mlsanityData to 14 Oct 2026

Archangel: A Hybrid UAV-based Human Detection Benchmark with Position and Pose Metadata

arXiv 2209.00128 ↗First posted 31 Aug 2022cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Learning to detect objects, such as humans, in imagery captured by an unmanned aerial vehicle (UAV) usually suffers from tremendous variations caused by the UAV's position towards the objects. In addition, existing UAV-based benchmark datasets do not provide adequate dataset metadata, which is essential for precise model diagnosis and learning features invariant to those variations. In this paper, we introduce Archangel, the first UAV-based object detection dataset composed of real and synthetic subsets captured with similar imagining conditions and UAV position and object pose metadata. A series of experiments are carefully designed with a state-of-the-art object detector to demonstrate the benefits of leveraging the metadata during model evaluation. Moreover, several crucial insights involving both real and synthetic data during model optimization are presented. In the end, we discuss the advantages, limitations, and future directions regarding Archangel to highlight its distinct value for the broader machine learning community.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 31 of its 65 references that are in the map. First posted on arXiv 31 Aug 2022.

Builds on

31 of 65 references.

References · 31

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  3. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,630
  4. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  5. 2021Domain Generalization: A Surveycited by 764
  6. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  7. 2020Detection and Tracking Meet Drones Challengecited by 263
  8. 2018Unity: A General Platform for Intelligent Agentscited by 236
  9. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 204
  10. 2017Drone-based Object Counting by Spatially Regularized Regional Proposal Networkcited by 156
  11. 2019Meta-Sim: Learning to Generate Synthetic Datasetscited by 128
  12. 2019Synthetic Data for Deep Learningcited by 113
19 more
  1. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 98
  2. 2021UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehiclescited by 96
  3. 2019Clustered Object Detection in Aerial Imagescited by 83
  4. 2021SeaDronesSee: A Maritime Benchmark for Detecting Humans in Open Watercited by 61
  5. 2020AU-AIR: A Multi-modal Unmanned Aerial Vehicle Dataset for Low Altitude Traffic Surveillancecited by 56
  6. 2021MedAug: Contrastive learning leveraging patient metadata improves representations for chest X-ray interpretationcited by 52
  7. 2017Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detectioncited by 46
  8. 2021Deep Learning for UAV-based Object Detection and Tracking: A Surveycited by 33
  9. 2020HRDNet: High-resolution Detection Network for Small Objectscited by 25
  10. 2019Delving into Robust Object Detection from Unmanned Aerial Vehicles: A Deep Nuisance Disentanglement Approachcited by 23
  11. 2020Small Data, Big Decisions: Model Selection in the Small-Data Regimecited by 23
  12. 2021Leveraging Synthetic Data in Object Detection on Unmanned Aerial Vehiclescited by 22
  13. 2019Generative Modeling for Small-Data Object Detectioncited by 20
  14. 2020MOR-UAV: A Benchmark Dataset and Baselines for Moving Object Recognition in UAV Videoscited by 15
  15. 2020The 1st Tiny Object Detection Challenge:Methods and Resultscited by 14
  16. 2020Mixing Real and Synthetic Data to Enhance Neural Network Training -- A Review of Current Approachescited by 13
  17. 2022A Multi-purpose Realistic Haze Benchmark with Quantifiable Haze Levels and Ground Truthcited by 9
  18. 2019FollowMeUp Sports: New Benchmark for 2D Human Keypoint Recognitioncited by 3
  19. 2022Validation of object detection in UAV-based images using synthetic datacited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 5; 2025: 1; 2026: 1.

9 papers.

  1. 2022Progressive Transformation Learning for Leveraging Virtual Images in Trainingcited by 10
  2. 2023UAV-Sim: NeRF-based Synthetic Data Generation for UAV-based Perceptioncited by 10
  3. 2024Diversifying Human Pose in Synthetic Data for Aerial-view Human Detectioncited by 5
  4. 2024TK-Planes: Tiered K-Planes with High Dimensional Feature Vectors for Dynamic UAV-based Scenescited by 3
  5. 2024Exploring the Impact of Synthetic Data for Aerial-view Human Detectioncited by 3
  6. 2024Exploring the Potential of Synthetic Data to Replace Real Datacited by 3
  7. 2024SynPlay: Large-Scale Synthetic Human Data with Real-World Diversity for Aerial-View Perceptioncited by 1
  8. 2025UAVTwin: Neural Digital Twins for UAVs using Gaussian Splattingcited by 1
  9. 2026Can Synthetic UAV Benchmarks Be Trusted? Real-Synthetic Validation for UAV Model Selectioncited by 0