Digital Commons Network^™

Instant Hdr-Nerf: Fast Learning Of High Dynamic Range View Synthesis With Unknown Exposure Settings, Nam Nguyen

Master's Theses

We propose Instant High Dynamic Range Neural Radiance Fields (Instant HDR-NeRF), a method of learning high dynamic range (HDR) view synthesis from a set of low dynamic range (LDR) views with unknown and varying exposure and white balance in as little as minutes. Our method can render novel HDR views without ground-truth supervision, and novel LDR views in different exposure settings, including those that match the ground-truth LDR views. The key to our method is to model the physical process of the camera with two implicit MLPs: a radiance field and a monotonically increasing tone-mapper. Built upon Instant Neural Graphics …

3d Pano Inpainting: Scene Construction Using A Single Input Panorama, Shivam Asija

Master's Theses

Creating 360-degree 3D content has gained traction in the past few years, being used for Virtual Reality environments. However, creating such content is challenging because it requires a multi-camera setup or a collection of images from different perspectives. This paper proposes 3D Pano Inpainting, a pipeline capable of transforming a single equirectangular panoramic RGBD image into a complete 360° 3D virtual reality scene represented as a textured mesh. Our methodology is as follows: we estimate a consistent depth map for the input panorama; we use a pre built framework to convert the image and its depth map into a textured …

Insights Into Cellular Evolution: Temporal Deep Learning Models And Analysis For Cell Image Classification, Xinran Zhao

Master's Theses

Understanding the temporal evolution of cells poses a significant challenge in developmental biology. This study embarks on a comparative analysis of various machine-learning techniques to classify cell colony images across different timestamps, thereby aiming to capture dynamic transitions of cellular states. By performing Transfer Learning with state-of-the-art classification networks, we achieve high accuracy in categorizing single-timestamp images. Furthermore, this research introduces the integration of temporal models, notably LSTM (Long Short Term Memory Network), R-Transformer (Recurrent Neural Network enhanced Transformer) and ViViT (Video Vision Transformer), to undertake this classification task to verify the effectiveness of incorporating temporal features into the classification …

Smartphone Based Object Detection For Shark Spotting, Darrick W. Oliver

Master's Theses

Given concern over shark attacks in coastal regions, the recent use of unmanned aerial vehicles (UAVs), or drones, has increased to ensure the safety of beachgoers. However, much of city officials' process remains manual, with drone operation and review of footage still playing a significant role. In pursuit of a more automated solution, researchers have turned to the usage of neural networks to perform detection of sharks and other marine life. For on-device solutions, this has historically required assembling individual hardware components to form an embedded system to utilize the machine learning model. This means that the camera, neural processing …

Experimental Characterization And Computer Vision-Assisted Detection Of Pitting Corrosion On Stainless Steel Structural Members, Riley J. Muehler

Master's Theses

Pitting corrosion is a prevalent form of corrosive damage that can weaken, damage, and initiate failure in corrosion-resistant metallic materials. For instance, 304 stainless steel is commonly utilized in various structures (e.g., miter gates, heat exchangers, and storage tanks), but is prone to failure through pitting corrosion and stress corrosion cracking under mechanical loading, regardless of its high corrosion resistance. In this study, to better understand the pitting corrosion damage development, controlled corrosion experiments were conducted to generate pits on 304 stainless steel specimens with and without mechanical loading. The pit development over time was characterized using a high-resolution laser …

Iris Detection Authenticator, Nathan D. Tang, Bryan K. Chau

Electrical Engineering

The development of iris biometric identification recognition is presented. Iris recognition differs from other methods because data acquisition is non-physical and is more accessible. It has been proven that the iris does not change as an individual ages and is well protected from external damages due to the eyelid and cornea, acting as a shield to the iris. In addition, the iris is almost impossible to forge due to its complex patterns and the current limitations in technology. Using Canny Edge Detection, Hough Transform, rubber-sheet normalization, Histogram of Gradient feature extraction, and the MultiMedia University iris database as our subjects, …

Eagle Medical Tray Denesting & Debris Removal Process, Nicholas Allen Ungefug, Noah Chavez, Susana Shu-Lin Okhuysen, Michael Augustine Pennington

Industrial and Manufacturing Engineering

Eagle Medical Incorporated is a contract medical device packaging and sterilization company. The company purchases thermoformed medical packaging trays, which maintain the sterility of medical devices, from various manufacturers. To ensure packaging quality and to prevent cleanroom contamination, Eagle Medical inspects and sterilizes each blister tray that they order. This process is an essential non-value-added activity that creates a bottleneck. Cleanroom employees must stop packaging medical devices and attend to the processing of blister trays and packaging solutions. The blister trays arrive at Eagle’s facility in nested stacks. Vibration and movement during shipping further compresses the stacks, which makes separation …

An Analysis Of Camera Configurations And Depth Estimation Algorithms For Triple-Camera Computer Vision Systems, Jared Peter-Contesse

Master's Theses

The ability to accurately map and localize relevant objects surrounding a vehicle is an important task for autonomous vehicle systems. Currently, many of the environmental mapping approaches rely on the expensive LiDAR sensor. Researchers have been attempting to transition to cheaper sensors like the camera, but so far, the mapping accuracy of single-camera and dual-camera systems has not matched the accuracy of LiDAR systems. This thesis examines depth estimation algorithms and camera configurations of a triple-camera system to determine if sensor data from an additional perspective will improve the accuracy of camera-based systems. Using a synthetic dataset, the performance of …

Take The Lead: Toward A Virtual Video Dance Partner, Ty Farris

Master's Theses

My work focuses on taking a single person as input and predicting the intentional movement of one dance partner based on the other dance partner's movement. Human pose estimation has been applied to dance and computer vision, but many existing applications focus on a single individual or multiple individuals performing. Currently there are very few works that focus specifically on dance couples combined with pose prediction. This thesis is applicable to the entertainment and gaming industry by training people to dance with a virtual dance partner.

Many existing interactive or virtual dance partners require a motion capture system, multiple cameras …

Dataset And Evaluation Of Self-Supervised Learning For Panoramic Depth Estimation, Ryan Nett

Master's Theses

Depth detection is a very common computer vision problem. It shows up primarily in robotics, automation, or 3D visualization domains, as it is essential for converting images to point clouds. One of the poster child applications is self driving cars. Currently, the best methods for depth detection are either very expensive, like LIDAR, or require precise calibration, like stereo cameras. These costs have given rise to attempts to detect depth from a monocular camera (a single camera). While this is possible, it is harder than LIDAR or stereo methods since depth can't be measured from monocular images, it has to …

Attentional Parsing Networks, Marcus Karr

Master's Theses

Convolutional neural networks (CNNs) have dominated the computer vision field since the early 2010s, when deep learning largely replaced previous approaches like hand-crafted feature engineering and hierarchical image parsing. Meanwhile transformer architectures have attained preeminence in natural language processing, and have even begun to supplant CNNs as the state of the art for some computer vision tasks.

This study proposes a novel transformer-based architecture, the attentional parsing network, that reconciles the deep learning and hierarchical image parsing approaches to computer vision. We recast unsupervised image representation as a sequence-to-sequence translation problem where image patches are mapped to successive layers …

Attacking Computer Vision Models Using Occlusion Analysis To Create Physically Robust Adversarial Images, Jacobsen Loh

Master's Theses

Self-driving cars rely on their sense of sight to function effectively in chaotic and uncontrolled environments. Thanks to recent developments in computer vision, specifically convolutional neural networks, autonomous vehicles have developed the ability to see at or above human-level capabilities, which in turn has allowed for rapid advances in self-driving cars. Unfortunately, much like humans being confused by simple optical illusions, convolutional neural networks are susceptible to simple adversarial inputs. As there is no overlap between the optical illusions that fool humans and the adversarial examples that threaten convolutional neural networks, little is understood as to why these adversarial examples …

Visual Speech Recognition Using A 3d Convolutional Neural Network, Matthew Rochford

Master's Theses

Main stream automatic speech recognition (ASR) makes use of audio data to identify spoken words, however visual speech recognition (VSR) has recently been of increased interest to researchers. VSR is used when audio data is corrupted or missing entirely and also to further enhance the accuracy of audio-based ASR systems. In this research, we present both a framework for building 3D feature cubes of lip data from videos and a 3D convolutional neural network (CNN) architecture for performing classification on a dataset of 100 spoken words, recorded in an uncontrolled envi- ronment. Our 3D-CNN architecture achieves a testing accuracy of …

A Study Of Face Embedding In Face Recognition, Khanh Duc Le

Master's Theses

Face Recognition has been a long-standing topic in computer vision and pattern recognition field because of its wide and important applications in our daily lives such as surveillance system, access control, and so on. The current modern face recognition model, which keeps only a couple of images per person in the database, can now recognize a face with high accuracy. Moreover, the model does not need to be retrained every time a new person is added to the database.

By using the face dataset from Digital Democracy, the thesis will explore the capability of this model by comparing it with …

Strawberry Detection Under Various Harvestation Stages, Yavisht Fitter

Master's Theses

This paper analyzes three techniques attempting to detect strawberries at various stages in its growth cycle. Histogram of Oriented Gradients (HOG), Local Binary Patterns (LBP) and Convolutional Neural Networks (CNN) were implemented on a limited custom-built dataset. The methodologies were compared in terms of accuracy and computational efficiency. Computational efficiency is defined in terms of image resolution as testing on a smaller dimensional image is much quicker than larger dimensions. The CNN based implementation obtained the best results with an 88% accuracy at the highest level of efficiency as well (600x800). LBP generated moderate results with a 74% detection accuracy …

Localization Using Convolutional Neural Networks, Shannon D. Fong

Computer Engineering

With the increased accessibility to powerful GPUs, ability to develop machine learning algorithms has increased significantly. Coupled with open source deep learning frameworks, average users are now able to experiment with convolutional neural networks (CNNs) to solve novel problems. This project sought to train a CNN capable of classifying between various locations within a building. A single continuous video was taken while standing at each desired location so that every class in the neural network was represented by a single video. Each location was given a number to be used for classification and the video was subsequently titled locX. These …

Corridor Navigation For Monocular Vision Mobile Robots, Matthew James Ng

Master's Theses

Monocular vision robots use a single camera to process information about its environment. By analyzing this scene, the robot can determine the best navigation direction. Many modern approaches to robot hallway navigation involve using a plethora of sensors to detect certain features in the environment. This can be laser range finders, inertial measurement units, motor encoders, and cameras.

By combining all these sensors, there is unused data which could be useful for navigation. To draw back and develop a baseline approach, this thesis explores the reliability and capability of solely using a camera for navigation. The basic navigation structure begins …

Automated Pruning Of Greenhouse Indeterminate Tomato Plants, Joey M. Angeja

Master's Theses

Pruning of indeterminate tomato plants is vital for a profitable yield and it still remains a manual process. There has been research in automated pruning of grapevines, trees, and other plants, but tomato plants have yet to be explored. Wage increases are contributing to the depleting profits of greenhouse tomato farmers. Rises in population are the driving force behind the need for efficient growing techniques. The major contribution of this thesis is a computer vision algorithm for detecting greenhouse tomato pruning points without the use of depth sensors. Given an up-close 2-D image of a tomato stem with the background …

Underwater Computer Vision - Fish Recognition, Spencer Chang, Austin Otto

Computer Engineering

The Underwater Computer Vision – Fish Recognition project includes the design and implementation of a device that can withstand staying underwater for a duration of time, take pictures of underwater creatures, such as fish, and be able to identify certain fish. The system is meant to be cheap to create, yet still able to process the images it takes and identify the objects in the pictures with some accuracy. The device can output its results to another device or an end user.

Multispectral Identification Array, Zachary D. Eagan

Computer Engineering

The Multispectral Identification Array is a device for taking full image spectroscopy data via the illumination of a subject with sixty-four unique spectra. The array combines images under the illumination spectra to produce an approximate reflectance graph for every pixel in a scene. Acquisition of an entire spectrum allows the array to differentiate objects based on surface material. Spectral graphs produced are highly approximate and should not be used to determine material properties, however the output is sufficiently consistent to allow differentiation and identification of previously sampled subjects. While not sufficiently advanced for use as a replacement to spectroscopy the …

Using Intel Realsense Depth Data For Hand Tracking In Unreal Engine 4, Granger Lang

Liberal Arts and Engineering Studies

This project describes how to build a hand tracking method for VR/AR using the raw data from a depth sensing camera.

Calculating Staircase Slope From A Single Image, Nicholas Joseph Clarke

Master's Theses

Realistic modeling of a 3D environment has grown in popularity due to the increasing realm of practical applications. Whether for practical navigation purposes, entertainment value, or architectural standardization, the ability to determine the dimensions of a room is becoming more and more important. One of the trickier, but critical, features within any multistory environment is the staircase. Staircases are difficult to model because of their uneven surface and various depth aspects. Coupling this need is a variety of ways to reach this goal. Unfortunately, many such methods rely upon specialized sensory equipment, multiple calibrated cameras, or other such impractical setups. …

Development Of A Tridimensional Measuring Application For Ipads, Michael Casebolt, Nicolas Kouatli, Jack Mullen

Computer Science and Software Engineering

In today’s fast-paced distribution centers workers and management alike are constantly searching for the quickest and most efficient way to package items for distribution. Even with the advancement of app-oriented solutions to a variety of problems across many industries there is a distinct unmet need in distribution environments for an application capable of increasing the efficiency and accuracy of packaging items. This senior project focused on the development and testing of an application utilizing the Structure Three Dimensional Sensor and a 4th generation iPad to scan an object or group of objects to be packaged and determine the overall dimensions …

Element Detection In Japanese Comic Book Panels, Toshihiro Kuboi

Master's Theses

Comic books are a unique and increasingly popular form of entertainment combining visual and textual elements of communication. This work pertains to making comic books more accessible. Specifically, this paper explains how we detect elements such as speech bubbles present in Japanese comic book panels. Some applications of the work presented in this paper are automatic detection of text and its transformation into audio or into other languages. Automatic detection of elements can also allow reasoning and analysis at a deeper semantic level than what’s possible today. Our approach uses an expert system and a machine learning system. The expert …

Early Forest Fire Heat Plume Detection Using Neural Network Classification Of Spectral Differences Between Long-Wave And Mid-Wave Infrared Regions, Raul-Alexander Aldama

Master's Theses

It is difficult to capture the early signs of a forest fire at night using current visible-spectrum sensor technology. Infrared (IR) light sensors, on the other hand, can detect heat plumes expelled at the initial stages of a forest fire around the clock. Long-wave IR (LWIR) is commonly referred to as the “thermal infrared” region where thermal emissions are captured without the need of, or reflections from, external radiation sources. Mid‑wave IR (MWIR) bands lie between the “thermal infrared” and “reflected infrared” (i.e. short-wave IR) regions. Both LWIR and MWIR spectral regions are able to detect thermal radiation; however, they …

Markerless Affine Region Tracking And Augmentation Using Mser And Sift, Gregory (Greg) Eddington Ii

Computer Engineering

Due to the advancements in mobile computing hardware and the inclusion of cameras in many computing platforms, augmented reality systems have become widely available. This paper presents a real-time implementation of a novel markerless augmented reality algorithm which is able to track two-dimensional affine regions without a priori information of the environment or computing a world model. The implementation consists of the MAR library; a modular software library which performs the region detection, identification, and tracking; and the Lighthouse application; a program which uses the MAR library to allow the user to augment scenes viewed from a camera. The algorithm …

The Use Of Contextual Clues In Reducing False Positives In An Efficient Vision-Based Head Gesture Recognition System, Brian M. Blonski

Master's Theses

This thesis explores the use of head gesture recognition as an intuitive interface for computer interaction. This research presents a novel vision-based head gesture recognition system which utilizes contextual clues to reduce false positives. The system is used as a computer interface for answering dialog boxes. This work seeks to validate similar research, but focuses on using more efficient techniques using everyday hardware. A survey of image processing techniques for recognizing and tracking facial features is presented along with a comparison of several methods for tracking and identifying gestures over time. The design explains an efficient reusable head gesture recognition …