UruDendro4: A Benchmark Dataset for Automatic Tree-Ring Detection in Cross-Section Images of Pinus taeda L

2025-11-25

AI Summary

Manual tree-ring measurement is time-consuming, error-prone, and hindered by scarce high-quality annotated data and lack of automated algorithms for 3D modeling. Method: We introduce UruDendro4—the first benchmark dataset for 3D modeling of loblolly pine cross-sections—comprising 102 multi-height cross-sectional images with pixel-accurate ring-boundary annotations. We further propose DeepCS-TRD, a deep learning model enabling precise ring segmentation and volumetric growth reconstruction. Results: On UruDendro4, DeepCS-TRD achieves 0.838 mean precision, 0.782 mean recall, and 0.084 Adapted Rand Error—substantially outperforming baseline methods. Ablation studies confirm that multi-height sampling critically enhances model generalization. This work establishes a foundational dataset and a novel technical paradigm for automated dendrochronological analysis and 3D tree growth modeling.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Ensemble Methods
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Web Mining and Content Analysis: Models for Web evolution
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Tree-ring growth represents the annual wood increment for a tree, and quantifying it allows researchers to assess which silvicultural practices are best suited for each species. Manual measurement of this growth is time-consuming and often imprecise, as it is typically performed along 4 to 8 radial directions on a cross-sectional disc. In recent years, automated algorithms and datasets have emerged to enhance accuracy and automate the delineation of annual rings in cross-sectional images. To address the scarcity of wood cross-section data, we introduce the UruDendro4 dataset, a collection of 102 image samples of Pinus taeda L., each manually annotated with annual growth rings. Unlike existing public datasets, UruDendro4 includes samples extracted at multiple heights along the stem, allowing for the volumetric modeling of annual growth using manually delineated rings. This dataset (images and annotations) allows the development of volumetric models for annual wood estimation based on cross-sectional imagery. Additionally, we provide a performance baseline for automatic ring detection on this dataset using state-of-the-art methods. The highest performance was achieved by the DeepCS-TRD method, with a mean Average Precision of 0.838, a mean Average Recall of 0.782, and an Adapted Rand Error score of 0.084. A series of ablation experiments were conducted to empirically validate the final parameter configuration. Furthermore, we empirically demonstrate that training a learning model including this dataset improves the model's generalization in the tree-ring detection task.

Problem

• Manual tree-ring measurement is time-consuming and often imprecise
• There is scarcity of annotated wood cross-section image datasets
• Automated algorithms are needed for accurate annual ring detection

Innovation

• Introduces UruDendro4 benchmark dataset for tree rings
• Provides baseline performance using DeepCS-TRD method
• Enables volumetric modeling through multi-height samples