Phase 2 Documentation

Spatial Intelligence Engine (SIE)

Welcome to the official documentation for the Spatial Intelligence Engine (SIE). SIE bridges raw video camera feeds and spatial imagery with precise metric coordinate systems, enabling autonomous agents, industrial robots, and human operators to share a common operational map in real time.

Phase 2 Update: Sub-pixel grid calibration and movement prediction vector tracking are now fully supported out-of-the-box in v0.2.0.

5-Minute Quickstart

Get your first spatial stream ingested, calibrated, and analyzed in minutes using our Python SDK or Docker instance.

Step 1: Install Python Package

pip install spatial-intelligence-engine

Step 2: Initialize Engine & Calibrate Grid

from sie import SpatialEngine, GridConfig

# Initialize engine with warehouse feed
engine = SpatialEngine.connect("rtsp://warehouse-cam-01.local:554/stream")

# Configure 8x12 metric grid
grid = GridConfig(rows=8, columns=12, line_thickness=1)
calibrated_scene = engine.calibrate(grid)

print(f"Grid active with {calibrated_scene.total_cells} total cells.")
calibrated_scene.run_analysis(model="nanodet", tracking=True)

System Requirements

Hardware Specs (Edge / Server)

CPU: 4+ Cores (AVX2 support recommended)
RAM: 8 GB minimum (16 GB for 4K video streams)
GPU: Optional NVIDIA CUDA (Compute 6.0+) for hardware accelerated ONNX inference

Software Environment

Python 3.9 - 3.12
Docker 24.0+ & Docker Compose v2
OpenCV 4.8+ & NumPy 1.24+

Sources & Ingestion Module

SIE supports multi-modal media ingestion. Whether you are uploading static high-res JPEGs of facility layouts, connecting live USB sensors, or streaming RTSP security feeds, the pipeline normalizes frames into synchronous spatial matrices.

// Supported Source Protocols

🖼️ Images (JPG, PNG)

🎥 Videos (MP4, MOV)

📹 USB / IP Webcams

🌐 RTSP / WebRTC

Grid Calibration & Setup

Calibrating your physical environment turns raw pixels into actionable metric grid coordinates `(x, y)`. Use the interactive UI or configure programmatically.

from sie.calibration import GridCalibrator

calibrator = GridCalibrator(image="warehouse.jpg")
grid_matrix = calibrator.generate(
    rows=8,
    cols=12,
    line_thickness=1,
    color="#3B82F6"
)
grid_matrix.export_config("config/warehouse_grid.json")

REST API & Webhooks Reference

Interact directly with the SIE daemon using standard HTTP REST endpoints or configure outbound webhooks for real-time event triggers.

POST /api/v2/spatial/analyze

Triggers synchronous frame analysis and returns bounding boxes, object counts, and grid coordinates.

GET /api/v2/telemetry/report

Retrieves aggregated zone occupancy density and flow throughput metrics in JSON format.

Docker Compose Deployment

Deploy SIE inside production environments with our official containerized docker-compose stack.

version: '3.8'
services:
  sie-engine:
    image: spatialintelligence/engine:v0.2.0
    ports:
      - "8080:8080"
    environment:
      - SIE_ENV=production
      - ACCELERATION=cuda
    volumes:
      - ./data:/app/data