# Video Analytics Serving

Video Analytics Serving is an Intel microservice and a set of prebuilt Docker images for deploying optimized video-analytics pipelines. It is open source and self-hosted, installable on Docker Hub.

Canonical page: https://ourlocalhost.com/app/6612/video-analytics-serving

## Description

Video Analytics Serving is an Intel microservice and a set of prebuilt Docker images for deploying optimized video-analytics pipelines. It packages OpenVINO-based pipelines built on GStreamer or FFmpeg and exposes APIs to discover, start, stop, customize, and monitor pipeline execution. It is for developers and homelabbers who want ready-to-run, hardware-accelerated video analysis (object detection, motion, scene analysis) without assembling the GStreamer/FFmpeg toolchain themselves.

## Platform availability

Available on 0 of 10 platforms.

## Health score

2/100 (Low), based on 3 of 4 factors.
- Maintained: 0 (last commit 1891 days ago)
- Popular: 0 (0 GitHub stars)
- Easy to install: 10 (0 install platforms, Docker image)

## Links

- Docker Hub: https://hub.docker.com/r/intel/video-analytics-serving
- GitHub: https://github.com/leopck/video-analytics-serving

## Common questions

### Can I define pipelines without writing low-level GStreamer or FFmpeg code?

Yes. Pipelines use JSON definition files and templates that let developers define and parameterize pipelines while abstracting low-level details.

### Does the microservice expose a REST API for controlling pipelines?

Yes. It provides RESTful endpoints that match the Python module for discovering, starting, stopping, customizing, and monitoring pipelines.

### Is the sample deployment suitable for production as-is?

No. It is provided as a sample and is not intended for production deployment without modification. Developers should review it against their production requirements.

### How is OpenVINO model precision handled?

OpenVINO-based models can be packaged and referenced in pipeline definitions. The model precision can be auto-selected at runtime based on the chosen inference device.

### Do I get container assets for deploying the pipelines?

Yes. It includes scripts and Dockerfiles to build and run container images with the dependencies needed for hardware-optimized media analytics pipelines.

---
Source: Our Local Host (https://ourlocalhost.com/app/6612/video-analytics-serving), the self-hosted and open-source app directory.
