Abstract
Unmanned Aerial Vehicles (UAVs) are increasingly deployed in close proximity to humans for applications such as parcel delivery, traffic monitoring, disaster response and infrastructure inspections. Ensuring safe and reliable operation in these human-populated environments demands accurate perception of human poses and actions from an aerial viewpoint. This perspective challenges existing methods with low resolution, steep viewing angles and (self-)occlusion, especially if the application demands realtime feasibile models. We train and deploy FlyPose, a lightweight top-down human pose estimation pipeline for aerial imagery. Through multi-dataset training, we achieve an average improvement of 6.8 mAP in person detection across the test-sets of Manipal-UAV, VisDrone, HIT-UAV as well as our custom dataset. For 2D human pose estimation we report an improvement of 16.3 mAP on the challenging UAV-Human dataset. FlyPose runs with an inference latency of ~20 milliseconds including preprocessing on a Jetson Orin AGX Developer Kit and is deployed onboard a quadrotor UAV during flight experiments. We also publish FlyPose-104, a small but challenging aerial human pose estimation dataset, that includes manual annotations from difficult aerial perspectives: this https URL.
Abstract (translated)
无人驾驶飞行器（UAVs）在诸如包裹递送、交通监控、灾害应对和基础设施检查等人周围环境中越来越常见。为了确保这些有人类居住环境中的安全可靠运行，需要从空中视角准确感知人体姿势和动作。这一角度对现有方法提出了挑战，包括低分辨率、陡峭的观察角度以及（自我）遮挡问题，尤其是在实时模型的需求下。我们训练并部署了FlyPose，这是一种针对航拍图像的人体姿态估计轻量级顶视图管道。通过多数据集训练，我们在Manipal-UAV、VisDrone、HIT-UAV和我们自定义的数据集中实现了平均6.8 mAP（平均精度）的人物检测改进。对于2D人体姿态估计，在具有挑战性的UAV-Human数据集上，FlyPose显示出了16.3 mAP的提升。 FlyPose在Jetson Orin AGX开发套件上的推理延迟约为20毫秒，包括预处理步骤，并且已部署到四旋翼无人机进行飞行实验。此外，我们发布了FlyPose-104，这是一个小但具有挑战性的航拍人体姿态估计数据集，其中包含了从困难视角的手动注释：[链接](this https URL)。 （注意：原文中的"this https URL"似乎是一个错误的格式，应该替换为实际的数据集发布链接。）
URL
https://arxiv.org/abs/2601.05747
