gghl-oriented-object-detection

task = oriented-object-detection

🛠 Model Purpose

This model is part of the GeoAi javascript library.

GeoAi enables geospatial AI inference directly in the browser or Node.js without requiring a heavy backend.

GeoAi pipeline accepts geospatial polygons as input (in GeoJSON format) and outputs results as a GeoJSON FeatureCollection, ready for use with libraries like Leaflet and Mapbox GL.

<video controls autoplay loop width="1024" height="720" src="https://geobase-docs.s3.amazonaws.com/geobase-ai-assets/oriented-object-detection.mp4"></video>

---

🚀 Demo

Explore the model in action with the interactive Demo.

📦 Model Information

• Architecture: GGHL
• Source Model: https://github.com/Shank2358/GGHL
• Quantization: Yes

---

💡 Example Usage

import { geoai } from "geoai";

export const ESRI_CONFIG = {
  provider: "esri" as const,
  serviceUrl: "https://server.arcgisonline.com/ArcGIS/rest/services",
  serviceName: "World_Imagery",
  tileSize: 256,
  attribution: "ESRI World Imagery",
};

// Example polygon (GeoJSON)
const polygon = {
  type: "Feature",
  properties: {},
  geometry: {
    coordinates: [
      [
        [114.9750523641963, -3.4852698831433315],
        [114.97650060618412, -3.4852559566003265],
        [114.97644200679741, -3.487269732522151],
        [114.97511654447737, -3.4871973146522492],
        [114.9750523641963, -3.4852698831433315]
      ],
    ],
    type: "Polygon",
  },
} as GeoJSON.Feature;

// Initialize pipeline
const pipeline = await geoai.pipeline(
  [{ task: "oriented-object-detection" }],
  providerParams : ESRI_CONFIG
);
 
// Run detection
const result = await pipeline.inference({
  inputs: { polygon }
});
 
// Sample output format
// {
//     "detections": {
//         "type": "FeatureCollection",
//         "features": [
//             {
//                 "type": "Feature",
//                 "properties": {
//                      "class_name": "bridge"
//                      "score": 0.6177883799306727
//                 },
//                 "geometry": {
//                     "type": "Polygon",
//                     "coordinates": [
//                         [
//                             [114.97610299609376, -3.4866272343749998],
//                             [114.97612444921876, -3.4866915],
//                             [114.97552912500001, -3.48678254296875],
//                             [114.97550767187501, -3.486712921875],
//                             [114.97610299609376, -3.4866272343749998]
//                         ]
//                     ]
//                 }
//             },
//             {"type": 'Feature', "properties": {…}, "geometry": {…}}, 
//             {"type": 'Feature', "properties": {…}, "geometry": {…}},
//         ]
//     },
//     "geoRawImage": GeoRawImage {data: Uint8ClampedArray(1048576), width: 512, height: 512, channels: 4, bounds: {…}, …}
// }

📖 Documentation & Demo

• GeoBase Docs: https://docs.geobase.app/geoai
• NPM Package: https://www.npmjs.com/package/geoai
• Demo Playground: https://docs.geobase.app/geoai-live/tasks/oriented-object-detection
• GitHub Repo: https://github.com/decision-labs/geoai.js