Date of Award

1-8-2025

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Information Science

First Advisor

Xiaowei Xu

Abstract

This masters thesis proposes an innovative approach to satellite image segmentation by focusing on the detection and mapping of walking, hiking, and biking trails. The motivation behind this project comes from the underexplored area in segmentation techniques for trail identification and offers potential benefits for urban planning, environmental monitoring, and public health. The problem statement addresses the need for a model that can differentiate between various trail types and other natural or man-made elements. The project aims for efficiency and scalability in processing satellite imagery across different compute hardware. The work details several stages: researching existing segmentation techniques, specifically road and street identification, collecting and processing a set of satellite images of trails, selecting and training several state-of-the-art convolutional neural network models for semantic segmentation, evaluating the models using standard and specialized metrics, and real-world testing on an area familiar to the author. Through these stages, the project aims to advance the field of satellite image segmentation by introducing a fine-tuned model that can accurately identify and map trails. It can also contribute to areas of urban planning, environmental conservation, and public wellness. The project hopes to innovate in the technical aspects of machine learning and computer vision and also to have an impact on the maintenance and utilization of trails to help foster a closer connection between communities and their natural surroundings.

Download

Share

COinS