The proliferation of unmanned aerial vehicles (UAVs) has created urgent demand for precise UAV monitoring. Existing RGB-based systems rely on spatial cues that degrade at small scales, particularly with high inter-type similarity, target-clutter ambiguity, and low contrast. Multispectral imaging (MSI) encodes material-aware spectral signatures, yet MSI-based fine-grained small-UAV detection remains underexplored due to lack of dedicated datasets. We introduce UAVNet-MS, the first multispectral dataset for fine-grained small-UAV detection, comprising 15,618 temporally synchronized RGB-MSI data cubes (1440x1080) with bounding box annotations. The dataset features challenging small objects (93.7% <= 32^2 pixels, average 18^2 pixels, ~0.02% image area) under low contrast. We propose MFDNet, a dual-stream baseline addressing array-induced parallax and spatial-spectral fusion. Extensive evaluation under RGB-only, MSI-only, and RGB+MSI protocols against 20 detectors shows MFDNet achieves +6.2% AP50 improvement over best RGB-only methods, demonstrating spectral cues provide complementary material evidence beyond spatial cues. This work provides foundational dataset, strong baseline, and benchmark for multispectral UAV monitoring research.
@article{arxiv.2605.20963,
title = {Towards UAV Detection in the Real World: A New Multispectral Dataset UAVNet-MS and a New Method},
author = {Yihang Luo and Jun Chen and Chao Xiao and Yingqian Wang and Zhaoxu Li and Qiang Ling and Xu He and Nuo Chen and Gaowei Guo and Hongge Li and Miao Li and Longguang Wang and Yulan Guo and Li Liu and Wei An and Zhijie Chen},
journal= {arXiv preprint arXiv:2605.20963},
year = {2026}
}
Comments
submitted to IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)