Towards UAV Detection in the Real World: A New Multispectral Dataset UAVNet-MS and a New Method

TL;DR

This paper introduces UAVNet-MS, a novel multispectral dataset for small-UAV detection, and proposes MFDNet, a dual-stream model that leverages spectral signatures to improve detection accuracy over RGB-only methods.

Contribution

The paper provides the first multispectral dataset for small-UAV detection and introduces a new dual-stream model that effectively fuses spatial and spectral information.

Findings

MFDNet outperforms RGB-only detectors by +6.2% AP50.

UAVNet-MS contains 15,618 synchronized RGB-MSI data cubes with annotations.

Spectral cues significantly enhance small-UAV detection accuracy.

Abstract

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.