[论文解读] FOR-instance: a UAV laser scanning benchmark dataset for semantic and instance segmentation of individual trees

Stefano Puliti, Grant D. Pearse+5 more|arXiv (Cornell University)|Sep 3, 2023

Remote Sensing and LiDAR Applications被引用 26

一句话总结

FOR-instance 数据集提供五个经过筛选的无人机LiDAR集合，带有手动注释，用于对单个树木的语义和实例分割的训练/测试基准，并包括用于3D森林分析的DBH数据。

ABSTRACT

The FOR-instance dataset (available at https://doi.org/10.5281/zenodo.8287792) addresses the challenge of accurate individual tree segmentation from laser scanning data, crucial for understanding forest ecosystems and sustainable management. Despite the growing need for detailed tree data, automating segmentation and tracking scientific progress remains difficult. Existing methodologies often overfit small datasets and lack comparability, limiting their applicability. Amid the progress triggered by the emergence of deep learning methodologies, standardized benchmarking assumes paramount importance in these research domains. This data paper introduces a benchmarking dataset for dense airborne laser scanning data, aimed at advancing instance and semantic segmentation techniques and promoting progress in 3D forest scene segmentation. The FOR-instance dataset comprises five curated and ML-ready UAV-based laser scanning data collections from diverse global locations, representing various forest types. The laser scanning data were manually annotated into individual trees (instances) and different semantic classes (e.g. stem, woody branches, live branches, terrain, low vegetation). The dataset is divided into development and test subsets, enabling method advancement and evaluation, with specific guidelines for utilization. It supports instance and semantic segmentation, offering adaptability to deep learning frameworks and diverse segmentation strategies, while the inclusion of diameter at breast height data expands its utility to the measurement of a classic tree variable. In conclusion, the FOR-instance dataset contributes to filling a gap in the 3D forest research, enhancing the development and benchmarking of segmentation algorithms for dense airborne laser scanning data.

研究动机与目标

• 满足从激光扫描数据中进行准确的单棵树分割的需求。
• 提供一个标准化、适用于ML的基准，以推动密集3D森林场景中的实例与语义分割。
• 提供来自全球不同地区的多样化基于无人机的LiDAR集合，以支持可泛化的基准测试。
• 启用带有开发集和测试集的评估协议以及使用的实践指南。
• 包含胸高直径(DBH)数据，以扩展对传统树木测量的应用。

提出的方法

• 从多样的森林类型中整理五个基于无人机的激光扫描数据集。
• 将数据手动注释为单棵树的实例和语义类别（例如：树干、木质枝干、活枝、地形、低层植被）。
• 将数据集分为开发集和测试集，并附带使用指南。
• 确保数据集可适配深度学习框架及各种分割策略（语义与实例）。
• 提供ML就绪数据以促进基准测试和3D森林场景分割的进展。

实验结果

研究问题

• RQ1 RQ1 无人机基LiDAR数据能否被有效标注以实现对单棵树的可靠实例分割？
• RQ2 RQ2 FOR-instance数据集如何支持在多样化森林类型上对语义和实例分割的评估？
• RQ3 RQ3 能否将深度学习框架有效应用于本数据集，以实现密集3D森林场景分割？
• RQ4 RQ4 注释DBH数据如何提升树木级别分析和分割的实用性？

主要发现

• FOR-instance 数据集由五个经过筛选的基于无人机的激光扫描集合组成，适用于ML驱动的分割。
• 数据手动注释为每棵树的实例和语义类别，如树干、木质枝干、活枝、地形和低层植被。
• 数据集分为开发子集和测试子集，以促进方法进步和客观评估。
• 它被设计为可适应各种深度学习分割策略和框架。
• 包含 DBH 数据，扩展数据集在传统树木测量与分割任务的实用性。