Filter Urban
1 credit / requestPOST /v1/filter-urbanQuickly separate empty urban or human-modified images from images with an animal, human, or vehicle. Returns bounding boxes and coarse labels only.
Processing images regularly or at large scale?
Use this synchronous endpoint for first tests, debugging, and small workflows. For steady pipelines, larger files, or bursty camera-fleet uploads, approved customers can use Async Image Processing.
Open Async Image ProcessingExamples
Node.js / Express
const form = new FormData()
form.append('image', imageFile)
form.append('threshold', '0.2')
form.append('metadata', 'true')
const response = await fetch('https://api.animaldetect.com/v1/filter-urban', {
method: 'POST',
headers: {
Authorization: 'Bearer ' + process.env.ANIMAL_DETECT_API_KEY,
},
body: form,
})
const data = await response.json()Example Response
{
"id": "753c34fb-9202-4da2-b1d5-3f0c020db674",
"expires_at": "2026-03-12T09:44:20.954Z",
"detections": [
{
"id": 0,
"bbox": [0.22, 0.18, 0.41, 0.53],
"score": 0.96,
"label": "human",
"category": "human"
}
],
"metadata": {
"image_width": 4000,
"image_height": 3000,
"file_size": 2456789
},
"info": {
"processing_time_ms": 388,
"model_version": "mdv5",
"model_id": "mdv5",
"threshold_applied": 0.2
}
}Parameters
Required
file | base64 string
Image data. Upload request body limit is 20MB; raw image budget is 10MB.
Optional
string
Optional geofencing hint (CCA2/CCA3/full country name).
number
Confidence threshold between 0.01 and 0.99. Default: 0.2.
boolean
Set to `true` to include available image metadata in the response.
Request Notes
Send multipart/form-data for files or JSON with a base64 image. Limits: 20MB request body and 10MB raw image.
Status Codes
200Filtering completed.
400Validation error (bad payload, threshold, or image).
401Invalid, missing, or revoked API key.
402Credit limit exceeded.
413Payload too large for the sync upload limit.
429Rate limit exceeded.
503AI processing service temporarily unavailable.
Notes
- Best for: urban, indoor, roadside, zoo, farm, and other human-modified empty-vs-object screening.
- `metadata=true` includes metadata only for fields found in the source image.
- Returns only coarse categories: `animal`, `human`, `vehicle`.