WHU-STree: A Multi-modal Benchmark Dataset for Street Tree Inventory

Abstract

Street trees are vital to urban livability, providing ecological and social benefits. Establishing a detailed, accurate, and dynamically updated street tree inventory has become essential for optimizing these multifunctional assets within space-constrained urban environments. Given that traditional field surveys are time-consuming and labor-intensive, automated surveys utilizing Mobile Mapping Systems (MMS) offer a more efficient solution. However, existing MMS-acquired tree datasets are limited by small-scale scene, limited annotation, or single modality, restricting their utility for comprehensive analysis. To address these limitations, we introduce WHU-STree, a cross-city, richly annotated, and multi-modal urban street tree dataset. Collected across two distinct cities, WHU-STree integrates synchronized point clouds and high-resolution images, encompassing 21,007 annotated tree instances across 50 species and 2 morphological parameters. Leveraging the unique characteristics, WHU-STree concurrently supports over 10 tasks related to street tree inventory. We benchmark representative baselines for two key tasks--tree species classification and individual tree segmentation. Extensive experiments and in-depth analysis demonstrate the significant potential of multi-modal data fusion and underscore cross-domain applicability as a critical prerequisite for practical algorithm deployment. In particular, we identify key challenges and outline potential future works for fully exploiting WHU-STree, encompassing multi-modal fusion, multi-task collaboration, cross-domain generalization, spatial pattern learning, and Multi-modal Large Language Model for street tree asset management. The WHU-STree dataset is accessible at: https://github.com/WHU-USI3DV/WHU-STree.

Plant phenotyping relevance

樹木の個体セグメンテーションと形態パラメータを含むマルチモーダルデータセットを構築し、ベンチマークする研究であり、植物個体の状態・形態抽出手法が中心である。

Code and data availability

The paper's core asset is the WHU-STree multi-modal street tree dataset (point clouds, panoramic images, 21,007 annotated tree instances, 50 species, height/DBH), which the authors state is publicly accessible via their GitHub organization WHU-USI3DV. The Zenodo DOIs in the reference list belong to cited prior datasets