Skip to content

Abnormal Event Detection in Videos using SpatioTemporal AutoEncoder

Notifications You must be signed in to change notification settings

Light-City/Abnormal_Event_Detection

 
 

Repository files navigation

Abnormal_Event_Detection

Abnormal Event Detection in Videos using SpatioTemporal AutoEncoder

Code for the paper.

Dependencies:

Install ffmpeg for Video frame extraction.

Library based Dependencies:

numpy

sklearn

keras

tensorflow

h5py

scipy

OpenCV

Instructions

Run processor.py with args the path of Video directory and frame rate.

Run train.py to train the model

Run test.py to test on testing data.

Run start_live_feed.py to test the model on live webcam feed.

You can adjust the threshold parameter in test.py to different values to adjust sensitivity

Datasets Recommended: Avenue Dataset for Anomaly Detection

About

Abnormal Event Detection in Videos using SpatioTemporal AutoEncoder

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%