xView Satellite Object Detection

Large-scale overhead imagery object detection (Lam et al., arXiv 2018). Detect 60 object classes including vehicles, buildings, and infrastructure from satellite images.

Fichier de configurationconfig.yaml

# xView Satellite Object Detection Configuration
# Based on Lam et al., arXiv 2018

annotation_task_name: "xView Satellite Object Detection"
task_dir: "."

data_files:
  - "sample-data.json"

item_properties:
  id_key: "id"
  text_key: "image_url"
  context_key: "context"

user_config:
  allow_all_users: true

annotation_schemes:
  - annotation_type: "multiselect"
    name: "vehicles"
    description: "Select visible vehicle types"
    labels:
      - name: "small_car"
        tooltip: "Passenger vehicles"
      - name: "bus"
        tooltip: "Buses"
      - name: "truck"
        tooltip: "Trucks and cargo vehicles"
      - name: "cargo_plane"
        tooltip: "Cargo aircraft"
      - name: "helicopter"
        tooltip: "Helicopters"
      - name: "small_aircraft"
        tooltip: "Small planes"
      - name: "ship"
        tooltip: "Ships and vessels"
      - name: "motorboat"
        tooltip: "Motorboats"
      - name: "train"
        tooltip: "Trains"

  - annotation_type: "multiselect"
    name: "structures"
    description: "Select visible structures"
    labels:
      - name: "building"
        tooltip: "Buildings"
      - name: "storage_tank"
        tooltip: "Storage tanks"
      - name: "shipping_container"
        tooltip: "Shipping containers"
      - name: "tower"
        tooltip: "Towers, antennas"
      - name: "helipad"
        tooltip: "Helipads"
      - name: "facility"
        tooltip: "Industrial facilities"

  - annotation_type: "multiselect"
    name: "equipment"
    description: "Select visible equipment"
    labels:
      - name: "crane"
        tooltip: "Cranes"
      - name: "construction_vehicle"
        tooltip: "Construction vehicles"
      - name: "agricultural_vehicle"
        tooltip: "Farm equipment"
      - name: "engineering_vehicle"
        tooltip: "Engineering vehicles"

  - annotation_type: "radio"
    name: "image_quality"
    description: "Rate the image quality"
    labels:
      - name: "clear"
        tooltip: "Clear, high-resolution"
      - name: "moderate"
        tooltip: "Some noise or blur"
      - name: "poor"
        tooltip: "Significant quality issues"

  - annotation_type: "text"
    name: "bbox_list"
    description: "List bounding boxes: class,x,y,w,h (one per line)"

interface_config:
  item_display_format: "<img src='{{text}}' style='max-width:100%; max-height:500px;'/><br/><small>{{context}}</small>"

output_annotation_format: "json"
output_annotation_dir: "annotations"

Données d'exemplesample-data.json

[
  {
    "id": "xview_001",
    "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/1/10/Empire_State_Building_%28aerial_view%29.jpg/800px-Empire_State_Building_%28aerial_view%29.jpg",
    "context": "Overhead satellite imagery. Detect all visible objects including vehicles, buildings, and equipment."
  },
  {
    "id": "xview_002",
    "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/1/1e/San_Francisco_from_the_Marin_Headlands_in_March_2019.jpg/1200px-San_Francisco_from_the_Marin_Headlands_in_March_2019.jpg",
    "context": "Satellite view. Mark all xView object categories visible."
  }
]

// ... and 1 more items

Obtenir ce design

View on GitHub

Clone or download from the repository

Démarrage rapide :

git clone https://github.com/davidjurgens/potato-showcase.git
cd potato-showcase/image/aerial/xview
potato start config.yaml

Détails

Types d'annotation

multiselectradiotext

Domaine

Remote SensingSatellite Imagery

Cas d'utilisation

Object DetectionSatellite AnalysisGeospatial Intelligence

Étiquettes

xviewsatelliteoverheadobject-detectiongeospatial

Vous avez trouvé un problème ou souhaitez améliorer ce design ?

Ouvrir un ticket

Designs associés

DOTA Aerial Image Object Detection

Oriented bounding box detection in aerial images (Xia et al., CVPR 2018). Detect 15 object categories with arbitrary orientations including planes, ships, vehicles, and sports facilities.

multiselectradio

FLAIR: French Land Cover from Aerospace Imagery

Land use and land cover classification from high-resolution aerial imagery. Annotators classify the primary land use category of aerial image patches and identify any secondary land uses present. Based on the FLAIR dataset from the French National Institute of Geographic and Forest Information (IGN).

multiselectradio

CUB-200-2011 Fine-Grained Bird Classification

Fine-grained visual categorization of 200 bird species (Wah et al., 2011). Annotate bird images with species labels, part locations, and attribute annotations.

multiselectradio