picarta 0.4

A package to geolocate images from URL or local files using Picarta AI

Picarta

A Python package to geolocate images from URL or local files using Picarta.ai API 🌍🔍.

Overview

The Picarta Image Geolocalization API allows users to localize images and obtain predictions about their geographic location based on their content and/or embedded metadata. Users can provide an image either from a local file or via a URL and receive predictions about the location depicted in the image. The API returns information such as city, province, country, GPS coordinates, and confidence scores for each prediction.

Authentication

To access the API, users need to provide an API token in the request headers. Users can obtain an API token by registering on the Picarta website.

Installation

To install the picarta package, use pip:

pip install picarta

Usage

Request Format

The API accepts HTTP POST requests with a JSON payload containing the following parameters:

• TOKEN: User's API token.
• IMAGE: image path or URL of the image to localize.
• TOP_K (Optional): Number of top predictions to return (default is 10, maximum is 100).
• Center_LATITUDE (Optional): Latitude of the center of the search area.
• Center_LONGITUDE (Optional): Longitude of the center of the search area.
• RADIUS (Optional): Radius of the search area around the center point in kilometers.

Example Request using the picarta Package

from picarta import Picarta

api_token = "YOUR_API_TOKEN"
localizer = Picarta(api_token)

# Geolocate a local image
result = localizer.localize(img_path="/path/to/local/image.jpg")

print(result)

# Geolocate an image from URL with optional parameters for a specific location search
result = localizer.localize(
img_path="https://upload.wikimedia.org/wikipedia/commons/8/83/San_Gimignano_03.jpg",
top_k=10,
center_latitude=43.464, 
center_longitude=11.038,
radius=100)

print(result)

Response Format

The API returns a JSON object containing geographic location results, including metadata about the image and a dictionary of topk predictions.

Example API Response

{
  "ai_country": "Fiji",
  "ai_lat": -10.932661290178117,
  "ai_lon": 173.54167690802137,
  "camera_maker": "NIKON CORPORATION",
  "camera_model": "NIKON D200",
  "city": "Ahau",
  "confidence": 0.7205776784126713,
  "province": "Rotuma",
  "timestamp": "2010:09:21 12:04:46",
  "topk_predictions_dict": {
    "1": {
      "address": {"city": "Ahau", "country": "Fiji", "province": "Rotuma"},
      "confidence": 0.7205776784126713,
      "gps": [-10.932661290178117, 173.54167690802137]
    },
    "2": {
      "address": {"city": "Nghi Xuan", "country": "Vietnam", "province": "Ha Tinh"},
      "confidence": 0.13465818962254223,
      "gps": [18.831436938230198, 106.00851919090474]
    },
    "3": {
      "address": {"city": "Hanga Roa", "country": "Chile", "province": "Valparaiso"},
      "confidence": 0.03465818962254226,
      "gps": [-42.42505486943787, -118.63631306266818]
    }
  }
}

Additional Notes

• topk_predictions_dict is presented in the second version of the API.
• topk_predictions_dict[1] is equal to province, ai_country, city, ai_lat, ai_lon, and ai_confidence. (It shows the top 1 result, which was in the first version of the API).
• The API could also return the following values if the EXIF data exists in the images:
  • exif_lat: Latitude from EXIF metadata.
  • exif_lon: Longitude from EXIF metadata.
  • exif_country: Country name from EXIF metadata.

Contact Information

For any inquiries or assistance, feel free to contact us via:

• Email: [e-mail]
• Discord: Join our Discord channel
• Share your feedback: API Feedback Survey