Computer Sciences Commons^™

Image Stitching: Handling Parallax, Stereopsis, And Video, Fan Zhang

Dissertations and Theses

Panorama stitching increases the field of view in an image by assembling multiple views together. Traditional stitching techniques are proven to be effective only when dealing with parallax-free monocular images. Many challenges that remain unsolved in the stitching research area include how to stitch monocular images with large parallax, how to stitch stereoscopic images to maintain their stereoscopic consistency and original disparity distribution, and how to create panoramic videos with temporally coherent content. To provide more powerful stitching techniques with more universality, we first develop a parallax-tolerant image stitching technique. With the help of it, we then effectively extend the …

Accelerating Object Extraction And Detection Using A Hierarchical Approach With Shape Descriptors, Bassam Syed Arshad

Theses and Dissertations

Automatic object recognition is a fundamental problem in the fields of computer vision and machine learning, that has received a lot of research attention lately. Miniaturization and affordability, of both, high resolution digital cameras and advanced computing hardware, have further advanced the scope and applications of object recognition methods. While there are different methods, that build upon various low level features to construct object models, this work explores and implements the use of closed-contours as formidable object features. A hierarchical technique is employed to extract the contours, exploiting the inherent spatial relationships between the parent and child contours of an …

Vision-Based Motion For A Humanoid Robot, Khalid Abdullah Alkhulayfi

Dissertations and Theses

The overall objective of this thesis is to build an integrated, inexpensive, human-sized humanoid robot from scratch that looks and behaves like a human. More specifically, my goal is to build an android robot called Marie Curie robot that can act like a human actor in the Portland Cyber Theater in the play Quantum Debate with a known script of every robot behavior. In order to achieve this goal, the humanoid robot need to has degrees of freedom (DOF) similar to human DOFs. Each part of the Curie robot was built to achieve the goal of building a complete humanoid …

Active Object Localization In Visual Situations, Max H. Quinn, Anthony Rhodes, Melanie Mitchell

Computer Science Faculty Publications and Presentations

—We describe a method for performing active localization of objects in instances of visual situations. A visual situation is an abstract concept—e.g., “a boxing match”, “a birthday party”, “walking the dog”, “waiting for a bus”—whose image instantiations are linked more by their common spatial and semantic structure than by low-level visual similarity. Our system combines given and learned knowledge of the structure of a particular situation, and adapts that knowledge to a new situation instance as it actively searches for objects. More specifically, the system learns a set of probability distributions describing spatial and other relationships among relevant objects. The …

Deep Semantic Image Interpolation, Joshua D. Little

McKelvey School of Engineering Graduate Student Theses & Dissertations

Image datasets often live on a continuum: Images from an outdoor scene vary from day to night, across different weather conditions, and over the course of seasons. Faces age and exhibit different expressions. We consider the problem of taking individual images from these datasets and explicitly manipulating those images to change where they lie on the continuum. We focus on a version of this problem that requires as little input as possible, and we build off of previous work using CNN features to construct an intermediate image manifold on which to manipulate the images. We also investigate a novel way …

Real-Time, Non-Contact Heart Rate Monitor, Daniel Blike

Computer Engineering

No abstract provided.

Exemplar-Driven Top-Down Saliency Detection Via Deep Association, Shengfeng He, Rynson W. H. Lau, Qingxiong Yang

Research Collection School Of Computing and Information Systems

Top-down saliency detection is a knowledge-driven search task. While some previous methods aim to learn this "knowledge" from category-specific data, others transfer existing annotations in a large dataset through appearance matching. In contrast, we propose in this paper a locateby-exemplar strategy. This approach is challenging, as we only use a few exemplars (up to 4) and the appearances among the query object and the exemplars can be very different. To address it, we design a two-stage deep model to learn the intra-class association between the exemplars and query objects. The first stage is for learning object-to-object association, and the second …

Investigations Of An "Objectness" Measure For Object Localization, Lewis Richard James Coates

Dissertations and Theses

Object localization is the task of locating objects in an image, typically by finding bounding boxes that isolate those objects. Identifying objects in images that have not had regions of interest labeled by humans often requires object localization to be performed first. The sliding window method is a common naïve approach, wherein the image is covered with bounding boxes of different sizes that form windows in the image. An object classifier is then run on each of these windows to determine if each given window contains a given object. However, because object classification algorithms tend to be computationally expensive, it …

Collecting Image Cropping Dataset: A Hybrid System Of Machine And Human Intelligence, Uyen T. Mai, Feng Liu

Student Research Symposium

Image cropping is a common tool that exists in almost any image editor, yet automatic cropping is still a difficult problem in Computer Vision. Since images nowadays can be easily collected through the web, machine learning is a promising approach to solve this problem. However, an image cropping dataset is not yet available and gathering such a large-scale dataset is a non-trivial task. Although a crowdsourcing website such as Mechanical Turk seems to be a solution to this task, image cropping is a sophisticated task that is vulnerable to unreliable annotation; furthermore, collecting a large-scale high-quality dataset through crowdsourcing is …

Grounding Robot Motion In Natural Language And Visual Perception, Scott Alan Bronikowski

Open Access Dissertations

The current state of the art in military and first responder ground robots involves heavy physical and cognitive burdens on the human operator while taking little to no advantage of the potential autonomy of robotic technology. The robots currently in use are rugged remote-controlled vehicles. Their interaction modalities, usually utilizing a game controller connected to a computer, require a dedicated operator who has limited capacity for other tasks.

I present research which aims to ease these burdens by incorporating multiple modes of robotic sensing into a system which allows humans to interact with robots through a natural-language interface. I conduct …

Learning In Vision And Robotics, Daniel P. Barrett

Open Access Dissertations

I present my work on learning from video and robotic input. This is an important problem, with numerous potential applications. The use of machine learning makes it possible to obtain models which can handle noise and variation without explicitly programming them. It also raises the possibility of robots which can interact more seamlessly with humans rather than only exhibiting hard-coded behaviors. I will present my work in two areas: video action recognition, and robot navigation. First, I present a video action recognition method which represents actions in video by sequences of retinotopic appearance and motion detectors, learns such models automatically …

Position And Volume Estimation Of Atmospheric Nuclear Detonations From Video Reconstruction, Daniel T. Schmitt

Theses and Dissertations

Recent work in digitizing films of foundational atmospheric nuclear detonations from the 1950s provides an opportunity to perform deeper analysis on these historical tests. This work leverages multi-view geometry and computer vision techniques to provide an automated means to perform three-dimensional analysis of the blasts for several points in time. The accomplishment of this requires careful alignment of the films in time, detection of features in the images, matching of features, and multi-view reconstruction. Sub-explosion features can be detected with a 67% hit rate and 22% false alarm rate. Hotspot features can be detected with a 71.95% hit rate, 86.03% …

Probabilistic And Deep Learning Algorithms For The Analysis Of Imagery Data, Saikat Basu

LSU Doctoral Dissertations

Accurate object classification is a challenging problem for various low to high resolution imagery data. This applies to both natural as well as synthetic image datasets. However, each object recognition dataset poses its own distinct set of domain-specific problems. In order to address these issues, we need to devise intelligent learning algorithms which require a deep understanding and careful analysis of the feature space. In this thesis, we introduce three new learning frameworks for the analysis of both airborne images (NAIP dataset) and handwritten digit datasets without and with noise (MNIST and n-MNIST respectively). First, we propose a probabilistic framework …

Face Recognition-Based Real-Time System For Surveillance, Fahad Parvez Mahdi, Md. Mahmudul Habib, Susan Mckeever, A.S.M. Moslehuddin, Pandian Vasant

Articles

The ability to automatically recognize human faces based on dynamic facial images is important in security, surveillance and the health/independent living domains. Specific applications include access control to secure environments, identification of individuals at a particular place and intruder detection. This research proposes a real-time system for surveillance using cameras. The process is broken into two steps: (1) face detection and (2) face recognition to identify particular persons. For the first step, the system tracks and selects the faces of the detected persons. An efficient recognition algorithm is then used to recognize detected faces with a known database. The proposed …

Un Indicator De Incluziune Cu Aplicaţii În Computer Vision, Florentin Smarandache, Ovidiu Ilie Sandru

Branch Mathematics and Statistics Faculty and Staff Publications

În aceasta lucrare vom prezenta un procedeu de algoritmizare a operatiilor necesare deplasarii automate a unui obiect predefinit dintr-o imagine video data intr-o regiune tinta a acelei imagini, menit a facilita realizarea de aplicatii software specializate in rezolvarea acestui gen de probleme.

An Efficient Method For Optimizing Segmentation Parameters, Jacob D' Avy, Wei-Wen Hsu, Chung-Hao Chen, Andreas F. Koschan, Mongi Abidi

Electrical & Computer Engineering Faculty Publications

Segmenting an image into meaningful regions is an important step in many computer vision applications such as facial recognition, target tracking and medical image analysis. Because image segmentation is an ill-posed problem, parameters are needed to constrain the solution to one that is suitable for a given application. For a user, setting parameter values is often unintuitive. We present a method for automating segmentation parameter selection using an efficient search method to optimize a segmentation objective function. Efficiency is improved by utilizing prior knowledge about the relationship between a segmentation parameter and the objective function terms. An adaptive sampling of …

The Performance Of Random Prototypes In Hierarchical Models Of Vision, Kendall Lee Stewart

Dissertations and Theses

I investigate properties of HMAX, a computational model of hierarchical processing in the primate visual cortex. High-level cortical neurons have been shown to respond highly to particular natural shapes, such as faces. HMAX models this property with a dictionary of natural shapes, called prototypes, that respond to the presence of those shapes. The resulting set of similarity measurements is an effective descriptor for classifying images. Curiously, prior work has shown that replacing the dictionary of natural shapes with entirely random prototypes has little impact on classification performance. This work explores that phenomenon by studying the performance of random prototypes on …

Oriented Object Proposals, Shengfeng He, Rynson W. H. Lau

Research Collection School Of Computing and Information Systems

In this paper, we propose a new approach to generate oriented object proposals (OOPs) to reduce the detection error caused by various orientations of the object. To this end, we propose to efficiently locate object regions according to pixelwise object probability, rather than measuring the objectness from a set of sampled windows. We formulate the proposal generation problem as a generative probabilistic model such that object proposals of different shapes (i.e., sizes and orientations) can be produced by locating the local maximum likelihoods. The new approach has three main advantages. First, it helps the object detector handle objects of different …

Automated Multi-Modal Search And Rescue Using Boosted Histogram Of Oriented Gradients, Matthew A. Lienemann

Master's Theses

Unmanned Aerial Vehicles (UAVs) provides a platform for many automated tasks and with an ever increasing advances in computing, these tasks can be more complex. The use of UAVs is expanded in this thesis with the goal of Search and Rescue (SAR), where a UAV can assist fast responders to search for a lost person and relay possible search areas back to SAR teams. To identify a person from an aerial perspective, low-level Histogram of Oriented Gradients (HOG) feature descriptors are used over a segmented region, provided from thermal data, to increase classification speed. This thesis also introduces a dataset …

Leveraging Contextual Relationships Between Objects For Localization, Clinton Leif Olson

Dissertations and Theses

Object localization is currently an active area of research in computer vision. The object localization task is to identify all locations of an object class within an image by drawing a bounding box around objects that are instances of that class. Object locations are typically found by computing a classification score over a small window at multiple locations in the image, based on some chosen criteria, and choosing the highest scoring windows as the object bounding-boxes. Localization methods vary widely, but there is a growing trend towards methods that are able to make localization more accurate and efficient through the …

Visual Saliency Estimation : A Pre-Attentive Cognitive And Context-Aware Approach, Amanda Shannon Danko

Legacy Theses & Dissertations (2009 - 2024)

At each glance, biological vision systems organize a tremendous amount of input and

Seavipers - Computer Vision And Inertial Position Reference Sensor System (Cviprss), Justin Lee Erdman

LSU Doctoral Dissertations

This work describes the design and development of an optical, Computer Vision (CV) based sensor for use as a Position Reference System (PRS) in Dynamic Positioning (DP). Using a combination of robotics and CV techniques, the sensor provides range and heading information to a selected reference object. The proposed optical system is superior to existing ones because it does not depend upon special reflectors nor does it require a lengthy set-up time. This system, the Computer Vision and Inertial Position Reference Sensor System (CVIPRSS, pronounced \nickname), combines a laser rangefinder, infrared camera, and a pan--tilt unit with the robust TLD …

Mathematical Modeling For Partial Object Detection., Ahmed Reda Amin El-Barkouky

Electronic Theses and Dissertations

From a computer vision point of view, the image is a scene consisting of objects of interest and a background represented by everything else in the image. The relations and interactions among these objects are the key factors for scene understanding. In this dissertation, a mathematical model is designed for the detection of partially occluded faces captured in unconstrained real life conditions. The proposed model novelty comes from explicitly considering certain objects that are common to occlude faces and embedding them in the face model. This enables the detection of faces in difficult settings and provides more information to subsequent …

Designing A Bayer Filter With Smooth Hue Transition Interpolation Using The Xilinx System Generator, Zhiqiang Li, Peter Revesz

School of Computing: Conference and Workshop Papers

This paper describes the design of a Bayer filter with smooth hue transition using the System Generator for DSP. We describe and compare experimentally two different designs, one based on a MATLAB implementation and the other based on a modification of the Bayer filter using bilinear interpolation.

Camera Viewpoint Invariant Vehicular Traffic Segmentation And Classification, Jeffrey B. Flora

Electrical & Computer Engineering Theses & Dissertations

The goal of this intelligent transportation systems work is to develop a computer vision method that is view angle independent for segmenting and classifying vehicular traffic on highway systems. In order to achieve this goal, this work implements an algorithm for vehicle segmentation, feature extraction, and classification using the existing Virginia Department of Transportation (VDOT) infrastructure on networked traffic cameras. The VDOT traffic video is analyzed for vehicle detection and segmentation using an adaptive Gaussian mixture model algorithm. Speed estimation is performed using a single camera calibration. Size and shape features from morphological properties and texture features from histogram of …

Using Gist Features To Constrain Search In Object Detection, Joanna Browne Solmon

Dissertations and Theses

This thesis investigates the application of GIST features [13] to the problem of object detection in images. Object detection refers to locating instances of a given object category in an image. It is contrasted with object recognition, which simply decides whether an image contains an object, regardless of the object's location in the image.

In much of computer vision literature, object detection uses a "sliding window" approach to finding objects in an image. This requires moving various sizes of windows across an image and running a trained classifier on the visual features of each window. This brute force method can …

Walking Assistant – A Mobile Aid For The Visually-Impaired, Adin T. Miller

Master's Theses

The most common navigation aid visually-impaired people employ is a white cane, but, recently, technology has given rise to a varied set of sophisticated navigation aids. While these new aids can provide more assistance to a visually-impaired person than a white cane, they tend to be expensive due to a small market segment, which in turn can reduce their accessibility. In an effort to produce a technologically-advanced yet accessible navigation aid, an Android application is proposed that detects and notifies users about obstacles within their path through the use of a smartphone's camera. While the smartphone is mounted on a …

Moving Object Detection For Interception By A Humanoid Robot, Saltanat B. Tazhibayeva

Open Access Theses

Interception of a moving object with an autonomous robot is an important problem in robotics. It has various application areas, such as in an industrial setting where products on a conveyor would be picked up by a robotic arm, in the military to halt intruders, in robotic soccer (where the robots try to get to the moving ball and try to block an opponent's attempt to pass the ball), and in other challenging situations. Interception, in and of itself, is a complex task that demands a system with target recognition capability, proper navigation and actuation toward the moving target. There …

The Role Of Prototype Learning In Hierarchical Models Of Vision, Michael David Thomure

Dissertations and Theses

I conduct a study of learning in HMAX-like models, which are hierarchical models of visual processing in biological vision systems. Such models compute a new representation for an image based on the similarity of image sub-parts to a number of specific patterns, called prototypes. Despite being a central piece of the overall model, the issue of choosing the best prototypes for a given task is still an open problem. I study this problem, and consider the best way to increase task performance while decreasing the computational costs of the model. This work broadens our understanding of HMAX and related hierarchical …

Intelligent Sensing Based On Low Cost Unmanned Aerial Vehicles (Uav) For Bridge Condition Assessment, Theodore Teates, Austin Boyd, Chung-Hao Chen

Electrical & Computer Engineering Faculty Publications

The eventual completion of this project envisions the use of an Unmanned Aerial Vehicle (UAV) to inspect bridge infrastructure. This project may also be expanded to encompass general object detection and inspection in order to unburden this technology so that it may reach its fullest potential. The project requires research and development in three distinct areas of image processing, control structures, and integration of systems. Initial undergraduate research sets the base knowledge for the overall project, explores the areas of concentration that are desired to expand upon in the future project, and provides a base UAV model that new researchers …