Abstract

Autonomous navigation is a critical component of autonomous vehicles. This requires precise object detection and real-time decisions. This project explores four state-of-the art object detection algorithms: Faster-RCNN, YOLO, RetinaNet, and SSD. Models were trained on their respective datasets. Implemented using TensorFlow, PyTorch, and OpenCV, assessing their mean average precision score. The results offer insights into optimizing object detection by applying structural changes and data augmentation techniques. This study contributes to the development of efficient AI-driven perception systems for self driving applications.

Advisor

As'ad, Asa'd

Department

Computer Science

Publication Date

2025

Degree Granted

Bachelor of Arts

Document Type

Senior Independent Study Thesis

Share

COinS
 

© Copyright 2025 Nathan Ferrence