# DISCONTINUATION OF PROJECT #
This project will no longer be maintained by Intel.
Intel has ceased development and contributions including, but not limited to, maintenance, bug fixes, new releases, or updates, to this project.
Intel no longer accepts patches to this project.
# FFmpeg Video Analytics (FFVA) Plugin

## Overview

This repository contains FFmpeg patches that enable CNN model-based video analytics capabilities in the FFmpeg framework. These patches contain filter based implementation include such things as object detection, classification, and recognition. Following is an example that runs detection & emotion classification, using specific models on a video file:
```sh
ffmpeg -i test.mp4 -vf detect=model=face-detection-adas-0001.xml:model_proc=face-detection-adas-0001.json,classify=model=emotions-recognition-retail-0003.xml:model_proc=emotions-recognition-retail-0003.json -an -f null -
```

The solution leverages:
* Open-source FFmpeg framework for pipeline management
* FFmpeg components for input and output, such as media files and real-time streaming from a camera or network
* Video decode and encode plugins, including either CPU-optimized plugins or GPU-accelerated plugins, [based on VAAPI](https://trac.ffmpeg.org/wiki/Hardware/VAAPI)

In addition, the solution installs the following Deep Learning-specific elements, also available in this repository:
* Inference plugins leveraging [OpenVINO<sup>&#8482;</sup> Toolkit](https://software.intel.com/en-us/openvino-toolkit) for high-performance inference using CNN models
* Visualization of computer vision results (such as bounding boxes and labels of detected objects) on top of video stream

## License
The FFmpeg Video Analytics Patches are licensed under the 
GNU Lesser General Public License (LGPL) version 2.1 or later.

## Prerequisites
### Hardware
* OpenVINO<sup>&#8482;</sup> Toolkit has information about the [hardware requirements for inference elements](https://software.intel.com/en-us/openvino-toolkit/hardware)
* On platforms with Intel Gen graphics, see the ffmpeg vaapi wiki for [Hardware Support](https://trac.ffmpeg.org/wiki/Hardware/QuickSync)

### Software
* OpenVINO<sup>&#8482;</sup> Toolkit 2019 R3 (Inference Engine 2.1.0) or above
* Linux* system with kernel 4.15 or above
* FFmpeg framework version [n4.2](https://github.com/FFmpeg/FFmpeg/releases/tag/n4.2)

## Getting Started
* Start here: [Getting Started Guide](https://github.com/VCDP/FFmpeg-patch/wiki/Getting-Started-Guide)
* [API reference](https://www.ffmpeg.org/doxygen/4.1/index.html)
* [OpenVisualCloud/Dockerfiles wiki](https://github.com/OpenVisualCloud/Dockerfiles/wiki)

## Samples
See the [command-line examples](samples/shell)

## Reporting Bugs and Feature Requests
Report bugs and requests [on the issues page](https://github.com/VCDP/FFmpeg-patch/issues)

<!---
## Usage and integration into application
### Pipelining and data flow
[Details](https://github.com/opencv/gst-video-analytics/wiki/Data-flow) about pipeline construction and the data flow between pipeline elements

### Metadata
[Details](https://github.com/opencv/gst-video-analytics/wiki/Metadata) about metadata generated by inference plugins and attached to video frames

### Model preparation
[Details](https://github.com/opencv/gst-video-analytics/wiki/Model-preparation) about how to prepare Tensorflow*, Caffe*, and other models for the inference plugins

### Plugins parameters
[Elements list](https://github.com/opencv/gst-video-analytics/wiki/Elements) and properties list for each element
--->

## How to contribute
Pull requests aren't monitored, so if you have bug fix or an idea to improve this project, post a description on the [issues page](https://github.com/VCDP/FFmpeg-patch/issues)

---
\* Other names and brands may be claimed as the property of others.