# HALOWERK Dense Farneback Optical Flow

> HALOWERK Dense Farneback Optical Flow is a paid API for AI agents from medien.halowerk.com, paid per call via x402, $0.004/call, status unknown (last checked 2026-10-28).

Computes dense Farneback optical flow between two consecutive grayscale frames, returning per-pixel horizontal and vertical displacement vectors for the entire image.

## Facts

- Endpoint: POST https://medien.halowerk.com/v1/oss-opencv-dense-frame-optical-flow?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-28
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/halowerk-dense-farneback-optical-flow-266bdb18
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_FqMa68ckY0RDXxiX9BZOY

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 halowerk-dense-farneback-optical-flow-266bdb18 -d '<json body>'
```

Example prompt: I have two consecutive grayscale frames from a video of a river — can you compute the dense optical flow between them to get the full per-pixel horizontal and vertical displacement across the whole image, including the featureless water surface?

## When to prefer this

Choose this endpoint when you need motion information for every pixel in an image, especially in regions lacking distinct visual features (smoke, water, fog, crowds, uniform textures, panning backgrounds). It is preferable to sparse feature tracking (e.g. Lucas-Kanade on keypoints) when the regions of interest have no trackable corners or edges, and when a complete dense flow field is required for downstream analysis such as motion segmentation, action recognition, or video stabilization.

## Known failure modes

- Frames are different sizes — both inputs must have identical dimensions
- Non-grayscale or multi-channel images may be rejected or produce incorrect results
- Frames taken too far apart in time may produce noisy or unreliable flow due to large displacements
- Empty or malformed image data in the request body returns a 400/422 error
- Payment not included or insufficient USDC triggers a 402 Payment Required response

## How this service works

Computes dense Farneback optical flow between two consecutive grayscale frames and returns the horizontal and vertical displacement of every pixel. Unlike sparse tracking this covers the whole image, which is what you want for measuring motion in regions with no distinct features to track — smoke, water, crowds, a panning background. Both frames must be the same size and should come from the same camera at a short interval.

## Output

Returns a dense optical flow field covering every pixel in the input frames: a horizontal displacement map (flow_x) and a vertical displacement map (flow_y), both the same spatial dimensions as the input images, representing how far each pixel has moved between the two frames in the x and y directions.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType"
   ],
   "properties": {
    "type": {
     "const": "http"
    },
    "method": {
     "const": "POST"
    },
    "bodyType": {
     "const": "json"
    },
    "schemaUrl": {
     "type": "string",
     "format": "uri"
    },
    "exampleUrl": {
     "type": "string",
     "format": "uri"
    }
   },
   "additionalProperties": true
  },
  "output": {
   "type": "object",
   "required": [
    "type",
    "example"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {}
   }
  }
 },
 "additionalProperties": true
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/halowerk-dense-farneback-optical-flow-266bdb18/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from medien.halowerk.com](https://www.zero.xyz/host/medien.halowerk.com/llms.txt)