# MultiFly：一个真实世界多模态空中数据集，具备注释高效的标签迁移和跨模态语义一致性

> 原文链接：https://robotics.hellobike.com/papers/2026-10-07-2610-10359
> 频道：papers | 更新日期：2026-10-07 | 标签：arxiv, cs.RO
> 核心摘要：MultiFly面向低空UAV多模态语义感知，通过几何标签迁移生成一致标注，并在RGB、热成像、LiDAR和雷达上验证。

# MultiFly：一个真实世界多模态空中数据集，具备注释高效的标签迁移和跨模态语义一致性

::: v-pre
> 原文链接：[MultiFly: A Real-World Multimodal Aerial Dataset with Annotation-Efficient Label Transfer and Cross-Modal Semantic Consistency](https://arxiv.org/abs/2610.10359)（arXiv 2610.10359 · 发布日期：2026-10-07）

**MultiFly: A Real-World Multimodal Aerial Dataset with Annotation-Efficient Label Transfer and Cross-Modal Semantic Consistency**

MultiFly面向低空UAV多模态语义感知，通过几何标签迁移生成一致标注，并在RGB、热成像、LiDAR和雷达上验证。

## 核心要点

- 低空UAV多模态语义感知需要跨RGB、热成像、LiDAR和雷达的一致逐帧标注。
- 数据集含17,272个同步样本、15类语义标注、标定及GNSS-RTK/IMU测量。
- 方法仅人工标注115张RGB图像，经共享几何表示向四种模态传播标签。
- 实验给出89.93%标注一致率和90.94%跨模态一致性，并建立四模态分割基准；数据已公开。

**验证范围与局限**：验证范围为四个郊区场景的真实低空UAV数据，覆盖RGB、热成像、LiDAR和雷达语义感知。

## 英文摘要 (Abstract)

We introduce MultiFly, a real-world, low-altitude UAV dataset for semantic perception across RGB, thermal, LiDAR, and radar modalities. MultiFly provides 17,272 synchronized samples from four suburban scenes with frame-wise annotations for 15 semantic classes, together with calibration and GNSS-RTK/IMU measurements. To avoid costly and inconsistent modality-specific annotation, we propagate labels from only 115 manually annotated RGB images through shared geometric representations to all four modalities. This approach generates semantic labels for 17,157 additional RGB images, 17,272 thermal images, 840M LiDAR points, and 3.4M radar points. Transferred annotations achieve 89.93% average agreement with held-out manual annotations, and 90.94% average semantic consistency across all six modality pairs. We further establish semantic segmentation benchmarks for all four modalities, revealing distinct architectural behavior for dense LiDAR and sparse radar data. Taken together, MultiFly provides a scalable foundation for multimodal aerial perception and, to the best of our knowledge, the first public real-world low-altitude aerial benchmark that combines consistent frame-wise semantic annotations for RGB, thermal, LiDAR, and radar. Data at https://github.com/markus-42/multifly.

作者：Markus Gross, Andreas Greiner, Taehyoung Kim, Sivasubiramaniam Subbiah, Tomaž Cotič, Conrad Christoph, Oussema Dhaouadi, Simon Zieher, Surya Vijaya Kumar, Gordon Elger
:::

## 原始参考来源 (Sources)

- [arXiv 2610.10359：MultiFly: A Real-World Multimodal Aerial Dataset with Annotation-Efficient Label Transfer and Cross-Modal Semantic Consistency](https://arxiv.org/abs/2610.10359)