[论文解读] TreeLoc++: Robust 6-DoF LiDAR Localization in Forests with a Compact Digital Forest Inventory

Minwoo Jung, Dongjae Lee+4 more|arXiv (Cornell University)|Mar 4, 2026

Remote Sensing and LiDAR Applications被引用 0

一句话总结

TreeLoc++ 通过紧凑的数字森林目录（DFIs）与两阶段检索+基于几何的细化，在森林中实现鲁棒的6-DoF LiDAR 定位，配合轻量化地图数据达到厘米级位姿精度。

ABSTRACT

Reliable localization is essential for sustainable forest management, as it allows robots or sensor systems to revisit and monitor the status of individual trees over long periods. In modern forestry, this management is structured around Digital Forest Inventories (DFIs), which encode stems using compact geometric attributes rather than raw data. Despite their central role, DFIs have been overlooked in localization research, and most methods still rely on dense gigabyte-sized point clouds that are costly to store and maintain. To improve upon this, we propose TreeLoc++, a global localization framework that operates directly on DFIs as a discriminative representation, eliminating the need to use the raw point clouds. TreeLoc++ reduces false matches in structurally ambiguous forests and improves the reliability of full 6-DoF pose estimation. It augments coarse retrieval with a pairwise distance histogram that encodes local tree-layout context, subsequently refining candidates via DBH-based filtering and yaw-consistent inlier selection to further reduce mismatches. Furthermore, a constrained optimization leveraging tree geometry jointly estimates roll, pitch, and height, enhancing pose stability and enabling accurate localization without reliance on dense 3D point cloud data. Evaluations on 27 sequences recorded in forests across three datasets and four countries show that TreeLoc++ achieves precise localization with centimeter-level accuracy. We further demonstrate robustness to long-term change by localizing data recorded in 2025 against inventories built from 2023 data, spanning a two-year interval. The system represents 15 sessions spanning 7.98 km of trajectories using only 250KB of map data and outperforms both hand-crafted and learning-based baselines that rely on point cloud maps. This demonstrates the scalability of TreeLoc++ for long-term deployment.

研究动机与目标

• 在 GNSS 不可靠且密集点云存储成本高的森林中，推动鲁棒的全局定位。
• 提出基于 DFI 的定位框架，直接在树木属性上操作以降低感知混淆与存储需求。
• 通过成对几何上下文提升检索，并通过 DBH 过滤和偏航一致的内点投票来细化匹配。
• 使用基于轴的 2D 投影和受约束的优化实现稳定的 6-DoF 位姿估计，而无需密集的 3D 数据。
• 在多会话、跨数据集和长期场景中展示可扩展性与鲁棒性。

提出的方法

• 通过聚合 LiDAR 有效载荷并通过 RealtimeTrees 提取树木属性（A_j、p'_j、d_j）来构建 Digital Forest Inventory（数字森林目录）。
• 将树干中心投影到与树轴对齐的 2D 平面上，获得对滚转与俯仰不变的描述符坐标。
• 使用两张直方图进行粗检索，分别为树分布直方图（TDH）和成对距离直方图（PDH），实现鲁棒的地点识别。
• 引入由对齐的树中心构建的一个二维三角形描述子，通过三角形哈希来细化候选匹配。
• 基于 DBH 的过滤来消除哈希冲突造成的歧义匹配，并通过偏航一致的内点投票来加强全局位姿的一致性。
• 进行几何核验和受约束的6-DoF 优化，结合匹配树几何信息同时估计滚转、俯仰与高度。

Figure 1 : (Left) Images captured from the same location in the Evo forest two years apart, showing vegetation growth (yellow) and denser foliage (cyan), which amplifies perceptual aliasing. (Right) TreeLoc++ achieves accurate multi-session alignment using only lightweight DFIs by leveraging tree at

实验结果

研究问题

• RQ1 DFIs 是否能够在不使用密集点云、且存储需求最小化的前提下提供可靠的森林环境6-DoF 定位？
• RQ2 将成对几何上下文（PDH）与 TDH 的结合是否相较于仅使用结构性重复的森林布局能提升粗检索效果？
• RQ3 基于 DBH 的过滤与偏航一致的内点投票在减少哈希冲突引起的错误对应方面有多高的有效性？
• RQ4 在树冠覆盖不足的条件下，受约束的联合估计滚转、俯仰和高度的优化是否能提升位姿稳定性？
• RQ5 TreeLoc++ 在多会话、跨数据集和长期场景中的泛化能力如何？

主要发现

• TreeLoc++ 在仅使用总计约 250 KB 地图的 DFIs 情况下实现厘米级位姿精度。
• 在来自三个数据集、27 条序列、四个国家的实验中，TreeLoc++ 超越依赖密集点云的基线，在粗检索中达到更高的召回率（例如与 LoGG3D-Net 相比，Evo Recall@1 从 0.521 提升到 0.940）。
• 该方法对 2025 年采集的数据相对于 2023 年的目录表现鲁棒，演示了两年时间改变对定位的影响容忍性。
• 该管线在 7.98 公里轨迹数据的 15 次会话中实现，极少的地图存储且查询时间亚 10 ms。
• DBH 过滤和偏航投票有效抑制哈希冲突带来的错配，提升了用于核验的候选对应的可靠性。
• 受约束优化同时估计滚转、俯仰和高度，提升了位姿稳定性且不依赖于密集 3D 数据。

Figure 2 : Pipeline of TreeLoc++. TreeLoc++ extracts tree-level traits using RealtimeTrees and converts them into two descriptors for place recognition. Based on the retrieved candidates, it estimates the full 6-DoF pose while suppressing outliers arising from incorrect triangle matches. Using the r