Electrical and Computer Engineering Commons^™

Scalefusion: Hierarchical Feature Aggregation For Unified Multiscale Object Detection, Ayşenur Yaylaci, Berru Kaya, Mehmet Kiliçarslan

Turkish Journal of Electrical Engineering and Computer Sciences

Detecting objects across a wide range of scales, particularly small ones, remains a significant challenge in computer vision. Existing methods often improve small object detection at the cost of performance on larger objects or introduce significant computational overhead through external techniques like image slicing. This paper introduces ScaleFusion, a novel, unified, end-to-end object detection architecture designed to provide robust performance across all scales within a single model. The core of our approach is a hierarchical feature aggregation strategy structured like a tree. ScaleFusion processes an image by running a shared backbone network only on fine-grained patches at the lowest level …

Robust Real-Time Uav Target Tracking With Onboard Vision-Based Yaw Control, Rylan Malarchick, Jose Castelblanco, Enrique Amaya, Carmen Dimario, Graysen Brinkman, Chirag Kumar, Kiwon Yoon, Sajid Berhane

Beyond: Undergraduate Research Journal

Autonomous tracking of agile unmanned aerial vehicles (UAVs) presents significant challenges for real-time perception and control systems. This work presents AIRHOUND (Autonomous Intelligent Rotorcraft for Hostile Object Unified Navigation and Detection), a UAV platform implementing vision-based yaw tracking through a modular ROS2 software architecture. The system employs YOLOv8 object detection optimized with NVIDIA TensorRT for embedded deployment on an NVIDIA Jetson Orin companion computer. Detected targets are processed through a geometric tracking module that converts pixel coordinates to angular yaw errors using pinhole camera intrinsics, with a proportional controller generating rate-limited yaw commands. These commands are streamed to a PX4 …

A Comparative Study Of Model Predictive Control And The Stanley Method For Vehicle Path Tracking Applications, Noah S. Fitzgerald

Master's Theses

This thesis compares a model predictive controller (MPC) and a lateral Stanley controller for vehicle path-tracking applications under simulation-based and perception-driven operating conditions. Both controllers were evaluated in simulation using a nonlinear dynamic bicycle model executing single and double lane change maneuvers. Following simulation-based evaluation, both controllers were implemented on hardware within a perception-driven steering-control pipeline. This pipeline utilized recorded sensor data from the MXcarkit 1/8^th-scale autonomous vehicle platform, incorporating lane instance segmentation and homography-based roadway estimation.

Under idealized simulation conditions, the MPC demonstrated improved trajectory-tracking performance during aggressive maneuvers while requiring greater steering activity and computational effort …

Vision-Guided Motion Planning For Autonomous Catch With A Robotic Arm, Kayla Go-Oco, Ashik K. Islam, Raegan Gritzmacher

Electrical Engineering

Modern robotic systems are often evaluated using static and highly controlled tasks, such as pick-and-place demonstrations, which do not fully represent the uncertainty and adaptability required in real-world environments. A major challenge in robotics research is enabling robotic systems to perceive, track, and respond to dynamic objects in real time while maintaining accurate and reliable motion control. This project addresses these challenges by developing an autonomous robotic platform in which an OpenMANIPULATOR-Y robotic arm detects, tracks, and attempts to catch a moving tennis ball using a vision-guided control system. The system integrates YOLO-based object detection with an Intel RealSense D455 …

Deep Learning Approaches For Ctenophore Identification And Tracking, Anagha Bharadwaj

Theses

Ctenophores are translucent marine organisms with nearly invisible tentacles and pose significant challenges due to their transparent morphology and ambiguous structural features. This research addresses the classification and tracking of these organisms and evaluates the performance of current computer vision models under sparse-data environments.

A dataset from the NJIT Life History Lab consisting of microscopic laboratory videos and photographs of different growth stages is used to train and assess a number of convolutional neural network designs, including VGG16, ResNet, BioCLIP2, YOLO, and DeepLabCut. Additionally, a web-based interface is developed to evaluate expert-labeled ground truth with the model's performance.

The findings …

Performance Analysis Of Video Coding For Machines With Vision Transformers, Vaishnavi Dhulipudi

Electronic Theses and Dissertations

This thesis investigates the performance of Video Coding for Machines (VCM) with Vision Transformer based object detection models. While existing VCM studies and tool designs have largely been developed under CNN-based assumptions, recent advances in computer vision have shown the growing importance of transformer based models. Motivated by this shift, this work studies whether VCM compressed data remains suitable for Vision Transformer based inference in addition to conventional CNN-based task networks.

To address this problem, three representative transformer based object detection models were selected: DETR, SWIN, and YOLOS. These models were chosen to represent different architectural styles, namely a CNN …

Using Ai To Predict Energy Expenditure In Lower Limb Prosthesis Users, Nelly Diaz, Siem Hadish

Posters - 2026

• Computer vision has evolved from simple image classification and object detection to analyzing human motion and biomechanics (1). • CNN’s are usually focused on image classification, but, in this case, we are not asking the model if a person is walking. • Many real-world problems require regression: Predicting a continuous number like energy expenditure of walking is a complex task. • It is essential for Prosthetists to understand energy expenditure of their prosthetic patients (2). • An amputee may use 20-30% more energy to walk. • In this project, we developed an AI model to analyze human motion and …

Analysis Of Vision Transformers And Domain Adaptation In Long-Range Facial Recognition, Zachary Michael Swanson

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

Atmospheric turbulence presents a significant barrier to long-range facial recognition, introducing severe geometric distortions and blur that degrade image quality. This thesis investigates deep learning approaches for mitigating these effects, with a focus on transformer based architectures and domain adaptation strategies.

An in-depth benchmarking study was performed using convolutional neural networks (CNNs) and vision transformers (ViTs) on the Husker BRIAR Research Collection from up to 500m (HBRC-500) face dataset. The results demonstrated that vision transformers, particularly hierarchical vision transformers like the shifted-window (Swin) transformer, outperform CNN-based models at long distances due to their ability to model global spatial relationships and …

An Edge Computing Device Optimized And Transfer Learning Enhanced Deep Learning Model For Detecting Wildfire Flame And Smoke, Giovanny Vazquez

UNLV Theses, Dissertations, Professional Papers, and Capstones

The integration of autonomous unmanned aerial vehicles (UAVs) with edge computing technology and deep learning (DL)-based object detection offers a groundbreaking solution for real-time wildfire detection, enabling rapid data processing directly on devices and minimizing response delays in critical scenarios. However, although showing early promise, performance is often constrained by limited training data and edge computing devices that lack graphics processing unit (GPU) acceleration. This thesis seeks to address these limitations in two stages.First, this work explores the transformative potential of Transfer Learning (TL) to enhance wildfire object detection model accuracy while also investigating TL’s impact, for DL-based object detection …

Computer Vision-Based Framework For Data Extraction From Heterogeneous Financial Tables: A Comprehensive Approach To Unlocking Financial Insights, Iftakhar Ali Khandokar, Priya Deshpande

Electrical and Computer Engineering Faculty Research and Publications

Information extraction from financial document images is crucial in computer vision and NLP, as financial data often exists in image or PDF format, enabling organizations to analyze and make informed business decisions using OCR advancements. The table contents of financial document images are one of the prominent structures to confine important portions of data of the document and many Deep learning-based methods have been proposed to detect Table regions inside document images. The shortcomings of the current approach are that it is bounded within the detection of the table region and struggles in cases such as handling different layouts and …

Surgical Suturing Skill Assessment Using Estimated Hand Roll Angle From A Deep-Learning Computer Vision Algorithm, Jianxin Gao, Amir Mehdi Shayan, Simar P. Singh, Joe Bible, Ravikiran Singapogu, Richard E. Groff

Publications

This paper proposes a deep-learning computer vision algorithm to estimate hand roll angles for metric-based assessment of surgical suturing skills. The number of rolls metric, previously calculated directly from IMU data, counts the number of hand roll reversals during a single suture. To calculate this metric using computer vision, we apply a deep-learning algorithm that can reliably estimate hand roll angles after training on suturing videos collected on the SutureCoach simulator. Results show that the estimation accuracy of the deep-learning algorithm is robust to different video backgrounds. The number of rolls metrics were used to analyze suturing performance in the …

Two-Dimensional Quantum Material Identification Via Self-Attention And Soft-Labeling In Deep Learning, Xuan Bac Nguyen, Apoorva Bisht, Benjamin Thompson, Hugh O.H. Churchill, Khoa Luu, Samee U. Khan

Electrical Engineering and Computer Science Faculty Publications and Presentations

Detecting two-dimensional (2D) materials in silicon chips presents a significant challenge in the field of quantum machines due to the difficulty of data collection. Specifically, among thousands of flakes, not all flakes are useful or well-annotated, resulting in noisy and hard samples within the dataset, which challenges the deep neural network (DNN) to learn. To address this problem, we propose a novel method for identifying quantum 2D flakes even when there is a high rate of missing annotations in the input images. In particular, we first propose a new mechanism for automatically detecting false negative flakes that are missing annotations. …

Impact Of Operational Ladar Occlusions On Point Cloud Instance Segmentation, Andrew D. Gibson

Theses and Dissertations

Data exploitation techniques are the enabler for technological advancements in military ISR applications of ladar ISR. By identifying instances of military objects in observed scenes, point cloud deep learning models can unlock new standards of real-time information delivery to warfighters. Although current deep learning training datasets do not include real-world collection occlusions consistent with military applications, this research characterizes SPT model performance by adding occlusions to the DALESObjects dataset via artificial flyby simulations.We find that a baseline model trained on unoccluded data suffers performance degradation on both semantic and instance segmentation tasks when evaluated on occluded data, but that the …

Star-Based Reachability Analysis Of Binary Neural Networks On Continuous Input, Mykhailo Ivashchenko

School of Computing: Dissertations, Theses, and Student Research

Deep Neural Networks (DNNs) have become a popular instrument for solving various real-world problems. DNNs’ sophisticated structure allows them to learn complex representations and features. However, architecture specifics and floating-point number usage result in increased computational operations complexity. For this reason, a more lightweight type of neural networks is widely used when it comes to edge devices, such as microcomputers or microcontrollers – Binary Neural Networks (BNNs). Like other DNNs, BNNs are vulnerable to adversarial attacks; even a small perturbation to the input set may lead to an errant output. Unfortunately, only a few approaches have been proposed for verifying …

Uncovering And Mitigating Spurious Features In Domain Generalization, Saeed Karimi, Hamdi̇ Di̇bekli̇oğlu

Turkish Journal of Electrical Engineering and Computer Sciences

Domain generalization (DG) techniques strive to attain the ability to generalize to an unfamiliar target domain solely based on training data originating from the source domains. Despite the increasing attention given to learning from multiple training domains through the application of various forms of invariance across those domains, the enhancements observed in comparison to ERM are nearly insignificant under specified evaluation rules. In this paper, we demonstrate that the disentanglement of spurious and invariant features is a challenging task in conventional training since ERM simply minimizes the loss and does not exploit invariance among domains. To address this issue, we …

Motion Magnification-Inspired Feature Manipulation For Deepfake Detection, Aydamir Mirzayev, Hamdi Di̇bekli̇oğlu

Turkish Journal of Electrical Engineering and Computer Sciences

Recent advances in deep learning, increased availability of large-scale datasets, and improvement of accelerated graphics processing units facilitated creation of an unprecedented amount of synthetically generated media content with impressive visual quality. Although such technology is used predominantly for entertainment, there is widespread practice of using deepfake technology for malevolent ends. This potential for malicious use necessitates the creation of detection methods capable of reliably distinguishing manipulated video content. In this work we aim to create a learning-based detection method for synthetically generated videos. To this end, we attempt to detect spatiotemporal inconsistencies by leveraging a learning-based magnification-inspired feature manipulation …

Ai And 6g Into The Metaverse: Fundamentals, Challenges And Future Research Trends, Muhammad Zawish, Fayaz Ali Dharejo, Sunder Ali Khowaja, Saleem Raza, Steven Davy, Kapal Dev, Paolo Bellavista

Articles

Since Facebook was renamed Meta, a lot of attention, debate, and exploration have intensified about what the Metaverse is, how it works, and the possible ways to exploit it. It is anticipated that Metaverse will be a continuum of rapidly emerging technologies, usecases, capabilities, and experiences that will make it up for the next evolution of the Internet. Several researchers have already surveyed the literature on artificial intelligence (AI) and wireless communications in realizing the Metaverse. However, due to the rapid emergence and continuous evolution of technologies, there is a need for a comprehensive and in-depth survey of the role …

A Survey On Few-Shot Class-Incremental Learning, Songsong Tian, Lusi Li, Weijun Li, Hang Ran, Xin Ning, Prayag Tiwari

Computer Science Faculty Publications

Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup can easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance. Studying FSCIL helps overcome deep learning model limitations on data volume and acquisition time, while improving practicality and adaptability of machine learning models. This paper provides a comprehensive survey on FSCIL. Unlike previous surveys, we aim to synthesize few-shot learning and incremental …

Enhanced Privacy-Enabled Face Recognition Using Κ-Identity Optimization, Ryan Karl

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

Facial recognition is becoming more and more prevalent in the daily lives of the common person. Law enforcement utilizes facial recognition to find and track suspects. The newest smartphones have the ability to unlock using the user's face. Some door locks utilize facial recognition to allow correct users to enter restricted spaces. The list of applications that use facial recognition will only increase as hardware becomes more cost-effective and more computationally powerful. As this technology becomes more prevalent in our lives, it is important to understand and protect the data provided to these companies. Any data transmitted should be encrypted …

Implementation Of Adas And Autonomy On Unlv Campus, Zillur Rahman

UNLV Theses, Dissertations, Professional Papers, and Capstones

The integration of Advanced Driving Assistance Systems (ADAS) and autonomous driving functionalities into contemporary vehicles has notably surged, driven by the remarkable progress in artificial intelligence (AI). These AI systems, capable of learning from real-world data, now exhibit the capability to perceive their surroundings via a suite of sensors, create optimal routes from source to destination, and execute vehicle control akin to a human driver.

Within the context of this thesis, we undertake a comprehensive exploration of three distinct yet interrelated ADAS and Autonomy projects. Our central objective is the implementation of autonomous driving(AD) technology at UNLV campus, culminating in …

Precision Spraying Using Variable Time Delays And Vision-Based Velocity Estimation, Paolo Rommel Sanchez, Hong Zhang

Henry M. Rowan College of Engineering Departmental Research

Traditionally, precision farm equipment often relies on real-time kinematics and global positioning systems (RTK-GPS) for accurate position and velocity estimates. This approach proved effective and widely adopted in developed regions where RTK-GPS satellite and base station availability and visibility are not limited. However, RTK-GPS signal can be limited in farm areas due to topographic and economic constraints. Thus, this study developed a precision sprayer that estimated the travel velocity locally by tracking the relative motion of plants using a deep-learning-based machine vision system. Sprayer valves were then controlled by variable time delay (VTD) queuing and dynamic filtering. The proposed velocity …

Pymaivar: An Open-Source Python Suit For Audio-Image Representation In Human Action Recognition, Muhammad B. Shaikh, Douglas Chai, Syed M. S. Islam, Naveed Akhtar

Research outputs 2022 to 2026

We present PyMAiVAR, a versatile toolbox that encompasses the generation of image representations for audio data including Wave plots, Spectral Centroids, Spectral Roll Offs, Mel Frequency Cepstral Coefficients (MFCC), MFCC Feature Scaling, and Chromagrams. This wide-ranging toolkit generates rich audio-image representations, playing a pivotal role in reshaping human action recognition. By fully exploiting audio data's latent potential, PyMAiVAR stands as a significant advancement in the field. The package is implemented in Python and can be used across different operating systems.

Novel Approach For Non-Invasive Prediction Of Body Shape And Habitus, Emma Young

Electronic Theses and Dissertations

While marker-based motion capture remains the gold standard in measuring human movement, accuracy is influenced by soft-tissue artifacts, particularly for subjects with high body mass index (BMI) where markers are not placed close to the underlying bone. Obesity influences joint loads and motion patterns, and BMI may not be sufficient to capture the distribution of a subject’s weight or to differentiate differences between subjects. Subjects in need of a joint replacement are more likely to have mobility issues or pain, which prevents exercise. Obesity also increases the likelihood of needing a total joint replacement. Accurate movement data for subjects with …

Efficient Scopeformer: Towards Scalable And Rich Feature Extraction For Intracranial Hemorrhage Detection Using Hybrid Convolution And Vision Transformer Networks, Yassine Barhoumi

Theses and Dissertations

The field of medical imaging has seen significant advancements through the use of artificial intelligence (AI) techniques. The success of deep learning models in this area has led to the need for further research. This study aims to explore the use of various deep learning algorithms and emerging modeling techniques to improve training paradigms in medical imaging. Convolutional neural networks (CNNs) are the go-to architecture for computer vision problems, but they have limitations in mapping long-term dependencies within images. To address these limitations, the study explores the use of techniques such as global average pooling and self-attention mechanisms. Additionally, the …

Detection, Tracking, And Classification Of Aircraft And Birds From Multirotor Small Unmanned Aircraft Systems, Chester Valentine Dolph

Electrical & Computer Engineering Theses & Dissertations

The ability for small Unmanned Aircraft Systems (sUAS) to safely operate beyond visual line of sight (BVLOS) is of great interest to governments, businesses, and scientific research. One critical element for sUAS to operate BVLOS is the capability to avoid other air traffic. While many aircraft will be cooperative and broadcast their locations using Automatic Dependent Surveillance Broadcast (ADS-B), it is expected that many aircraft will remain non-cooperative – meaning they do not communicate position or flight plan to other aircraft. Avoiding mid-air collisions with non-cooperative aircraft is a critical limitation to widespread sUAS flying BVLOS. Examples of non-cooperative traffic …

Exploratory Analysis Of Machine Learning For Images: Methods And Applications, Meenu Ajith

Electrical and Computer Engineering ETDs

This research focuses on implementing four different applications of machine learning on images. The various categories of digital images considered for these applications are grayscale, RGB, and infra-red images. The first framework uses an unsupervised learning strategy for detecting fire and smoke from an infra-red image dataset. This problem was solved using a classical machine learning algorithm since the dataset was small and unlabeled. Next, a semi-supervised deep learning model was used for facial expression recognition. Here we detect emotions from a moderately large dataset containing labeled and unlabeled grayscale images. The third application focused on single image superresolution, which …

Combinatorial Cnn Meta-Structures In Deep Learning Applications, Aswathy Rajendra Kurup

Electrical and Computer Engineering ETDs

The study aims in applying combinatorial structures motivated from the basic CNN in various applications. Convolutional neural networks (CNNs) have grown to be very popular in the field of deep learning. The ability of such networks to learn both Spatial and temporal characteristics in the data have helped in deploying them in various fields. Through this research we explore different kinds of CNN-derived architectures and how these structures can be trained and setup in combinatorial environment to solve problems in deep learning applications. First, we introduce the basic idea of a deep learning meta-structures which is used in the application …

Applied Deep Learning: Case Studies In Computer Vision And Natural Language Processing, Md Reshad Ul Hoque

Electrical & Computer Engineering Theses & Dissertations

Deep learning has proved to be successful for many computer vision and natural language processing applications. In this dissertation, three studies have been conducted to show the efficacy of deep learning models for computer vision and natural language processing. In the first study, an efficient deep learning model was proposed for seagrass scar detection in multispectral images which produced robust, accurate scars mappings. In the second study, an arithmetic deep learning model was developed to fuse multi-spectral images collected at different times with different resolutions to generate high-resolution images for downstream tasks including change detection, object detection, and land cover …

Computer Aided Diagnosis System For Breast Cancer Using Deep Learning., Asma Baccouche

Electronic Theses and Dissertations

The recent rise of big data technology surrounding the electronic systems and developed toolkits gave birth to new promises for Artificial Intelligence (AI). With the continuous use of data-centric systems and machines in our lives, such as social media, surveys, emails, reports, etc., there is no doubt that data has gained the center of attention by scientists and motivated them to provide more decision-making and operational support systems across multiple domains. With the recent breakthroughs in artificial intelligence, the use of machine learning and deep learning models have achieved remarkable advances in computer vision, ecommerce, cybersecurity, and healthcare. Particularly, numerous …

Automatic Testing Of Organic Strain Gauge Tactile Sensors., Brian P. Goulet

Electronic Theses and Dissertations

Human-Robot Interaction is a developing field of science, that is posed to augment everything we do in life. Skin sensors that can detect touch, temperature, distance, and other physical interaction parameters at the human-robot interface are very important to enhancing the collaboration between humans and machines. As such, these sensors must be efficiently tested and characterized to give accurate feedback from the sensor to the robot. The objective of this work is to create a diversified software testing suite that removes as much human intervention as possible. The tests and methodology discussed here provide multiple realistic scenarios that the sensors …