{
  "id": "2401.05971",
  "version": "v1",
  "published": "2024-01-11T15:19:21.000Z",
  "updated": "2024-01-11T15:19:21.000Z",
  "title": "UAVD4L: A Large-Scale Dataset for UAV 6-DoF Localization",
  "authors": [
    "Rouwan Wu",
    "Xiaoya Cheng",
    "Juelin Zhu",
    "Xuxiang Liu",
    "Maojun Zhang",
    "Shen Yan"
  ],
  "journal": "3DV 2024",
  "categories": [
    "cs.CV"
  ],
  "abstract": "Despite significant progress in global localization of Unmanned Aerial Vehicles (UAVs) in GPS-denied environments, existing methods remain constrained by the availability of datasets. Current datasets often focus on small-scale scenes and lack viewpoint variability, accurate ground truth (GT) pose, and UAV build-in sensor data. To address these limitations, we introduce a large-scale 6-DoF UAV dataset for localization (UAVD4L) and develop a two-stage 6-DoF localization pipeline (UAVLoc), which consists of offline synthetic data generation and online visual localization. Additionally, based on the 6-DoF estimator, we design a hierarchical system for tracking ground target in 3D space. Experimental results on the new dataset demonstrate the effectiveness of the proposed approach. Code and dataset are available at https://github.com/RingoWRW/UAVD4L",
  "revisions": [
    {
      "version": "v1",
      "updated": "2024-01-11T15:19:21.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "large-scale dataset",
      "offline synthetic data generation",
      "uav build-in sensor data",
      "despite significant progress",
      "lack viewpoint variability"
    ],
    "tags": [
      "journal article"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}