This project consists on showcasing the advantages of the Intel’s OpenVINO toolkit for inference in detecting people falling in an edge application.
This app perform single person fall detection using OpenVINO’s [human-pose-estimation-0001](https://docs.openvinotoolkit.org/latest/_models_intel_human_pose_estimation_0001_description_human_pose_estimation_0001.html).
To detect falls, the app uses the coordinates of the head(nose, eyes and ears), neck and shoulders positions in a frame-by-frame comparison to determine
if the person is falling.
It works with a video file input or webcam stream.
Project URL: https://github.com/computationalcore/fall-detection
