A Novel Large Vision Foundation Model (LVFM)-based Approach for Generating High-Resolution Canopy Height Maps in Plantations for Precision Forestry Management

2025-06-25

AI Summary

To address the high computational cost and low accuracy of generating high-resolution canopy height models (CHMs), this study proposes a low-cost RGB-image-based tree height inversion method leveraging large vision foundation models (LVFMs). We innovatively introduce a self-supervised feature enhancement module to strengthen spatial detail preservation and cross-regional generalization. Our end-to-end framework takes 1-m-resolution Google Earth RGB imagery as input to generate CHMs directly. Evaluated in the Fangshan experimental area, the method achieves a mean absolute error of 0.09 m, root mean square error of 0.24 m, and a Pearson correlation coefficient of 0.78 between predicted and field-measured heights; individual tree detection success exceeds 90%, biomass estimation is accurate, and performance remains robust in unseen regions. The approach significantly outperforms conventional CNNs, offering an efficient, scalable solution for carbon sink monitoring (e.g., CCER projects) and precision forestry management.

Technology Category

• Computer Vision: Large Vision Models
• Machine Learning: Ensemble Methods
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Accurate, cost-effective monitoring of plantation aboveground biomass (AGB) is crucial for supporting local livelihoods and carbon sequestration initiatives like the China Certified Emission Reduction (CCER) program. High-resolution canopy height maps (CHMs) are essential for this, but standard lidar-based methods are expensive. While deep learning with RGB imagery offers an alternative, accurately extracting canopy height features remains challenging. To address this, we developed a novel model for high-resolution CHM generation using a Large Vision Foundation Model (LVFM). Our model integrates a feature extractor, a self-supervised feature enhancement module to preserve spatial details, and a height estimator. Tested in Beijing's Fangshan District using 1-meter Google Earth imagery, our model outperformed existing methods, including conventional CNNs. It achieved a mean absolute error of 0.09 m, a root mean square error of 0.24 m, and a correlation of 0.78 against lidar-based CHMs. The resulting CHMs enabled over 90% success in individual tree detection, high accuracy in AGB estimation, and effective tracking of plantation growth, demonstrating strong generalization to non-training areas. This approach presents a promising, scalable tool for evaluating carbon sequestration in both plantations and natural forests.

Problem

• Generates high-resolution canopy height maps for plantations
• Reduces cost compared to standard lidar-based methods
• Improves accuracy in aboveground biomass monitoring

Innovation

• LVFM-based high-resolution canopy height mapping
• Self-supervised feature enhancement for spatial details
• Integration of feature extractor and height estimator