WHDL - 00010933

Detecting Burn Severity in Post Wildland Fire Imagery through k-Dimensional Trees and k-Nearest Neighbors Machine Learning Algorithms

Llewellyn B. Johnston

Description / Abstract

Submitted to the Department of Mathematics and Computer Science in partial fulfillment of the requirements for the degree of Bachelor of Science

This is a system for analyzing post-fire imagery to determine wildland fire severity. The system is written for the FireMAP project. It is written in C++ and C using the open source image processing library OpenCV. The system primarily is comprised of a k-Dimensional binary tree, for storing training data, along with a k-Nearest Neighbors algorithm to quickly classify imagery based on the training data. The algorithm utilizes parallel processing to fully utilize the CPU greatly increase the classification speed. Most of the system is written in-house to provide a unique and modifiable algorithm implementation for use by the FireMAP project. This effort is important to the FireMAP project because it provides the ability to automate the severity determination process that would previously take weeks for a Burn Area Emergency Response (BAER) team to do now takes several minutes or several seconds. So, the solution provided by this project is cheaper, faster, requires less manpower, and is overall a safer approach to the issue of burn severity analysis. Several areas of research and work were not included in this project and will require further attention. These areas are object-based analysis of imagery, further optimization and training for the classifier, more robust system testing, and full integration of the classifier into the full FireMAP project.

Detecting Burn Severity in Post Wildland Fire Imagery through k-Dimensional Trees and k-Nearest Neighbors Machine Learning Algorithms

Description / Abstract

Download this Resource

Download Free from WHDL

Collections With This Resource

NNU Computer Science Theses

Related Resources

A History of the Town and College of Bethany, Oklahoma

A Mobile Application for John Wesley's Explanatory Notes on the Bible

A Mobile Application for Northwest Nazarene University’s Complex College Community

A Modification to Meal Ticket’s Global Trade Item Number Validation to Use GS1 Data

A Novel Tool for the Identification of Plasmid Backbone Gene Labels

Addressing Data Integrity for Individual Profiles and Building Data Flow Models at NNU

An Exegetical Study of Peter's Understanding on Christian Suffering in 1 Peter 4:12-19

Analysis of Spectral Reflectance and Separability of Vegetation for FireMAP

Android Application for Completing Medical Forms

Autism Spectrum Disorder: Unique Challenges and Specific Demands

Autonomous Drone Project

Bethany Nazarene College Yearbooks

Classification of Aerial Imagery using a Relational Convolutional Neural Network

Classifying Wildland Fire Severity on Landsat Imagery Using Machine Learning Trained by Hyperspatial Imagery

Counseling Department Scheduling and Accreditation Tool

Creating a Drive Log Tool for Analysis

Creating a Mobile Application About Costa Rican Frogs and Toads Using React Native

Creating a Website with Laravel Framework for Northwest Nazarene University Students to Buy and Sell Books to Each Other

Creating and Configuring a Continuous Integration Machine for a Software Package

Creation of a Web-Based Audio Recorder Utilizing a USB Foot Pedal and External Microphone

Creation of MakerSat Flight Code

Current State Mapping and Duplicate Account Resolution

Cyclops: An Open Source Educational Tool for Modeling Digital Logic

Darda 1950

Darda 1974

About the Authors

Llewellyn B. Johnston