Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Computer vision (8)
- Machine learning (7)
- Action recognition (6)
- Tracking (6)
- Algorithms (5)
-
- Evolutionary computation (4)
- Artificial intelligence (3)
- Augmented reality (3)
- Authentication (3)
- Global illumination (3)
- Intrusion detection (3)
- Pattern recognition (3)
- Recognition (3)
- Uav (3)
- User study (3)
- Wavelets (3)
- 3D reconstruction (2)
- Bioinformatics (2)
- Communities (2)
- Computer Science (2)
- Computer graphics (2)
- Crowdsourcing (2)
- Data clustering (2)
- Data mining (2)
- GPU (2)
- Genetic algorithms (2)
- Gestures (2)
- High performance computing (2)
- Human action recognition (2)
- Image-based rendering (2)
- Publication Year
Articles 91 - 120 of 178
Full-Text Articles in Engineering
Learning Techniques For Information Retrieval And Mining In High-Dimensional Databases, Hao Cheng
Learning Techniques For Information Retrieval And Mining In High-Dimensional Databases, Hao Cheng
Electronic Theses and Dissertations
The main focus of my research is to design effective learning techniques for information retrieval and mining in high-dimensional databases. There are two main aspects in the retrieval and mining research: accuracy and efficiency. The accuracy problem is how to return results which can better match the ground truth, and the efficiency problem is how to evaluate users' requests and execute learning algorithms as fast as possible. However, these problems are non-trivial because of the complexity of the high-level semantic concepts, the heterogeneous natures of the feature space, the high dimensionality of data representations and the size of the databases. …
Efficient Techniques For Relevance Feedback Processing In Content-Based Image Retrieval, Danzhou Liu
Efficient Techniques For Relevance Feedback Processing In Content-Based Image Retrieval, Danzhou Liu
Electronic Theses and Dissertations
In content-based image retrieval (CBIR) systems, there are two general types of search: target search and category search. Unlike queries in traditional database systems, users in most cases cannot specify an ideal query to retrieve the desired results for either target search or category search in multimedia database systems, and have to rely on iterative feedback to refine their query. Efficient evaluation of such iterative queries can be a challenge, especially when the multimedia database contains a large number of entries, and the search needs many iterations, and when the underlying distance measure is computationally expensive. The overall processing costs, …
Geometric Invariance In The Analysis Of Human Motion In Video Data, Yuping Shen
Geometric Invariance In The Analysis Of Human Motion In Video Data, Yuping Shen
Electronic Theses and Dissertations
Human motion analysis is one of the major problems in computer vision research. It deals with the study of the motion of human body in video data from different aspects, ranging from the tracking of body parts and reconstruction of 3D human body configuration, to higher level of interpretation of human action and activities in image sequences. When human motion is observed through video camera, it is perspectively distorted and may appear totally different from different viewpoints. Therefore it is highly challenging to establish correct relationships between human motions across video sequences with different camera settings. In this work, we …
Scheduling And Resource Management For Complex Systems: From Large-Scale Distributed Systems To Very Large Sensor Networks, Chen Yu
Electronic Theses and Dissertations
In this dissertation, we focus on multiple levels of optimized resource management techniques. We first consider a classic resource management problem, namely the scheduling of data-intensive applications. We define the Divisible Load Scheduling (DLS) problem, outline the system model based on the assumption that data staging and all communication with the sites can be done in parallel, and introduce a set of optimal divisible load scheduling algorithms and the related fault-tolerant coordination algorithm. The DLS algorithms introduced in this dissertation exploit parallel communication, consider realistic scenarios regarding the time when heterogeneous computing systems are available, and generate optimal schedules. Performance …
Learning Semantic Features For Visual Recognition, Jingen Liu
Learning Semantic Features For Visual Recognition, Jingen Liu
Electronic Theses and Dissertations
Visual recognition (e.g., object, scene and action recognition) is an active area of research in computer vision due to its increasing number of real-world applications such as video (image) indexing and search, intelligent surveillance, human-machine interaction, robot navigation, etc. Effective modeling of the objects, scenes and actions is critical for visual recognition. Recently, bag of visual words (BoVW) representation, in which the image patches or video cuboids are quantized into visual words (i.e., mid-level features) based on their appearance similarity using clustering, has been widely and successfully explored. The advantages of this representation are: no explicit detection of objects or …
New Computational Approaches For Multiple Rna Alignment And Rna Search, Daniel Deblasio
New Computational Approaches For Multiple Rna Alignment And Rna Search, Daniel Deblasio
Electronic Theses and Dissertations
In this thesis we explore the the theory and history behind RNA alignment. Normal sequence alignments as studied by computer scientists can be completed in O(n2) time in the naive case. The process involves taking two input sequences and finding the list of edits that can transform one sequence into the other. This process is applied to biology in many forms, such as the creation of multiple alignments and the search of genomic sequences. When you take into account the RNA sequence structure the problem becomes even harder. Multiple RNA structure alignment is particularly challenging because covarying mutations make sequence …
Search And Delivery Techniques In Peer-To-Peer Networks, Tai Do
Search And Delivery Techniques In Peer-To-Peer Networks, Tai Do
Electronic Theses and Dissertations
The presence of millions of interconnected personal computing devices has given rise to a new class of decentralized networking applications, which are loosely labeled as peer-to-peer (P2P) applications. These P2P applications leverage resources such as processing cycles, storage, content, and network bandwidth available to the user devices, which are also known as peers. A number of current systems - SETI@home, Napster, BitTorrent, and Pastry - are examples of these emerging P2P systems. To fully realize the potential of the peer-to-peer technology, there is a need to define and provide a set of core competencies, serving as the basic services upon …
Attacks On Difficult Instances Of Graph Isomorphism: Sequential And Parallel Algorithms, Greg Tener
Attacks On Difficult Instances Of Graph Isomorphism: Sequential And Parallel Algorithms, Greg Tener
Electronic Theses and Dissertations
The graph isomorphism problem has received a great deal of attention on both theoretical and practical fronts. However, a polynomial algorithm for the problem has yet to be found. Even so, the best of the existing algorithms perform well in practice; so well that it is challenging to find hard instances for them. The most efficient algorithms, for determining if a pair of graphs are isomorphic, are based on the individualization-refinement paradigm, pioneered by Brendan McKay in 1981 with his algorithm nauty. Nauty and various improved descendants of nauty, such as bliss and saucy, solve the graph isomorphism problem by …
On The Application Of Locality To Network Intrusion Detection: Working-Set Analysis Of Real And Synthetic Network Server Traffic, Robert Lee
Electronic Theses and Dissertations
Keeping computer networks safe from attack requires ever-increasing vigilance. Our work on applying locality to network intrusion detection is presented in this dissertation. Network servers that allow connections from both the internal network and the Internet are vulnerable to attack from all sides. Analysis of the behavior of incoming connections for properties of locality can be used to create a normal profile for such network servers. Intrusions can then be detected due to their abnormal behavior. Data was collected from a typical network server both under normal conditions and under specific attacks. Experiments show that connections to the server do …
Concept Learning By Example Decomposition, Sameer Joshi
Concept Learning By Example Decomposition, Sameer Joshi
Electronic Theses and Dissertations
For efficient understanding and prediction in natural systems, even in artificially closed ones, we usually need to consider a number of factors that may combine in simple or complex ways. Additionally, many modern scientific disciplines face increasingly large datasets from which to extract knowledge (for example, genomics). Thus to learn all but the most trivial regularities in the natural world, we rely on different ways of simplifying the learning problem. One simplifying technique that is highly pervasive in nature is to break down a large learning problem into smaller ones; to learn the smaller, more manageable problems; and then to …
Automatic Graphics And Game Content Generation Through Evolutionary Computation, Erin Hastings
Automatic Graphics And Game Content Generation Through Evolutionary Computation, Erin Hastings
Electronic Theses and Dissertations
Simulation and game content includes the levels, models, textures, items, and other objects encountered and possessed by players during the game. In most modern video games and simulation software, the set of content shipped with the product is static and unchanging, or at best, randomized within a narrow set of parameters. However, ideally, if game content could be constantly and automatically renewed, players would remain engaged longer in the evolving stream of content. This dissertation introduces three novel technologies that together realize this ambition. (1) The first, NEAT Particles, is an evolutionary method to enable users to quickly and easily …
Realnav: Exploring Natural User Interfaces For Locomotion In Video Games, Brian Williamson
Realnav: Exploring Natural User Interfaces For Locomotion In Video Games, Brian Williamson
Electronic Theses and Dissertations
We present an exploration into realistic locomotion interfaces in video games using spatially convenient input hardware. In particular, we use Nintendo Wii Remotes to create natural mappings between user actions and their representation in a video game. Targeting American Football video games, we used the role of the quarterback as an exemplar since the game player needs to maneuver effectively in a small area, run down the field, and perform evasive gestures such as spinning, jumping, or the "juke". In our study, we developed three locomotion techniques. The first technique used a single Wii Remote, placed anywhere on the user's …
Vectorpad: A Tool For Visualizing Vector Operations, Jared Bott
Vectorpad: A Tool For Visualizing Vector Operations, Jared Bott
Electronic Theses and Dissertations
Visualization of three-dimensional vector operations can be very helpful in understanding vector mathematics. However, creating these visualizations using traditional WIMP interfaces can be a troublesome exercise. In this thesis, we present VectorPad, a pen-based application for three-dimensional vector mathematics visualization. VectorPad allows users to define vectors and perform mathematical operations upon them through the recognition of handwritten mathematics. The VectorPad user interface consists of a sketching area, where the user can write vector definitions and other mathematics, and a 3D graph for visualization. After recognition, vectors are visualized dynamically on the graph, which can be manipulated by the user. A …
Automated Regression Testing Approach To Expansion And Refinement Of Speech Recognition Grammars, Raul Dookhoo
Automated Regression Testing Approach To Expansion And Refinement Of Speech Recognition Grammars, Raul Dookhoo
Electronic Theses and Dissertations
This thesis describes an approach to automated regression testing for speech recognition grammars. A prototype Audio Regression Tester called ART has been developed using Microsoft's Speech API and C#. ART allows a user to perform any of three tasks: automatically generate a new XML-based grammar file from standardized SQL database entries, record and cross-reference audio files for use by an underlying speech recognition engine, and perform regression tests with the aid of an oracle grammar. ART takes as input a wave sound file containing speech and a newly created XML grammar file. It then simultaneously executes two tests: one with …
Semantic Video Retrieval Using High Level Context, Yusuf Aytar
Semantic Video Retrieval Using High Level Context, Yusuf Aytar
Electronic Theses and Dissertations
Video retrieval - searching and retrieving videos relevant to a user defined query - is one of the most popular topics in both real life applications and multimedia research. This thesis employs concepts from Natural Language Understanding in solving the video retrieval problem. Our main contribution is the utilization of the semantic word similarity measures for video retrieval through the trained concept detectors, and the visual co-occurrence relations between such concepts. We propose two methods for content-based retrieval of videos: (1) A method for retrieving a new concept (a concept which is not known to the system and no annotation …
Multi-View Approaches To Tracking, 3d Reconstruction And Object Class Detection, Saad Khan
Multi-View Approaches To Tracking, 3d Reconstruction And Object Class Detection, Saad Khan
Electronic Theses and Dissertations
Multi-camera systems are becoming ubiquitous and have found application in a variety of domains including surveillance, immersive visualization, sports entertainment and movie special effects amongst others. From a computer vision perspective, the challenging task is how to most efficiently fuse information from multiple views in the absence of detailed calibration information and a minimum of human intervention. This thesis presents a new approach to fuse foreground likelihood information from multiple views onto a reference view without explicit processing in 3D space, thereby circumventing the need for complete calibration. Our approach uses a homographic occupancy constraint (HOC), which states that if …
Appearance-Driven Material Design, Mark Colbert
Appearance-Driven Material Design, Mark Colbert
Electronic Theses and Dissertations
In the computer graphics production environment, artists often must tweak specific lighting and material parameters to match a mind's eye vision of the appearance of a 3D scene. However, the interaction between a material and a lighting environment is often too complex to cognitively predict without visualization. Therefore, artists operate in a design cycle, where they tweak the parameters, wait for a visualization, and repeat, seeking to obtain a desired look. We propose the use of appearance-driven material design. Here, artists directly design the appearance of reflected light for a specific view, surface point, and time. In this thesis, we …
Taming Crowded Visual Scenes, Saad Ali
Taming Crowded Visual Scenes, Saad Ali
Electronic Theses and Dissertations
Computer vision algorithms have played a pivotal role in commercial video surveillance systems for a number of years. However, a common weakness among these systems is their inability to handle crowded scenes. In this thesis, we have developed algorithms that overcome some of the challenges encountered in videos of crowded environments such as sporting events, religious festivals, parades, concerts, train stations, airports, and malls. We adopt a top-down approach by first performing a global-level analysis that locates dynamically distinct crowd regions within the video. This knowledge is then employed in the detection of abnormal behaviors and tracking of individual targets …
Alayzing The Effects Of Modularity On Search Spaces, Ozlem Garibay
Alayzing The Effects Of Modularity On Search Spaces, Ozlem Garibay
Electronic Theses and Dissertations
We are continuously challenged by ever increasing problem complexity and the need to develop algorithms that can solve complex problems and solve them within a reasonable amount of time. Modularity is thought to reduce problem complexity by decomposing large problems into smaller and less complex subproblems. In practice, introducing modularity into evolutionary algorithm representations appears to improve search performance; however, how and why modularity improves performance is not well understood. In this thesis, we seek to better understand the effects of modularity on search. In particular, what are the effects of module creation on the search space structure and how …
Improving Branch Prediction Accuracy Via Effective Source Information And Prediction Algorithms, Hongliang Gao
Improving Branch Prediction Accuracy Via Effective Source Information And Prediction Algorithms, Hongliang Gao
Electronic Theses and Dissertations
Modern superscalar processors rely on branch predictors to sustain a high instruction fetch throughput. Given the trend of deep pipelines and large instruction windows, a branch misprediction will incur a large performance penalty and result in a significant amount of energy wasted by the instructions along wrong paths. With their critical role in high performance processors, there has been extensive research on branch predictors to improve the prediction accuracy. Conceptually a dynamic branch prediction scheme includes three major components: a source, an information processor, and a predictor. Traditional works mainly focus on the algorithm for the predictor. In this dissertation, …
A Framework For Efficient Data Distribution In Peer-To-Peer Networks., Darshan Purandare
A Framework For Efficient Data Distribution In Peer-To-Peer Networks., Darshan Purandare
Electronic Theses and Dissertations
Peer to Peer (P2P) models are based on user altruism, wherein a user shares its content with other users in the pool and it also has an interest in the content of the other nodes. Most P2P systems in their current form are not fair in terms of the content served by a peer and the service obtained from swarm. Most systems suffer from free rider's problem where many high uplink capacity peers contribute much more than they should while many others get a free ride for downloading the content. This leaves high capacity nodes with very little or no …
Detecting Curved Objects Against Cluttered Backgrounds, Jan Prokaj
Detecting Curved Objects Against Cluttered Backgrounds, Jan Prokaj
Electronic Theses and Dissertations
Detecting curved objects against cluttered backgrounds is a hard problem in computer vision. We present new low-level and mid-level features to function in these environments. The low-level features are fast to compute, because they employ an integral image approach, which makes them especially useful in real-time applications. The mid-level features are built from low-level features, and are optimized for curved object detection. The usefulness of these features is tested by designing an object detection algorithm using these features. Object detection is accomplished by transforming the mid-level features into weak classifiers, which then produce a strong classifier using AdaBoost. The resulting …
Vcluster: A Portable Virtual Computing Library For Cluster Computing, Hua Zhang
Vcluster: A Portable Virtual Computing Library For Cluster Computing, Hua Zhang
Electronic Theses and Dissertations
Message passing has been the dominant parallel programming model in cluster computing, and libraries like Message Passing Interface (MPI) and Portable Virtual Machine (PVM) have proven their novelty and efficiency through numerous applications in diverse areas. However, as clusters of Symmetric Multi-Processor (SMP) and heterogeneous machines become popular, conventional message passing models must be adapted accordingly to support this new kind of clusters efficiently. In addition, Java programming language, with its features like object oriented architecture, platform independent bytecode, and native support for multithreading, makes it an alternative language for cluster computing. This research presents a new parallel programming model …
Real-Time Realistic Rendering Of Nature Scenes With Dynamic Lighting, Kevin Boulanger
Real-Time Realistic Rendering Of Nature Scenes With Dynamic Lighting, Kevin Boulanger
Electronic Theses and Dissertations
Rendering of natural scenes has interested the scientific community for a long time due to its numerous applications. The targeted goal is to create images that are similar to what a viewer can see in real life with his/her eyes. The main obstacle is complexity: nature scenes from real life contain a huge number of small details that are hard to model, take a lot of time to render and require a huge amount of memory unavailable in current computers. This complexity mainly comes from geometry and lighting. The goal of our research is to overcome this complexity and to …
Phase-Shifting Haar Wavelets For Image-Based Rendering Applications, Mais Alnasser
Phase-Shifting Haar Wavelets For Image-Based Rendering Applications, Mais Alnasser
Electronic Theses and Dissertations
In this thesis, we establish the underlying research background necessary for tackling the problem of phase-shifting in the wavelet transform domain. Solving this problem is the key to reducing the redundancy and huge storage requirement in Image-Based Rendering (IBR) applications, which utilize wavelets. Image-based methods for rendering of dynamic glossy objects do not truly scale to all possible frequencies and high sampling rates without trading storage, glossiness, or computational time, while varying both lighting and viewpoint. This is due to the fact that current approaches are limited to precomputed radiance transfer (PRT), which is prohibitively expensive in terms of memory …
Learning Geometry-Free Face Re-Lighting, Thomas Brendan Moore
Learning Geometry-Free Face Re-Lighting, Thomas Brendan Moore
Electronic Theses and Dissertations
The accurate modeling of the variability of illumination in a class of images is a fundamental problem that occurs in many areas of computer vision and graphics. For instance, in computer vision there is the problem of facial recognition. Simply, one would hope to be able to identify a known face under any illumination. On the other hand, in graphics one could imagine a system that, given an image, the illumination model could be identified and then used to create new images. In this thesis we describe a method for learning the illumination model for a class of images. Once …
Image-Space Approach To Real-Time Realistic Rendering, Musawir Shah
Image-Space Approach To Real-Time Realistic Rendering, Musawir Shah
Electronic Theses and Dissertations
One of the main goals of computer graphics is the fast synthesis of photorealistic image of virtual 3D scenes. The work presented in this thesis addresses this goal of speed and realism. In real-time realistic rendering, we encounter certain problems that are difficult to solve in the traditional 3-dimensional geometric space. We show that using an image-space approach can provide effective solutions to these problems. Unlike geometric space algorithms that operate on 3D primitives such as points, edges, and polygons, image-space algorithms operate on 2D snapshot images of the 3D geometric data. Operating in image-space effectively decouples the geometric complexity …
Behavior Of Variable-Length Genetic Algorithms Under Random Selection, Harold Stringer
Behavior Of Variable-Length Genetic Algorithms Under Random Selection, Harold Stringer
Electronic Theses and Dissertations
In this work, we show how a variable-length genetic algorithm naturally evolves populations whose mean chromosome length grows shorter over time. A reduction in chromosome length occurs when selection is absent from the GA. Specifically, we divide the mating space into five distinct areas and provide a probabilistic and empirical analysis of the ability of matings in each area to produce children whose size is shorter than the parent generation's average size. Diversity of size within a GA's population is shown to be a necessary condition for a reduction in mean chromosome length to take place. We show how a …
Augmentation In Visual Reality (Avr), Yunjun Zhang
Augmentation In Visual Reality (Avr), Yunjun Zhang
Electronic Theses and Dissertations
Human eyes, as the organs for sensing light and processing visual information, enable us to see the real world. Though invaluable, they give us no way to "edit" the received visual stream or to "switch" to a different channel. The invention of motion pictures and computer technologies in the last century enables us to add an extra layer of modifications between the real world and our eyes. There are two major approaches to modifications that we consider here, offline augmentation and online augmentation. The movie industry has pushed offline augmentation to an extreme level; audiences can experience visual surprises that …
Optimizing The High Dynamic Range Imaging Pipeline, Ahmet Oguz Akyuz
Optimizing The High Dynamic Range Imaging Pipeline, Ahmet Oguz Akyuz
Electronic Theses and Dissertations
High dynamic range (HDR) imaging is a rapidly growing field in computer graphics and image processing. It allows capture, storage, processing, and display of photographic information within a scene-referred framework. The HDR imaging pipeline consists of the major steps an HDR image is expected to go through from capture to display. It involves various techniques to create HDR images, pixel encodings and file formats for storage, tone mapping for display on conventional display devices and direct display on HDR capable screens. Each of these stages have important open problems, which need to be addressed for a smoother transition to an …