessing the language model, wherein performing recognition and outputting the semantic object are performed while capturing continues for subsequent portions of the input.

Computer-implemented building design and modeling and project cost estimation and scheduling system

Abstract: A computer-implemented building design and modeling system and method are provided. In one embodiment, the system comprises a spatial database; means for defining a plurality of parametric objects, each of the parametric objects representing a construction component of at least a portion of a building being modeled and including an interface through which the parametric object communicates information with other ones of the parametric objects; a cost database containing, for each of parametric objects, cost information associated with the parametric object; means for assembling a model of the building utilizing the parametric objects, wherein each of the parametric objects is created in the spatial database; and means for generating in real-time a cost-estimate for the building model based on the cost information associated with the parametric objects as the parametric objects are created in the spatial database.

System and method for vehicle detection and tracking

Abstract: A system and method for detecting and tracking an object is disclosed. A camera captures a video sequence comprised of a plurality of image frames. A processor receives the video sequence and analyzes each image frame to determine if an object is detected. The processor applies one or more classifiers to an object in each image frame and computes a confidence score based on the application of the one or more classifiers to the object. A database stores the one or more classifiers and vehicle training samples. A display displays the video sequence.

Sharing media objects in a network

Abstract: A method, computer readable medium, user component, and system for sharing media object in a network environment are disclosed. A network manager may determine a similarity metric between users of the environment, between media objects, and/or between a user and media objects. Based upon the similarity metric, the network manager may share media objects with another user if the similarity metric exceeds a predetermined value or is more similar than other retrieved media objects. A user component may also provide a network map manager to display a network map, and may provide a tailored view manager to display a web log associated with at least one of the user icons displayed in the network map.

Multimedia Security: Steganography and Digital Watermarking Techniques for Protection of Intellectual Property

Abstract: This work explores the myriad of issues regarding multimedia security. It covers various issues, including perceptual fidelity analysis, image, audio, and 3D mesh object watermarking, medical watermarking, and error detection (authentication) and concealment.

Importance-Driven Volume Rendering

Abstract: This paper introduces importance-driven volume rendering as a novel technique for automatic focus and context display of volumetric data. Our technique is a generalization of cut-away views, which - depending on the viewpoint - remove or suppress less important parts of a scene to reveal more important underlying information. We automatize and apply this idea to volumetric data. Each part of the volumetric data is assigned an object importance which encodes visibility priority. This property determines which structures should be readily discernible and which structures are less important. In those image regions, where an object occludes more important structures it is displayed more sparsely than in those areas where no occlusion occurs. Thus the objects of interest are clearly visible. For each object several representations, i.e., levels of sparseness, are specified. The display of an individual object may incorporate different levels of sparseness. The goal is to emphasize important structures and to maximize the information content in the final image. This paper also discusses several possible schemes for level of sparseness specification and different ways how object importance can be composited to determine the final appearance of a particular object.

Systems and methods of viewing, modifying, and interacting with “path-enhanced” multimedia

Abstract: “Path-enhanced” multimedia (PEM) data may be viewed, modified, or interacted with according to user selected views which determine the meaner in which at least a portion of the PEM data is displayed. The PEM data is stored in data structure as a scrapbook object including the first data object types corresponding to the PEM data and second object types corresponding to the different view types. The scrapbook object data structure lends itself to displaying portion of the PEM data according to the selected views that correspond to the particular time and place or to a particular time ordered sequence of locations (i.e., a particular path segment) and/or can be enhanced with other multimedia content related to the time and place or to the path segment, thereby providing a more interesting and effective display or the “path-enhanced” recorded events. For example, the time and location of a particular point on the path may be used to locate and append other recorded sounds and images associated with that time and/or that location, to thereby provide an enhanced presentation of a trip or other path-oriented experience. Moreover, the data defining any such associated path may also be edited to thereby define a new or modified path.

Methods and apparatus for enabling transactions in networks

Abstract: Methods and apparatus are described which enable transactions in electronic networks relating to digital assets, e.g., digital goods or services, through the use of title objects. A title object may have a number of elements and attributes which identify one or more digital assets and define access rights to the corresponding digital asset(s).

Some puzzling findings in multiple object tracking: I. Tracking without keeping track of object identities

Abstract: The task of tracking a small number (about four or five) visual targets within a larger set of identical items, each of which moves randomly and independently, has been used extensively to study object‐based attention. Analysis of this multiple object tracking (MOT) task shows that it logically entails solving the correspondence problem for each target over time, and thus that the individuality of each of the targets must be tracked. This suggests that when successfully tracking objects, observers must also keep track of them as unique individuals. Yet in the present studies we show that observers are poor at recalling the identity of successfully tracked objects (as specified by a unique identifier associated with each target, such as a number or starting location). Studies also show that the identity of targets tends to be lost when they come close together and that this tendency is greater between pairs of targets than between targets and nontargets. The significance of this finding in relation to the ...

Contact query data system and method

Abstract: A processor-implemented method of operating a mobile communication device operable to execute one or more communication applications includes issuing a query for contact data over a communication network, creating a contact resolution object, receiving contact data responsive to the query over the communication network, the contact data comprising communication contact data for the one or more communication applications, associating the contact data received with the contact resolution object, and resolving the contact resolution object to select communication contact data.