mlsanityData to 7 Oct 2026

FlyPose: Towards Robust Human Pose Estimation From Aerial Views

arXiv 2601.05747 ↗First posted 9 Jan 2026cs.CV cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

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: https://github.com/farooqhassaan/FlyPose.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 44 of its 65 references that are in the map. First posted on arXiv 9 Jan 2026.

Builds on

44 of 65 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  6. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  7. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  8. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  9. 2020Designing Network Design Spacescited by 954
  10. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  11. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  12. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
32 more
  1. 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistlescited by 287
  2. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 273
  3. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  4. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
  5. 2016Panoptic Studio: A Massively Multiview System for Social Interaction Capturecited by 173
  6. 2023RTMPose: Real-Time Multi-Person Pose Estimation based on MMPosecited by 170
  7. 2018xView: Objects in Context in Overhead Imagerycited by 145
  8. 2021UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehiclescited by 95
  9. 2021Lite-HRNet: A Lightweight High-Resolution Networkcited by 91
  10. 2022Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baselinecited by 90
  11. 2024RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformercited by 88
  12. 2018SNIPER: Efficient Multi-Scale Trainingcited by 87
  13. 2023Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Taskscited by 72
  14. 2022YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Losscited by 66
  15. 2019Scale Match for Tiny Person Detectioncited by 61
  16. 2021SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Watercited by 59
  17. 2022Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmarkcited by 56
  18. 2024LW-DETR: A Transformer Replacement to YOLO for Real-Time Detectioncited by 36
  19. 2021UFPMP-Det: Toward Accurate and Efficient Object Detection on Drone Imagerycited by 34
  20. 2023RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimationcited by 33
  21. 2022HIT-UAV: A high-altitude infrared thermal dataset for Unmanned Aerial Vehicle-based object detectioncited by 31
  22. 2019Top-view Trajectories: A Pedestrian Dataset of Vehicle-Crowd Interaction from Controlled Experiments and Crowded Campuscited by 25
  23. 2021DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoderscited by 23
  24. 2021Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimationcited by 20
  25. 2024ESOD: Efficient Small Object Detection on High-Resolution Imagescited by 15
  26. 2022AirPose: Multi-View Fusion Network for Aerial 3D Human Pose and Shape Estimationcited by 11
  27. 2024When Pedestrian Detection Meets Multi-Modal Learning: Generalist Model and Benchmark Datasetcited by 10
  28. 2022Swin-Pose: Swin Transformer Based Human Pose Estimationcited by 9
  29. 2018Human Pose and Path Estimation from Aerial Video using Dynamic Classifier Selectioncited by 5
  30. 2023NOMAD: A Natural, Occluded, Multi-scale Aerial Dataset, for Emergency Response Scenarioscited by 4
  31. 2023Rethinking the backbone architecture for tiny object detectioncited by 3
  32. 2023Human Pose Estimation in Monocular Omnidirectional Top-View Imagescited by 3

Built on by

Not cited yet.