GitHub - shsarv/Human-Activity-Detection: This experiment is the classification of human activities using a 2D pose time series dataset and an LSTM RNN. The idea is to prove the concept that using a series of 2D poses, rather than 3D poses or a raw 2D images, can produce an accurate estimation of the behaviour of a person or animal.

shsarv / Human-Activity-Detection Public

Notifications You must be signed in to change notification settings
Fork 0
Star 1

This experiment is the classification of human activities using a 2D pose time series dataset and an LSTM RNN. The idea is to prove the concept that using a series of 2D poses, rather than 3D poses or a raw 2D images, can produce an accurate estimation of the behaviour of a person or animal.

1 star 0 forks Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 4 Commits
images		images
models		models
src		src
templates		templates
Human_Action_Classification_deployment_with_ngrok.ipynb		Human_Action_Classification_deployment_with_ngrok.ipynb
Human_Activity_Recogination.ipynb		Human_Activity_Recogination.ipynb
app.py		app.py
lstm_train.ipynb		lstm_train.ipynb
requirements.txt		requirements.txt
sample_video.mp4		sample_video.mp4