LARD : Landing Approach Runway Detection, dataset of aerial front view images of runways

Landing Approach Runway Detection (LARD) is a dataset of aerial front view images of runways designed for aircraft landing phase. It contains over 17K synthetic images of various runways, enriched with more than 1800 annotated pictures from real landing footages for comparison. We also provide a synthetic image generator based on Google Earth Studio if you want to enrich your dataset, or fatten your LARD. Starting from a database of runway positions, our generator produces high quality synthetic pictures of airport runways with their metadata. Through geometric transformations, these pictures can then be automatically annotated with the position of the runway or any targeted element in the aerial picture.着陆进近跑道检测（Landing Approach Runway Detection，LARD）数据集是面向航空器着陆阶段的跑道航拍正视图像数据集。该数据集包含超过1.7万张各类跑道的合成图像，并补充了1800余张来自真实着陆航段的标注实拍影像以供对照使用。我们还提供了基于Google Earth Studio的合成图像生成工具，以供使用者扩充数据集、丰富LARD的样本规模。该生成工具以跑道位置数据库为初始输入，可生成附带元数据的高质量机场跑道合成图像。通过几何变换，可自动为这些图像标注跑道或航拍画面中任意目标元素的位置信息。

搜集汇总

背景与挑战

背景概述

LARD数据集是一个专注于飞机着陆阶段跑道检测的视觉数据集，包含超过17,000张合成跑道图像和1,800多张真实着陆标注图像，用于对比和验证。数据集还提供了基于Google Earth Studio的合成图像生成器，可自动生成高质量跑道图像并标注目标位置，适用于目标检测和视觉引导着陆研究。