[论文解读] Benchmarking tree species classification from proximally-sensed laser scanning data: introducing the FOR-species20K dataset

Rehush, Nataliia|arXiv (Cornell University)|Aug 12, 2024

Remote Sensing and LiDAR Applications被引用 5

一句话总结

介绍了FOR-species20K基准数据集，包含来自33个物种的2万多树木点云，支持用于从TLS、MLS、ULS数据进行物种分类的DL模型基准测试。

ABSTRACT

Proximally-sensed laser scanning offers significant potential for automated forest data capture, but challenges remain in automatically identifying tree species without additional ground data. Deep learning (DL) shows promise for automation, yet progress is slowed by the lack of large, diverse, openly available labeled datasets of single tree point clouds. This has impacted the robustness of DL models and the ability to establish best practices for species classification. To overcome these challenges, the FOR-species20K benchmark dataset was created, comprising over 20,000 tree point clouds from 33 species, captured using terrestrial (TLS), mobile (MLS), and drone laser scanning (ULS) across various European forests, with some data from other regions. This dataset enables the benchmarking of DL models for tree species classification, including both point cloud-based (PointNet++, MinkNet, MLP-Mixer, DGCNNs) and multi-view image-based methods (SimpleView, DetailView, YOLOv5). 2D image-based models generally performed better (average OA = 0.77) than 3D point cloud-based models (average OA = 0.72), with consistent results across different scanning platforms and sensors. The top model, DetailView, was particularly robust, handling data imbalances well and generalizing effectively across tree sizes. The FOR-species20K dataset, available at https://zenodo.org/records/13255198, is a key resource for developing and benchmarking DL models for tree species classification using laser scanning data, providing a foundation for future advancements in the field.

研究动机与目标

• 以无需大量地面实况数据的前提，推动基于近感激光扫描数据的自动树种分类。
• 提供一个大型、多样化、公开可用的带标签的单树木点云数据集，用于鲁棒DL基准测试。
• 实现跨平台和跨传感器的DL模型在物种分类任务上的评估。
• 评估2D图像基础和3D点云基础的DL方法在现实世界的TLS、MLS和ULS数据上的表现。

提出的方法

• 汇编并标注来自33个物种的2万多树木点云，这些数据来自欧洲森林的 terrestrial TLS、mobile MLS、drone ULS。
• 评估DL模型分两大类：点云基础（PointNet++, MinkNet, MLP-Mixer, DGCNNs）和多视图图像基础（SimpleView, DetailView, YOLOv5）。
• 使用总体准确度（OA）作为指标，比较2D图像基础与3D点云基础方法的性能。
• 分析数据不平衡的鲁棒性以及在不同树木大小上的泛化性，特别是对Top-performing DetailView模型。

实验结果

研究问题

• RQ1 能否在FOR-species20K上训练的DL模型在跨多传感器和多森林的 proximally-sensed laser scanning 数据上可靠地对树种进行分类？
• RQ2 2D图像基础方法在准确性和鲁棒性方面与3D点云基础方法在树种分类上有何比较？
• RQ3 哪些因素（传感器类型、物种不平衡、树木大小）对模型性能影响最大？
• RQ4 DetailView模型是否对数据不平衡具有特别鲁棒性，并在不同树木大小上泛化良好？
• RQ5 FOR-species20K在标准化树种分类任务基准测试方面的总体潜力如何？

主要发现

• 2D图像基础模型的平均准确率（OA 0.77）高于3D点云基础模型（OA 0.72）。
• DetailView模型成为最佳表现者并对数据不平衡显示鲁棒性。
• 在探测平台和传感器之间的表现一致，表明跨平台的泛化能力。
• FOR-species20K数据集使得对点云基础和多视图图像基础DL方法的基准测试成为可能。
• 数据集为未来在从近感知激光扫描数据进行树种分类方面的进步奠定基础。