Skip to content

Latest commit

 

History

History
12 lines (9 loc) · 799 Bytes

README.md

File metadata and controls

12 lines (9 loc) · 799 Bytes

Add video files to the input folder, a video file has been provided for testing.

Run the main extract_features.py file to get features extracted into the output folder.

This is part of an extension of work conducted for Anomaly Detection for video surveillance footage.

UCF Crime Dataset

Use the UCF Crime Dataset from the paper Real-world Anomaly Detection in Surveillance Videos which is available at UCF Crime Dataset to obtain CCTV Surveillance videos.

C3D Model from Facebook

The C3D feature extractor is originally available as a Caffe Model by Facebook.

Credit

This code is based on the work done Ptirupat.