---
title: "Watch a camera still · OpenVibe.Vision"
canonical: "https://openvibe.vision/watch"
updated: null
---

# Watch a camera still · OpenVibe.Vision

HTML: [Watch a camera still · OpenVibe.Vision](https://openvibe.vision/watch)

Watch · local

# Watch a camera still

Drop a still and see what is there: a delivery, a package, a person or a car. Runs on this host, and the picture is not stored.

  Drop a camera still

a photo or screenshot

 What are you watching for? A package A delivery A person A dog A cat A car 

[Read it instead](/read)

 Scene change and weather 

 Previous still (for scene change) Snow Scene change 

A scene change compares this still with the previous one. Snow and delivery use a local scene check.

## What Vision sees appears here

Drop a still from your camera. Vision names the things on your list, with a confidence for each, and says how long it took.

This is object detection, not face recognition. There is no template and no tracking identity.

 Use this from the API

Cam calls `POST /api/v1/watch` with an owner token, an image and up to 20 `classes`; send `previous_image` for a scene change. The API returns detections with class, confidence and box, plus a receipt for the engine, time and cost.