SIRST-UAVB: Single frame infrared small target dataset - UAV and birds.

Infrared dim-small target detection has gained increasing importance in both military and civilian applications due to its ability to detect thermal radiation, operate effectively at night, passively sense radiation, and offer strong concealment with high resistance to interference. These capabilities make it ideal for systems such as aircraft and bird surveillance, missile guidance, and maritime rescue operations. In these applications, the need for mid- to long-range observations often results in small targets that appear dim and are difficult to detect. This dataset, named SIRST-UAVB, provides infrared images captured in the 3–5 μm wavelength range using a mid-wave infrared camera, with a resolution of 640×512 pixels and shooting distances ranging from 100 to 800 meters. The dataset predominantly features small targets, which make up 94.3% of the total data and include unmanned aerial vehicles (UAVs) and birds. These targets are presented against complex backgrounds, such as skies, clouds, buildings, and vegetation, which introduce significant challenges. The combination of low signal-to-noise ratio (SNR), low signal-to-clutter ratio (SCR), and substantial background noise further complicates detection, as targets are easily obscured by environmental clutter.

红外弱小目标检测因其可探测热辐射、夜间稳定工作、被动感知辐射以及隐蔽性强、抗干扰能力优异的特性，在军事与民用领域均获得了日益广泛的重视。这些特性使其十分适用于飞行器与鸟类监测、导弹制导、海上搜救等应用场景。在这类应用中，中远距离观测的需求往往会导致目标体型小巧、特征微弱，难以被有效检测。该数据集命名为SIRST-UAVB，采用中波红外相机（mid-wave infrared camera）采集3~5 μm波长范围内的红外图像，图像分辨率为640×512像素，拍摄距离覆盖100至800米。该数据集以弱小目标为核心主体，目标样本占总数据量的94.3%，涵盖无人机（Unmanned Aerial Vehicles, UAVs）与鸟类两类。上述目标均处于天空、云层、建筑、植被等复杂背景中，为检测任务带来了极大挑战。低信噪比（signal-to-noise ratio, SNR）、低信杂比（signal-to-clutter ratio, SCR）与显著的背景噪声进一步加剧了检测难度，目标极易被环境杂波遮蔽。

搜集汇总

背景与挑战

背景概述

SIRST-UAVB是一个红外小目标检测数据集，包含无人机和鸟类目标，图像分辨率为640×512像素，拍摄距离在100至800米之间。数据集提供了2400张训练图像和600张测试图像，适用于目标检测和分割任务，背景复杂且目标小，挑战性强。