https://github.com/harshtikuu/Abnormal_Event_Detection

Abnormal Event Detection in Videos using SpatioTemporal AutoEncoder
https://github.com/harshtikuu/Abnormal_Event_Detection

anomaly-detection convolutional-neural-networks deep-learning keras livestream lstm-neural-networks machine-learning neural-network opencv python tensorflow video-processing

Last synced: about 2 months ago
JSON representation

Abnormal Event Detection in Videos using SpatioTemporal AutoEncoder

• Host: GitHub
• URL: https://github.com/harshtikuu/Abnormal_Event_Detection
• Owner: harshtikuu
• Created: 2017-10-20T21:38:44.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2019-01-28T20:19:23.000Z (over 5 years ago)
• Last Synced: 2024-06-27T04:33:09.586Z (3 months ago)
• Topics: anomaly-detection, convolutional-neural-networks, deep-learning, keras, livestream, lstm-neural-networks, machine-learning, neural-network, opencv, python, tensorflow, video-processing
• Language: Python
• Size: 21.8 MB
• Stars: 173
• Watchers: 13
• Forks: 88
• Open Issues: 31
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Abnormal_Event_Detection

Abnormal Event Detection in Videos using SpatioTemporal AutoEncoder

Code for the [paper](https://arxiv.org/abs/1701.01546).

# 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