First Advisor

D. Kevin McGrath

Date of Award

Spring 6-2026

Document Type

Thesis

Degree Name

Bachelor of Science (B.S.) in Computer Science and University Honors

Department

Computer Science

Language

English

Subjects

Computer Vision, Embedded Systems, Agile Project Management, Cross-Functional Team Dynamics

Abstract

This thesis details our design, implementation, and collaborative development of an intelligent vehicle logging system built on a Raspberry Pi 5. Unlike standard consumer dash cams that act as closed "black boxes," our system uses a dual-camera stereo vision setup integrated with centimeter-level accuracy. While we successfully built a functional Proof of Concept capable of event-triggered recording, dual-monitor visualization, and smart detection and recognition, this paper focuses on our engineering journey and the real-world challenges we faced. Using an Agile framework, we split into three specialized sub-teams to handle hardware, database, and interface design in parallel. This structure created unique bottlenecks, from aligning real-time AI data with precise geographic streams under tight storage limits, to managing critical hardware shipping delays. Ultimately, we provide an honest review of how we adapted our communication, overcame these technical and human setbacks, and successfully delivered a complex, integrated edge-computing platform.

Download

Share

COinS