Open Pose Tutorial #3 - Fall Detection with Pose Estimation | OpenCV Python | Computer Vision 2020

Описание

Pose Estimation Tutorial #3 - Fall Detection with Open Pose using OpenCV and Python
►FREE YOLO GIFT - http://augmentedstartups.info/yolofreegiftsp
⭐6-in-1 AI Mega Course with OpenPose - https://augmentedstartups.info/AugmentedAICVPRO

►GitHub Repo - http://augmentedstartups.info/Open-Pose-Github

Hey guys and welcome back. In this lecture I’m going to show you how to perform fall detection using OpenPose. So essentially in fall detection, basic logic is that person’s head goes down and we get drastically change in its head coordinates’ X and Y but mostly in Y axis.
• So, Firstly the difference between previous and present coordinates is should be positive so neither negative nor zero.
• We store these differences as an array or buffer to store previous coordinates and compare it with present coordinates. If it greater than our threshold of 25 then fall has been detection.
• When this happens then, we can print “Fall detected” using OpenCV print function or print it to screen.
With the algorithm in place, lets get started on the implementation.

--------------------------------------------------------------
Geeky Bee AI Pvt Ltd
https://www.geekyb.com/
https://www.linkedin.com/company/geekyb
https://www.facebook.com/geekybeeai/
https://www.youtube.com/channel/UCN-p2eCLNZDgJ-4QXVVLzVg
------------------------------------------------------------

Support Augmented Startups on Patreon
►AugmentedStartups.info/Patreon
Chat to us on Discord
►AugmentedStartups.info/discord
Interact with us on Facebook
►AugmentedStartups.info/Facebook
Check my latest work on Instagram
►AugmentedStartups.info/instagram
Learn Advanced Tutorials on Udemy
►AugmentedStartups.info/udemy
------------------------------------------------------------
To learn more on Artificial Intelligence, Augmented Reality IoT, Deep Learning FPGAs, Arduinos, PCB Design and Image Processing then check out
http://augmentedstartups.info/home

Please Like and Subscribe for more videos :)