Date of Award

8-2024

Document Type

Project

Degree Name

Master of Science in Computer Science

Department

School of Computer Science and Engineering

First Reader/Committee Chair

Bilal Khan

Abstract

In this research, we advance the domain of public safety by developing a machine learning model that utilizes the YOLO v8 architecture for real-time detection of firearms in video streams. A diverse and extensive dataset, capturing a range of firearms in varying lighting and backgrounds, was meticulously assembled and preprocessed to enhance the model's adaptability to real-world scenarios. Leveraging the YOLO v8 framework, known for its real-time object detection accuracy, the model was fine-tuned to accurately identify firearms across different shapes and orientations.

The training phase capitalized on GPU computing and transfer learning to expedite the learning process while preserving a high degree of precision, recall, and F1-score in the model’s performance metrics. Through iterative optimization post-evaluation, the model's detection capabilities were further refined.

Deployed in an Online Mode, the model operates on a cloud-based platform, utilizing the scalability and computational prowess of Google Cloud Platform (GCP). A dedicated application, designed with Flutter, delivers a consistent user interface that streamlines interaction, complemented by Google Cloud Functions that manage data communication seamlessly.

This project demonstrates the considerable promise of the YOLO v8 architecture for real-time surveillance and public safety applications. The outcomes are promising, and future endeavors will aim to broaden the validation with more extensive video datasets.

Share

COinS