Video Event Understanding With Pattern Theory, 2015 University of South Florida
Video Event Understanding With Pattern Theory, Fillipe Souza, Sudeep Sarkar, Anuj Srivastava, Jingyong Su
We propose a combinatorial approach built on Grenander’s pattern theory to generate semantic interpretations of video events of human activities. The basic units of representations, termed generators, are linked with each other using pairwise connections, termed bonds, that satisfy predefined relations. Different generators are specified for different levels, from (image) features at the bottom level to (human) actions at the highest, providing a rich representation of items in a scene. The resulting configurations of connected generators provide scene interpretations; the inference goal is to parse given video data and generate high-probability configurations. The probabilistic structures are imposed using energies ...
Two Correspondence Problems Easier Than One, 2015 Purdue University
Two Correspondence Problems Easier Than One, Aaron Michaux, Zygmunt Pizlo
Computer vision research rarely makes use of symmetry in stereo reconstruction despite its established importance in perceptual psychology. Such stereo reconstructions produce visually satisfying figures with precisely located points and lines, even when input images have low or moderate resolution. However, because few invariants exist, there are no known general approaches to solving symmetry correspondence on real images. The problem is significantly easier when combined with the binocular correspondence problem, because each correspondence problem provides strong non-overlapping constraints on the solution space. We demonstrate a system that leverages these constraints to produce accurate stereo models from pairs of binocular images ...
Formal Aspects Of Non-Rigid-Shape-From-Motion Perception, 2015 SUNY College of Optometry
Formal Aspects Of Non-Rigid-Shape-From-Motion Perception, Vicky Froyen, Qasim Zaidi
Our world is full of objects that deform over time, for example animals, trees and clouds. Yet, the human visual system seems to readily disentangle object motions from non-rigid deformations, in order to categorize objects, recognize the nature of actions such as running or jumping, and even to infer intentions. A large body of experimental work has been devoted to extracting rigid structure from motion, but there is little experimental work on the perception of non-rigid 3-D shapes from motion (e.g. Jain, 2011). Similarly, until recently, almost all formal work had concentrated on the rigid case. In the last ...
Object Recognition And Visual Search With A Physiologically Grounded Model Of Visual Attention, 2015 Chemnitz University of Technology
Object Recognition And Visual Search With A Physiologically Grounded Model Of Visual Attention, Frederik Beuth, Fred H. Hamker
Visual attention models can explain a rich set of physiological data (Reynolds & Heeger, 2009, Neuron), but can rarely link these findings to real-world tasks. Here, we would like to narrow this gap with a novel, physiologically grounded model of visual attention by demonstrating its objects recognition abilities in noisy scenes.
To base the model on physiological data, we used a recently developed microcircuit model of visual attention (Beuth & Hamker, in revision, Vision Res) which explains a large set of attention experiments, e.g. biased competition, modulation of contrast response functions, tuning curves, and surround suppression. Objects are represented by object-view specific neurons, learned via a trace learning approach (Antonelli et al., 2014, IEEE TAMD). A visual cortex model combines the microcircuit with neuroanatomical properties like top-down attentional processing, hierarchical-increasing receptive field sizes, and synaptic transmission delays. The visual cortex model is complemented by a model of the frontal eye field (Zirnsak et al., 2011, Eur J Neurosci).
We evaluated the model on a realistic object recognition task in which a given target has to be localized in a scene (guided visual search task), using 100 different target objects, 1000 scenes, and two backgrounds. The model achieves an accuracy of 92% at black, and of 71% at white-noise backgrounds. We found that two of the underlying, neuronal attention mechanisms are prominently relevant for guided visual search: amplification of neurons preferring the target; and suppression of neurons encoding distractors or background noise.
Modeling Visual Features To Recognize Biological Motion: A Developmental Approach, 2015 Robotics, Brain and Cognitive Sciences Department, Istituto Italiano di Tecnologia, Italy
Modeling Visual Features To Recognize Biological Motion: A Developmental Approach, Giulio Sandini, Nicoletta Noceti, Alessandra Sciutti, Francesco Rea, Alessandro Verri, Francesca Odone
In this work we deal with the problem of designing and developing computational vision models – comparable to the early stages of the human development – using coarse low-level information.
More specifically, we consider a binary classification setting to characterize biological movements with respect to non-biological dynamic events. To this purpose, our model builds on top of the optical flow estimation, and abstract the representation to simulate the limited amount of visual information available at birth. We take inspiration from known biological motion regularities explained by the Two-Thirds Power Law, and design a motion representation that includes different low-level features, which can ...
Gal: A Stepwise Model For Automated Cloud Shadow Detection In Hico Oceanic Imagery Utilizing Guided Filter, Pixel Assignment, And Geometric Linking, 2015 University of Southern Mississippi
Gal: A Stepwise Model For Automated Cloud Shadow Detection In Hico Oceanic Imagery Utilizing Guided Filter, Pixel Assignment, And Geometric Linking, Jennerpher Renee Meyers
Detection of cloud shadow pixels is an important step in image processing in several remote sensing ocean-color application domains, such as obtaining chlorophyll content. While shadow detection algorithms do exist, the vast majority are for over land which leaves few options for detection over water.
The detection of cloud shadow over water in HICO imagery is a unique problem. As its name implies, HICO (Hyperspectral Imager for the Coastal Ocean) imagery is produced for coastal and oceanic regions. Since land based algorithms remove water before processing, these approaches would not be applicable. The only currently published HICO shadow pixel detection ...
Video Event Recognition And Prediction Based On Temporal Structure Analysis, 2015 Northeastern University
Video Event Recognition And Prediction Based On Temporal Structure Analysis, Kang Li
Computer Engineering Dissertations
The increasing ubiquitousness of multimedia information in today's world has positioned video as a favored information vehicle, and given rise to an astonishing generation of social media and surveillance footage. Consumer-grade video is becoming abundant on the Internet, and it is now easier than ever to download multimedia material of any kind and quality. This raises a series of technological demands for automatic video understanding, which has motivated the research community to guide its steps towards a better attainment of such capabilities. As a result, current trends on cognitive vision promise to recognize complex events and self-adapt to different ...
Prepositional Phrase Attachment Problem Revisited: How Verbnet Can Help, 2015 University of Nebraska at Omaha
Prepositional Phrase Attachment Problem Revisited: How Verbnet Can Help, Dan Bailey, Yuliya Lierler, Benjamin Susman
Resolving attachment ambiguities is a pervasive problem in syntactic analysis. We propose and investigate an approach to resolving prepositional phrase attachment that centers around the ways of incorporating semantic knowledge derived from the lexico-semantic ontologies such as VERBNET and WORDNET.
Random Multipliers Numerically Stabilize Gaussian And Block Gaussian Elimination: Proofs And An Extension To Low-Rank Approximation, 2015 Lehman College and Graduate Center of CUNY
Random Multipliers Numerically Stabilize Gaussian And Block Gaussian Elimination: Proofs And An Extension To Low-Rank Approximation, Victor Pan, Xiaodong Yan
We study two applications of standard Gaussian random multipliers. At first we prove that with a probability close to 1 such a multiplier is expected to numerically stabilize Gaussian elimination with no pivoting as well as block Gaussian elimination. Then, by extending our analysis, we prove that such a multiplier is also expected to support low-rank approximation of a matrix without customary oversampling. Our test results are in good accordance with this formal study. The results remain similar when we replace Gaussian multipliers with random circulant or Toeplitz multipliers, which involve fewer random parameters and enable faster multiplication. We formally ...
An Extensible Technology Framework For Cyber Security Education, 2015 Brigham Young University - Provo
An Extensible Technology Framework For Cyber Security Education, Frank Jordan Sheen
All Theses and Dissertations
Cyber security education has evolved over the last decade to include new methods of teaching and technology to prepare students. Instructors in this field of study often deal with a subject matter that has rigid principles, but changing ways of applying those principles. This makes maintaining courses difficult. This case study explored the kind of teaching methods, technology, and means used to explain these concepts. This study shows that generally, cyber security courses require more time to keep up to date. It also evaluates one effort, the NxSecLab, on how it attempted to relieve the administrative issues in teaching these ...
Authentication Melee: A Usability Analysis Of Seven Web Authentication Systems, 2015 Brigham Young University - Provo
Authentication Melee: A Usability Analysis Of Seven Web Authentication Systems, Scott Ruoti
All Theses and Dissertations
Passwords continue to dominate the authentication landscape in spite of numerous proposals to replace them. Even though usability is a key factor in replacing passwords, very few alternatives have been subjected to formal usability studies and even fewer have been analyzed using a standard metric. We report the results of four within-subjects usability studies for seven web authentication systems. These systems span federated, smartphone, paper tokens, and email-based approaches. Our results indicate that participants prefer single sign-on systems. We utilize the Systems Usability Scale (SUS) as a standard metric for empirical analysis and find that it produces reliable, replicable results ...
Interpreting Multitouch Gestures, 2015 University or Minnesota, Morris
Interpreting Multitouch Gestures, Michael Schuweiler
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
Interpreting multitouch interactions can be as simple as understanding code that handles these multitouches and this code's associated actions. As more touch events are added to an input, inputs become more complex. There are multiple approaches to interpreting these inputs between users and touchscreens. Researchers in this field find answers to common problems and provide developers with tools that make interactions with multitouch devices easier to describe and incorporate into their systems. These tools are then used to create gestures through different approaches, specifically through demonstration and by declaration. In this paper, these researchers' tools are described and compared.
A Web-Based Job Management System For Three-Dimensional Printing And Scanning At The University Of North Dakota, Dalyn Limesand, Stephanie Hollman, Jeremy Straub, Scott Kerlin
Three-dimensional (3D) printers have gained popularity for use for many different projects. The work presented herein aims to make this process simpler. This paper discusses a system that will allow individuals from across campus to submit object files for printing by a 3D printer, without having to schedule appointment and manually operate it.
Logistical requirements dictate some level of human involvement, despite a goal of creating a fully automated system. Involvement areas include converting /preparing submitted files, sending the job to the printer, print tray preparation, and completed object removal. From a user’s perspective, however a seamless experience is ...
The Creation Of A Communication Systems For A Small Satellite At The University Of North Dakota, Michael Hlas, Jeremy Straub, Ronald Marsh
Software defined radios (SDRs) are poised to significantly enhance the future of small spacecraft communications. They allow signal processing to be performed on a computer by software rather than requiring dedicated hardware. The SDR takes data from the flight computer and converts it into an analog signal that is transmitted via the spacecraft antenna. Because the signal processing is done in software, the radio can be easily reconfigured.
Data is prepared for transmission by TCP stack software onboard the OpenOrbiter Spacecraft and placed in a queue while the spacecraft is listening for a signal from a ground station. When a ...
Update On The Development Of A 1-U Cubesat At The University Of North Dakota, 2015 SelectedWorks
Update On The Development Of A 1-U Cubesat At The University Of North Dakota, Jeremy Straub, Ronald Marsh
An overview of the progress on the development of the OpenOrbiter CubeSat is presented. This covers, at a high level, the work that has been performed during the past year and foundational work that occurred prior to this. This poster also discusses future plans for the Open Prototype for Educational NanoSats (OPEN) framework and the OpenOrbiter Small Spacecraft Development Initiative. Particular focus is given to the ongoing work to prepare for an orbital launch, which the program has been down-selected for through the NASA ELaNa CubeSat Launch Initiative program.
In addition to this discussion of the program’s origins, goals ...
Scheduling Algorithm Development For An Open Source Software Spacecraft, 2015 SelectedWorks
Scheduling Algorithm Development For An Open Source Software Spacecraft, Calvin Bina, Jeremy Straub, Ronald Marsh
The OpenOrbiter project at the University of North Dakota is working to develop a set of designs for a CubeSat class spacecraft as well as a working, modular collection of open source code that can be used by other CubeSat projects as a starting point for development. The availability of these designs and this codebase should foster accelerated development for other CubeSat projects, allowing those projects to focus their effort on their own application area, instead of reinventing the proverbial wheel. One aspect of this is to implement a task scheduler which will run on a Raspberry Pi flight computer ...
Decomposition-Based Optimal Market-Based Planning For Multi-Agent Systems With Shared Resources, 2015 Carnegie Mellon University
Decomposition-Based Optimal Market-Based Planning For Multi-Agent Systems With Shared Resources, Sue Ann Hong, Geoffrey J. Gordon
Machine Learning Department
Market-based algorithms have become popular in collaborative multi-agent planning due to their simplicity, distributedness, low communication requirements, and proven success in domains such as task allocation and robotic exploration. Most existing marketbased algorithms, however, suffer from two main drawbacks: resource prices must be carefully handcrafted for each problem domain, and there is no guarantee on final solution quality. We present an optimal marketbased algorithm, derived from a mixed integer program formulation of planning problems. Our method is based on two wellknown techniques for optimization: DantzigWolfe decomposition and Gomory cuts. The former prices resources optimally for a relaxed version of the ...
Noise-Adaptive Margin-Based Active Learning And Lower Bounds Under Tsybakov Noise Condition, 2015 Carnegie Mellon University
Noise-Adaptive Margin-Based Active Learning And Lower Bounds Under Tsybakov Noise Condition, Yining Wang, Aarti Singh
Machine Learning Department
We present a polynomial-time noise-robust margin-based active learning algorithm to find homogeneous (passing the origin) linear separators and analyze its statistical rate of error convergence when labels are corrupted by noise. We show that when the imposed noise satisfies the Tsybakov low noise condition [MT+99, Tsy04] the algorithm is able to adapt to unknown level of noise and achieves optimal statistical rate up to polylogarithmic factors. In addition, the presented algorithm is simple and does not require prior knowledge of the amount of noise in the label distribution. We also derive lower bounds for margin based active learning algorithms ...
An Interpretive Phenomenological Analysis Inquiry Into Facebook Newcomer Motivations For Participatory Activities, 2015 Nova Southeastern University
An Interpretive Phenomenological Analysis Inquiry Into Facebook Newcomer Motivations For Participatory Activities, Kristin Raub
This qualitative study provided insight into the phenomenon of newcomers in social networking, in particular, to understand what role specific Facebook features play in motivating content sharing and contribution among newcomers. Research indicated that the first several months or years of social networking site (SNS) membership are the most crucial in terms of indicating long-term participation and commitment to the SNS. Long-term participation is specifically manifested through interactions with peers who are members of the same website and through interactivity such as content sharing and contribution. A number of quantitative studies have focused on motivations for user contribution in social ...
Inspirational Space As A Mechanism To Transform Departmental Culture, 2015 Montana State University - Bozeman
Inspirational Space As A Mechanism To Transform Departmental Culture, John Paxton
Academic Chairpersons Conference Proceedings
Montana State University’s Computer Science Department created a collaborative, informal, Japanese-themed Student Success Center. The goal of the space was to broaden participation and induce cultural change in computer science. The design philosophy behind the room now serves as a model for collaborative space at MSU.