Author ORCID Identifier

https://orcid.org/0009-0003-1262-171X

Semester

Spring

Date of Graduation

2025

Document Type

Dissertation

Degree Type

PhD

College

Statler College of Engineering and Mineral Resources

Department

Mining Engineering

Committee Chair

Deniz Tuncay,

Committee Co-Chair

Qingqing Huang

Committee Member

Qingqing Huang

Committee Member

Amy McBrayer

Committee Member

Deniz Talan

Committee Member

Thomas Barczak

Abstract

Underground mining environments present challenges in accurately identifying geological formations and potential hazards due to poor lighting conditions and confined spaces. Traditional imaging methods often fall short, making it difficult to detect critical geological features such as limestone, shale, and other rock formations. This research addresses these challenges by integrating camera imagery with Light Detection and Ranging (LiDAR) data to improve geological formation detection in poorly lit mining settings.

LiDAR, with its ability to generate high-resolution three-dimensional models in low-light or dark conditions, offers a promising solution to these limitations. By combining LiDAR’s precise 3D models with camera imagery, the study applies advanced computer vision techniques, including deep learning-based semantic segmentation, to analyze and interpret the integrated data. Additionally, the research examines the effect of lighting conditions on the quality of visual data and its impact on geological feature recognition. A comprehensive dataset of geological images, captured under various lighting conditions, is developed to train deep learning models for improved detection.

This research aims to enhance the identification of geological features, leading to more accurate hazard assessments, better rock mass characterization, and ultimately, safer mining practices. The integration of LiDAR and computer vision techniques holds the potential to improve geological assessments, contributing to the prevention of roof fall accidents and advancing the application of technology in underground mining operations.

Share

COinS