Individual Tree Species Classification Using Pseudo Tree Crown (PTC) on Coniferous Forests
Preprint
- 30 July 2025
- preprint
- Published by MDPI AG in Preprints.org
Abstract
Coniferous forests in Canada play a vital role in carbon sequestration, wildlife conservation, climate change mitigation, and long-term sustainability. Traditional methods for classifying and segmenting coniferous trees have primarily relied on the direct use of spectral or LiDAR-based data. In 2024, we introduced a novel data representation method, Pseudo Tree Crown (PTC), which provides a pseudo-3D pixel-value view that enhances the informational richness of images and significantly improves classification performance. While our original implementation was successfully tested on urban and deciduous trees, this study extends the application of PTC to Canadian conifer species, including Jack Pine, Douglas Fir, Spruce, and Aspen. We address key challenges such as snow-covered backgrounds and evaluate the impact of training dataset size on classification results. Classification was performed using Random Forest, PyTorch(ResNet50), and YOLO versions v10, v11, and v12. The results demonstrate that PTC can substantially improve individual tree classification accuracy by up to 13% reaching the high 90% range.Keywords
All Related Versions
This publication has 36 references indexed in Scilit:
- Semi-supervised multi-class tree crown delineation using aerial multispectral imagery and lidar dataISPRS Journal of Photogrammetry and Remote Sensing, 2024
- Application of multi-temporal satellite imagery for urban tree species identificationUrban Forestry & Urban Greening, 2024
- Remote sensing based forest cover classification using machine learningScientific Reports, 2024
- Hybrid fuzzy support vector machine approach for Coconut tree classification using image measurementEngineering Applications of Artificial Intelligence, 2023
- Temperature-induced growing season drought threatens survival and height growth of white spruce in southern Ontario, CanadaForest Ecology and Management, 2019
- Deep Residual Learning for Image Recognition2016
- Forests are more than sticks of carbonNature, 2014
- Random ForestsMachine Learning, 2001
- Support-vector networksMachine Learning, 1995
- A Catalogue of Potential Spatial Discriminators for High Spatial Resolution Digital Images of Individual CrownsCanadian Journal of Remote Sensing, 1995