---
title: Intel OpenVINO Object Detection (model_api)
emoji: 📚
colorFrom: blue
colorTo: blue
sdk: gradio
sdk_version: 6.1.0
app_file: app.py
pinned: false
short_description: Intel OpenVINO™ object detection demo with Intel model_api.
tags:
- openvino
- intel
- model-api
- object-detection
- computer-vision
- yolo
- gradio
- inference
- edge-ai
models:
- Ultralytics/YOLO11
- mgumowsk/YOLO11

---

# Intel OpenVINO™ Object Detection with Intel® model_api

Fast, practical computer vision inference in the browser using:

- **Intel OpenVINO™ Runtime** for optimized CPU inference
- **Intel® OpenVINO Model API (model_api)** for unified preprocessing/postprocessing and task wrappers
- **Gradio** for a clean interactive UI

This Space supports **image inference** and **video inference** (processed output video), plus a lightweight **performance metrics** readout.

## What you can do

- Upload an image and run object detection
- Upload a video and run frame-by-frame object detection (outputs an annotated video)
- Try curated examples for both images and videos

## Tech stack (keywords)

Intel OpenVINO, Intel model_api, OpenVINO IR (.xml/.bin), YOLO object detection, Gradio demo, computer vision inference, edge AI.

## Links

- Intel® OpenVINO Model API (GitHub): https://github.com/open-edge-platform/model_api
- Model API documentation: https://open-edge-platform.github.io/model_api/latest
- Hugging Face Spaces config reference: https://huggingface.co/docs/hub/spaces-config-reference

## Notes

- Models are loaded from the repository `models/` directory.
- Example media is located in `examples/`.