# SAR Image Connected Component Extractor

> SAR Image Connected Component Extractor is a paid API for AI agents from space.halowerk.com, paid per call via x402, $0.004/call, status unknown (last checked 2026-09-14).

Labels four-neighbor connected components in a 2-D numeric grid above a caller-defined threshold, returning area, bounding box, peak, and mean value for each component.

## Facts

- Endpoint: POST https://space.halowerk.com/v1/sar-image-extract
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sar-image-connected-component-extractor-c47fd272
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_EjO1K6ZF1lF8jS52eJ2_E

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability sar-image-connected-component-extractor-c47fd272 -d '<json body>'
```

Example prompt: Take this 64×64 SAR backscatter grid and find all connected foreground regions above a threshold of 150, using a pixel area of 100 square meters and ignoring any components smaller than 5 pixels — give me the area, bounding box, peak, and mean for each one.

## When to prefer this

Use this endpoint when you have a raw 2-D numeric grid (e.g. SAR backscatter, difference images, or any raster) and need fast connected-component labeling with per-component statistics. It is ideal for detecting and measuring discrete foreground blobs by threshold without needing image ingestion, geolocation, speckle filtering, or object classification — those must be handled upstream or downstream.

## Known failure modes

- Grid dimensions exceed 128×128 limit — request rejected
- Threshold set so high no foreground pixels exist — empty component list returned
- Minimum component pixel size filters out all detected regions — empty result
- Grid contains non-numeric or out-of-range values — validation error
- Malformed grid (ragged rows, non-array types) — schema validation failure

## How this service works

Treats cells at or above a caller threshold as foreground, labels four-neighbor connected components, and reports area, bounding box, peak, and mean value. It does not ingest imagery, calibrate backscatter, remove speckle, geolocate pixels, classify objects, or infer real-world meaning.

## Output

A list of detected foreground connected components, each with: pixel count (area), bounding box coordinates, peak cell value, and mean cell value across the component. Components below the minimum pixel threshold are excluded.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "grid": {
   "type": "array",
   "items": {
    "type": "array",
    "items": {
     "type": "number",
     "maximum": 1000000000000,
     "minimum": -1000000000000,
     "description": "Numeric cell value in a caller-defined unit."
    },
    "maxItems": 128,
    "minItems": 1
   },
   "maxItems": 128,
   "minItems": 1
  },
  "threshold": {
   "type": "number",
   "maximum": 1000000000000,
   "minimum": -1000000000000
  },
  "pixel_area_m2": {
   "type": "number",
   "maximum": 1000000000000,
   "minimum": 0.000001
  },
  "minimum_component_pixels": {
   "type": "integer",
   "maximum": 16384,
   "minimum": 1
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sar-image-connected-component-extractor-c47fd272/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from space.halowerk.com](https://www.zero.xyz/host/space.halowerk.com/llms.txt)