Is this project an undergraduate, graduate, or faculty project?

Graduate

Project Type

group

Campus

Daytona Beach

Authors' Class Standing

Arjun Nambiar, Graduate student Sang-A Lee, Graduate student Diego Espino, Graduate student Will Obot Jr., Graduate student Jarrett Usui, Graduate student Ethan Encarnacion, Graduate student Jacob Kline, Graduate student

Lead Presenter's Name

Arjun Nambiar

Lead Presenter's College

DB College of Engineering

Faculty Mentor Name

Dr. Ryan Wallace

Abstract

The increasing complexity of public safety operations in urban and high-density environments necessitates intelligent, mobile surveillance systems capable of real-time threat identification and situational awareness. Traditional monitoring approaches, such as fixed CCTV systems and manual observation, are often limited by coverage, scalability, and response latency in complex environments or large-scale events. This project addresses these challenges through the development of a computer vision-enabled Uncrewed Aerial System (UAS) designed for crowd monitoring and firearm detection. The primary objective is to design and validate a modular, Artificial Intelligence (AI)-Machine Learning (ML)-driven model capable of identifying firearms within dynamic environments while supporting real-time decision-making for law enforcement and emergency response agencies. The system leverages a You Only Look Once (YOLO)-based object detection model trained on curated firearm datasets, with initial focus on three-class firearm detection. Ground-based validation was conducted using image inference and live webcam testing to simulate operational conditions. Preliminary results demonstrate a high detection rate with moderate recall, confirming the feasibility of integrating real-time computer vision into UAS platforms. The project is developed through an interdisciplinary collaboration integrating engineering, aviation, and domain-specific expertise, ensuring both technical rigor and operational relevance. Future work includes multi-class weapon detection, expansion to law enforcement- civilian classification, and vehicle identification, through deployment on onboard computing platforms such as NVIDIA Jetson systems. This research contributes to advancing AI-ML-integrated UAS technologies, offering scalable Drone as First Responder (DFR) solutions for enhanced public safety, faster response times, and improved situational awareness in both controlled and real-world environments.

Did this research project receive funding support (Spark, SURF, Research Abroad, Student Internal Grants, Collaborative, Climbing, or Ignite Grants) from the Office of Undergraduate Research?

No

Share

COinS
 

Crowd Monitoring and Firearm Detection UAS

The increasing complexity of public safety operations in urban and high-density environments necessitates intelligent, mobile surveillance systems capable of real-time threat identification and situational awareness. Traditional monitoring approaches, such as fixed CCTV systems and manual observation, are often limited by coverage, scalability, and response latency in complex environments or large-scale events. This project addresses these challenges through the development of a computer vision-enabled Uncrewed Aerial System (UAS) designed for crowd monitoring and firearm detection. The primary objective is to design and validate a modular, Artificial Intelligence (AI)-Machine Learning (ML)-driven model capable of identifying firearms within dynamic environments while supporting real-time decision-making for law enforcement and emergency response agencies. The system leverages a You Only Look Once (YOLO)-based object detection model trained on curated firearm datasets, with initial focus on three-class firearm detection. Ground-based validation was conducted using image inference and live webcam testing to simulate operational conditions. Preliminary results demonstrate a high detection rate with moderate recall, confirming the feasibility of integrating real-time computer vision into UAS platforms. The project is developed through an interdisciplinary collaboration integrating engineering, aviation, and domain-specific expertise, ensuring both technical rigor and operational relevance. Future work includes multi-class weapon detection, expansion to law enforcement- civilian classification, and vehicle identification, through deployment on onboard computing platforms such as NVIDIA Jetson systems. This research contributes to advancing AI-ML-integrated UAS technologies, offering scalable Drone as First Responder (DFR) solutions for enhanced public safety, faster response times, and improved situational awareness in both controlled and real-world environments.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.