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.

🖼️

image annotation

Configuration Fileconfig.yaml

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

annotation_task_name: "xView Satellite Object Detection"

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"

Sample Datasample-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

Get This Design

View on GitHub

Clone or download from the repository

Quick start:

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

Details

Annotation Types

bboxmultiselect

Domain

Remote SensingSatellite Imagery

Use Cases

Object DetectionSatellite AnalysisGeospatial Intelligence

Related Designs

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.

bboxmultiselect

BDD100K Autonomous Driving Segmentation

Large-scale diverse driving video dataset (Yu et al., CVPR 2020). Annotate driving scenes with bounding boxes, lane markings, drivable areas, and full-frame instance segmentation.

bboxpolygon

CelebA Face Attributes Classification

Large-scale face attributes dataset with 40 binary attributes (Liu et al., ICCV 2015). Annotate celebrity face images with attributes including hair color, age, gender, and facial features.

multiselectbbox