Author Identifier

Christopher Cameron Napier: https://orcid.org/0000-0002-5017-9024

Date of Award

2024

Document Type

Thesis

Publisher

Edith Cowan University

Degree Name

Master of Computing and Security by Research

School

School of Science

First Supervisor

Leisa Armstrong

Second Supervisor

David Cook

Third Supervisor

Dean Diepeveen

Abstract

This research considers a system for the recognition of real plant parts through image analysis based upon synthetic plant modelling. It aims to use data pipelines and synthetic datasets to define recognizable features that assist in the efficient analysis of real plants and plant images. This research asks about the efficacy of L-systems in accurately simulating wheat crop characteristics. It specifically focusses on readable, understandable, accurate, and complex L-system algorithms. The research examines wheat crops in terms of phenotypes and examines the accuracy of a dataset in support of real image annotation. The methodology used was experimental in nature and based around the generation of virtual plants and plant images to generate realistic synthetic plant 3D models. This research created a novel L-system framework. This generated an algorithmically derived synthetic dataset (L-NAP) which could be used to recognize and manage features for the precise consideration of wheat crop yield estimations. This study demonstrates the value of L-systems to create a viable dataset using less aggregated data, that retains accuracy, stability, complexity, and applied usability.

DOI

10.25958/qpbn-q159

Download

Share

 
COinS