videoflow’s documentation

_images/videoflow_logo.png

Videoflow is a Python framework for video stream processing. The library is designed to facilitate easy and quick definition of computer vision stream processing pipelines. It empowers developers to build applications and systems with self-contained Deep Learning and Computer Vision capabilities using simple and few lines of code. It contains off-the-shelf reference components for object detection, object tracking, human pose estimation, etc, and it is easily extensible with your own.

Developer friendly

Even complex flow applications can be defined in a simple file with less than 20 lines of code.

Automatic synchronization of resources

You only have to define flow as a computation graph. The framework automatically allocates the resources for the computation and takes care of the synchronization among them.

Easy to extend

It is very easy to create your own components and add them to the flow.

Free and open source

Videoflow is free and open source. It uses the MIT License, which means you can mostly do anything with it.