An Openpose based Fall detection system which detects falls in a given input video and takes counter measures, In this case sends an email to the respective person
此專案是針對一連串人體的骨幹座標(frames)變化來偵測人體的目前動作的 CNN，訓練資料來自 SBU_dataset 以及我自行利用拍攝好的照片經過 openpose 得出人體骨幹座標的資料
Client-server model based human fall detection using computer vision (OpenPose)
This repository is a collection of deep learning models created to detect potentially life threatening falls in videos. Models are written in python and utilize tensorflow, pandas and numpy. The most successful model uses the popular 'OpenPose' library to perform feature extraction of humans in videos, and then uses a CNN/LSTM framework to predict is a person is experiencing a potentially fatal fall.
Real-time fall detection using two-stream convolutional neural net (CNN) with Motion History Image (MHI)
Repository containing the material required to reproduce the results of the paper "Vision-Based Fall Detection with Convolutional Neural Networks"
AI Challenger, a platform for open datasets and programming competitions to artificial intelligence (AI) talents around the world.
A tensorflow implementation of Arxiv Paper "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose "(https://arxiv.org/abs/1811.12004)
