Automatic Extraction of Dendrometric Variables Using Multi-Platform LiDAR Data

• Grant number: 25/00683-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: March 01, 2025
• End date: February 28, 2026
• Field of knowledge: Physical Sciences and Mathematics - Geosciences - Geodesy
• Principal Investigator: Renato César dos Santos
• Grantee: Maria Eduarda Teixeira da Silva Ruy
• Host Institution: Faculdade de Ciências e Tecnologia (FCT). Universidade Estadual Paulista (UNESP). Campus de Presidente Prudente. Presidente Prudente , SP, Brazil
• Associated research grant: 21/06029-7 - High resolution remote sensing for digital agriculture, AP.TEM

Abstract

Dendrometry plays a crucial role in maintaining the health and sustainability of forests. Traditionally, the collection of dendrometric variables is conducted manually in the field, requiring significant effort and time. In this context, LiDAR (Light Detection and Ranging) technology emerges as an efficient alternative, capable of capturing high-quality geometric 3D point clouds, enabling the development of automatic and semi-automatic strategies for analyzing forest structure. Despite the numerous methods developed, most have been tested in Northern Hemisphere countries, where environmental conditions and complexities differ significantly from those in Brazil. Thus, this project aims to evaluate the application of an automatic tree detection method developed by the research group in different types of Brazilian forests (urban, plantation, and natural) using LiDAR data collected from multiple platforms. Unlike machine learning-based approaches, this method does not require training samples, and thresholds are defined intuitively. The project will expand testing to more diverse scenarios, assessing the robustness and limitations of the method. Additionally, the project includes developing an automatic strategy for estimating dendrometric variables (location, diameter at breast height (DBH), and height), aiming to overcome limitations in modeling cross-sections of non-circular trunks. As an expected outcome, the project seeks to foster the broader adoption of LiDAR technology in Brazil, taking into account its environmental specificities and providing support for forest conservation and sustainable management. Ultimately, the goal is to contribute to the national technical and scientific advancement in the use of LiDAR sensors, promoting their large-scale application.