Graphics and Human Computer Interfaces Commons^™

Wireless Networks: Spert: A Stateless Protocol For Energy-Sensitive Real-Time Routing For Wireless Sensor Network, Sohail Jabbar, Abid Ali Minhas, Raja Adeel Akhtar

International Conference on Information and Communication Technologies

Putting constraints on performance of a system in the temporal domain, some times turns right into wrong and update into outdate. These are the scenarios where apposite value of time inveterate in the reality. But such timing precision not only requires tightly scheduled performance constraints but also requires optimal design and operation of all system components. Any malfunctioning at any relevant aspect may causes a serious disaster and even loss of human lives. Managing and interacting with such real-time system becomes much intricate when the resources are limited as in wireless sensor nodes. A wireless sensor node is typically comprises …

Large-Scale Near-Duplicate Web Video Search: Challenge And Opportunity, Wan-Lei Zhao, Song Tan, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

The massive amount of near-duplicate and duplicate web videos has presented both challenge and opportunity to multimedia computing. On one hand, browsing videos on Internet becomes highly inefficient for the need to repeatedly fast-forward videos of similar content. On the other hand, the tremendous amount of somewhat duplicate content also makes some traditionally difficult vision tasks become simple and easy. For example, annotating pictures can be as simple as recycling the tags of Internet images retrieved from image search engines. Such tasks, of either to eliminate or to recycle near-duplicates, can usually be achieved by the nearest neighbor search of …

Exploring Inter-Concept Relationship With Context Space For Semantic Video Indexing, Xiao-Yong Wei, Yu-Gang Jiang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Semantic concept detectors are often individually and independently developed. Using peripherally related concepts for leveraging the power of joint detection, which is referred to as context-based concept fusion (CBCF), has been one of the focus studies in recent years. This paper proposes the construction of a context space and the exploration of the space for CBCF. Context space considers the global consistency of concept relationship, addresses the problem of missing annotation, and is extensible for cross-domain contextual fusion. The space is linear and can be built by modeling the inter-concept relationship through annotation provided by either manual labeling or machine …

Architecting Human Operator Trust In Automation To Improve System Effectiveness In Multiple Unmanned Aerial Vehicles (Uav), Eric A. Cring, Adam G. Lenfestey

Theses and Dissertations

Current Unmanned Aerial System (UAS) designs require multiple operators for each vehicle, partly due to imperfect automation matched with the complex operational environment. This study examines the effectiveness of future UAS automation by explicitly addressing the human/machine trust relationship during system architecting. A pedigreed engineering model of trust between human and machine was developed and applied to a laboratory-developed micro-UAS for Special Operations. This unprecedented investigation answered three primary questions. Can previous research be used to create a useful trust model for systems engineering? How can trust be considered explicitly within the DoD Architecture Framework? Can the utility of architecting …

Image Processing For Multiple-Target Tracking On A Graphics Processing Unit, Michael A. Tanner

Theses and Dissertations

Multiple-target tracking (MTT) systems have been implemented on many different platforms, however these solutions are often expensive and have long development times. Such MTT implementations require custom hardware, yet offer very little flexibility with ever changing data sets and target tracking requirements. This research explores how to supplement and enhance MTT performance with an existing graphics processing unit (GPU) on a general computing platform. Typical computers are already equipped with powerful GPUs to support various games and multimedia applications. However, such GPUs are not currently being used in desktop MTT applications. This research explores if and how a GPU can …

Visual Word Proximity And Linguistics For Semantic Video Indexing And Near-Duplicate Retrieval, Yu-Gang Jiang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Bag-of-visual-words (BoW) has recently become a popular representation to describe video and image content. Most existing approaches, nevertheless, neglect inter-word relatedness and measure similarity by bin-to-bin comparison of visual words in histograms. In this paper, we explore the linguistic and ontological aspects of visual words for video analysis. Two approaches, soft-weighting and constraint-based earth mover’s distance (CEMD), are proposed to model different aspects of visual word linguistics and proximity. In soft-weighting, visual words are cleverly weighted such that the linguistic meaning of words is taken into account for bin-to-bin histogram comparison. In CEMD, a cross-bin matching algorithm is formulated such …

Seasonal Adaptation Of Vegetation Color In Satellite Images For Flight Simulations, Yuzhong Shen, Jiang Li, Vamsi Mantena, Srinivas Jakkula

Electrical & Computer Engineering Faculty Publications

Automatic vegetation identification plays an important role in many applications including remote sensing and high performance flight simulations. This paper proposes a novel method that identifies vegetative areas in satellite images and then alters vegetation color to simulate seasonal changes based on training image pairs. The proposed method first generates a vegetation map for pixels corresponding to vegetative areas, using ISODATA clustering and vegetation classification. The ISODATA algorithm determines the number of clusters automatically. We then apply morphological operations to the clustered images to smooth the boundaries between clusters and to fill holes inside clusters. Six features are then computed …

Mapping Reality Into Virtual Worlds, Josh Mcfarlane

Computer Science and Computer Engineering Undergraduate Honors Theses

As virtual worlds become more prevalent, they become increasingly useful as a means of information dissemination. This thesis examines the possible connections between real world objects and their virtual world counterparts. We look at how, by attaching sensors to an object, or by using a smart object with embedded sensors, the information can be relayed to a server. From this information, it will be possible to create a duplicate object in the virtual world and have it mirror the real world object in terms of state and movement. Almost all current solutions for remotely viewing a room or area are …

Ontology-Based Visual Word Matching For Near-Duplicate Retrieval, Yu-Gang Jiang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

This paper proposes a novel approach to exploit the ontological relationship of visual words by linguistic reasoning. A visual word ontology is constructed to facilitate the rigorous evaluation of linguistic similarity across visual words. The linguistic similarity measurement enables cross-bin matching of visual words, compromising the effectiveness and speed of conventional keypoint matching and bag-of-word approaches. A constraint EMD is proposed and experimented to efficiently match visual words. Empirical findings indicate that the proposed approach offers satisfactory performance to near-duplicate retrieval, while still enjoying the merit of speed efficiency compared with other techniques.

Matlab Report, Nancy Hale

Cornerstone 3 Reports : Interdisciplinary Informatics

The objective of this effort is to create a multidisciplinary approach to problem solving using technology. Through Thinkfinity, the Seidenberg School of Computer Science and Information Systems is collaborating with the science and quantitative faculty to create lessons that can be used by high school and first -year college students to work interactively with data to solve problems. MatLab is the tool of choice. It gives the user the ability to create visual models of large data sets and is used in the science and finance areas.

The key features of MatLab:

• Interactive tools for iterative exploration, design, and …

Bag-Of-Visual-Words Expansion Using Visual Relatedness For Video Indexing, Yu-Gang Jiang, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Bag-of-visual-words (BoW) has been popular for visual classification in recent years. In this paper, we propose a novel BoW expansion method to alleviate the effect of visual word correlation problem. We achieve this by diffusing the weights of visual words in BoW based on visual word relatedness, which is rigorously defined within a visual ontology. The proposed method is tested in video indexing experiment on TRECVID-2006 video retrieval benchmark, and an improvement of 7% over the traditional BoW is reported.

Pitch Correction On The Human Voice, Suzanne Ownbey

Computer Science and Computer Engineering Undergraduate Honors Theses

Singing is an excellent way to achieve fame, granted one can sing on key. Alternatively, a person who does not inherently have this ability or want to spend the time practicing to achieve it could use a programmatic solution to pitch correction. Proprietary products already exist that can correct the pitch of a singer, but the average mediocre singer may not be willing or able to purchase them. The focus of this research is to use the basic frequency altering algorithm of resampling, which alters the length of the wave to correct the pitch of a note. Small parts of …

Multimodal News Story Clustering With Pairwise Visual Near-Duplicate Constraint, Xiao Wu, Chong-Wah Ngo, Alexander G. Hauptmann

Research Collection School Of Computing and Information Systems

Story clustering is a critical step for news retrieval, topic mining, and summarization. Nonetheless, the task remains highly challenging owing to the fact that news topics exhibit clusters of varying densities, shapes, and sizes. Traditional algorithms are found to be ineffective in mining these types of clusters. This paper offers a new perspective by exploring the pairwise visual cues deriving from near-duplicate keyframes (NDK) for constraint-based clustering. We propose a constraint-driven co-clustering algorithm (CCC), which utilizes the near-duplicate constraints built on top of text, to mine topic-related stories and the outliers. With CCC, the duality between stories and their underlying …

Columbia University/Vireo-Cityu/Irit Trecvid2008 High-Level Feature Extraction And Interactive Video Search, Shih-Fu Chang, Junfeng He, Yu-Gang Jiang, Elie El Khoury, Chong-Wah Ngo, Akira Yanagawa, Eric Zavesky

Research Collection School Of Computing and Information Systems

In this report, we present overview and comparative analysis of our HLF detection system, which achieves the top performance among all type-A submissions in 2008. We also describe preliminary evaluation of our video search system, CuZero, in the interactive search task.

Concept Detection: Convergence To Local Features And Opportunities Beyond, Shih-Fu Chang, Junfeng He, Yu-Gang Jiang, Elie El Khoury, Chong-Wah Ngo, Akira Yanagawa, Eric Zavesky

Research Collection School Of Computing and Information Systems

No abstract provided.

Neighborhood Defined Adaboost Based Mixture Of Color Components For Efficient Skin Segmentation, Ramya Reddy Maaram

Electrical & Computer Engineering Theses & Dissertations

A skin segmentation algorithm robust to illumination changes and skin-like backgrounds is developed in this thesis. So far skin pixel classification has been limited to only individual color spaces and there has not been a comprehensive evaluation of which color components or combination of color components would provide the best classification accuracy, Color components in a given color space form the feature set for the classification of skin pixels. The combination of the color components or the features present within a single color space may not be the best when it comes to skin pixel classification as the discriminatory power …

Integrating Game Technology And Discrete Event Simulation To Analyze Mass Casualty Scenarios, Jason Loveland

Computational Modeling & Simulation Engineering Theses & Dissertations

In the last 10 years, video games have become complex simulation environments with high resolution 3D graphics enabled by powerhouse rendering engines, multi-player client server networks, user friendly displays and graphical user interface , while remaining relatively inexpensive. There is a critical need for systems engineering analysis and rapid trade studies due to changes in operations caused by current events such as terrorist attacks, asymmetric threats, natural disasters, etc. Modem games provide a unique way to visualize and interact with these complex environments, scenarios, missions, and operations. A discrete event simulator (DES) provides an environment to model system architecture behavior, …

Ontology-Enriched Semantic Space For Video Search, Xiao-Yong Wei, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Multimedia-based ontology construction and reasoning have recently been recognized as two important issues in video search, particularly for bridging semantic gap. The lack of coincidence between low-level features and user expectation makes concept-based ontology reasoning an attractive midlevel framework for interpreting high-level semantics. In this paper, we propose a novel model, namely ontology-enriched semantic space (OSS), to provide a computable platform for modeling and reasoning concepts in a linear space. OSS enlightens the possibility of answering conceptual questions such as a high coverage of semantic space with minimal set of concepts, and the set of concepts to be developed for …

Evaluating Bag-Of-Visual-Words Representations In Scene Classification, Jun Yang, Yu-Gang Jiang, Alexander G. Hauptmann, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Based on keypoints extracted as salient image patches, an image can be described as a “bag of visual words” and this representation has been used in scene classification. The choice of dimension, selection, and weighting of visual words in this representation is crucial to the classification performance but has not been thoroughly studied in previous work. Given the analogy between this representation and the bag-of-words representation of text documents, we apply techniques used in text categorization, including term weighting, stop word removal, feature selection, to generate image representations that differ in the dimension, selection, and weighting of visual words. The …

Practical Elimination Of Near-Duplicates From Web Video Search, Xiao Wu, Alexander G. Hauptmann, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Current web video search results rely exclusively on text keywords or user-supplied tags. A search on typical popular video often returns many duplicate and near-duplicate videos in the top results. This paper outlines ways to cluster and filter out the nearduplicate video using a hierarchical approach. Initial triage is performed using fast signatures derived from color histograms. Only when a video cannot be clearly classified as novel or nearduplicate using global signatures, we apply a more expensive local feature based near-duplicate detection which provides very accurate duplicate analysis through more costly computation. The results of 24 queries in a data …

Towards Optimal Bag-Of-Features For Object Categorization And Semantic Video Retrieval, Yu-Gang Jiang, Chong-Wah Ngo, Jun Yang

Research Collection School Of Computing and Information Systems

Bag-of-features (BoF) deriving from local keypoints has recently appeared promising for object and scene classification. Whether BoF can naturally survive the challenges such as reliability and scalability of visual classification, nevertheless, remains uncertain due to various implementation choices. In this paper, we evaluate various factors which govern the performance of BoF. The factors include the choices of detector, kernel, vocabulary size and weighting scheme. We offer some practical insights in how to optimize the performance by choosing good keypoint detector and kernel. For the weighting scheme, we propose a novel soft-weighting method to assess the significance of a visual word …

A Wavelet Based Complementary Approach For Image Enhancement, Ismail Kosum

Electrical & Computer Engineering Theses & Dissertations

Detail in an image means more meaningful information that is very important in many computer vision and pattern recognition applications. The object region visibility in an image plays an important role in obtaining accurate and desired information from the original image. In particular, image processing techniques developed for region segmentation and object classification have better results depending on the visibility in images. There are several enhancement techniques available which are capable of obtaining clear images with balanced lighting and contrast. In this thesis, a completely image dependent approach to enhance the luminance of images under extreme lighting conditions and a …

Improvement To The Data Logging Capability Of A Cough Monitoring System, Matthew Barlow

Inquiry: The University of Arkansas Undergraduate Research Journal

Data logging capability of a previously developed self contained cough recorder using an accelerometer as the sensing element is improved by using a secure digital memory card for later retrieval on a computer. Firmware is developed to enhance the functionality of the cough recorder. Existing libraries are modified for increased write rates. Increased writing speed allows 8-bit sampling at rates exceeding 8kHz, allowing for detailed time and frequency domain analysis. Additional features have also been developed to enable easy management of recordings, such as a file system compatibility with Microsoft Windows., and unique file names for each recording.

Introduction: Special Issue For The Selected Papers In The Fourth International Conference On Intelligent Multimedia Computing And Networking (Immcn) 2005, Chong-Wah Ngo, Hong-Va Leong

Research Collection School Of Computing and Information Systems

This special issue introduces seven papers selected from the IMMCN’ 2005, covering a wide range of emerging topics in multimedia field. These papers receive high scores and good comments from the reviewers in their respective areas of intelligent and nextgeneration networking, technology and application, multimedia coding, content analysis and retrieval. The seven papers are extended to 20 pages and then gone through another review process before the final publication. In this issue, we have two papers for video streaming, two papers for multimedia applications, one paper for video coding, and two papers for image and video retrieval.

Modeling Local Interest Points For Semantic Detection And Video Search At Trecvid 2006, Yu-Gang Jiang, Xiaoyong Wei, Chong-Wah Ngo, Hung-Khoon Tan, Wanlei Zhao, Xiao Wu

Research Collection School Of Computing and Information Systems

Local interest points (LIPs) and their features have been shown to obtain surprisingly good results in object detection and recognition. Its effectiveness and scalability, however, have not been seriously addressed in large-scale multimedia database, for instance TRECVID benchmark. The goal of our works is to investigate the role and performance of LIPs, when coupling with multi-modality features, for high-level feature extraction and automatic video search.

Threading And Autodocumenting News Videos: A Promising Solution To Rapidly Browse News Topics, Xiao Wu, Chong-Wah Ngo, Qing Li

Research Collection School Of Computing and Information Systems

This paper describes the techniques in threading and autodocumenting news stories according to topic themes. Initially, we perform story clustering by exploiting the duality between stories and textual-visual concepts through a co-clustering algorithm. The dependency among stories of a topic is tracked by exploring the textual-visual novelty and redundancy of stories. A novel topic structure that chains the dependencies of stories is then presented to facilitate the fast navigation of the news topic. By pruning the peripheral and redundant news stories in the topic structure, a main thread is extracted for autodocumentary

Rapid Prototyping For The Design Of Virtual Worlds, Prabhu V. Krishnan

Electrical & Computer Engineering Theses & Dissertations

Development of Virtual Reality (VR) applications is challenging where application developers are required to have expertise in the target VR technologies along with the problem domain expertise. New VR technologies impose a significant learning curve to even the most experienced VR developer. The proposed solution relies on synthesis to automate the migration of a VR application to a new unfamiliar VR platform/technology. To solve the problem, the Common Scene Definition Framework (CSDF) was developed, that serves as a superset/model representation of the target virtual world. Input modules were developed to populate the framework with the capabilities of the virtual world …

Accelerating Missile Threat Engagement Simulations Using Personal Computer Graphics Cards, Sean E. Jeffers

Theses and Dissertations

The 453rd Electronic Warfare Squadron supports on-going military operations by providing battlefield commanders with aircraft ingress and egress routes that minimize the risk of shoulder or ground-fired missile attacks on our aircraft. To determine these routes, the 453rd simulates engagements between ground-to-air missiles and allied aircraft to determine the probability of a successful attack. The simulations are computationally expensive, often requiring two-hours for a single 10-second missile engagement. Hundreds of simulations are needed to perform a complete risk assessment which includes evaluating the effectiveness of countermeasures such as flares, chaff, jammers, and missile warning systems. Thus, the need for faster …

Creating Enterprise Simulations Using High Level Architecture, Anton R. Lidums

Electrical & Computer Engineering Theses & Dissertations

Despite an established need, there are two remaining roadblocks to building distributed simulations and enterprise simulation systems. First, commercial simulation packages and engineering modeling tools are not readily distributable across multiple computers and have traditionally had very little impetus for utilizing a distributable format. Second, although HLA simulations have been built and there are tools to facilitate those efforts, very little has been done or written that specifically describes a "non-standard" integration implementation in sufficient detail to make the process reusable or repeatable. This thesis introduces a proof of concept prototype that was developed to integrate simulations. The paper presents …

Crafting A Research Paper, Ronan Fitzpatrick, Kevin O'Donnell

Conference papers

Writing research papers presents numerous different challenges, which vary from how to layout the various pages and format the text to what to include in the different sections that make up the paper. In order to clarify these issues this paper sets out guidelines and best practice approaches and demonstrates their use in the style of this paper.