Skip to content
master
Switch branches/tags
Go to file
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Human Activity Recognition

We tried to implement the following pre-processing techniques to extract person from each frame of video:

  • Interactive Foreground Extraction using GrabCut Algorithm
  • Background Subtraction
  • Mask RCNN

Structure of the project:

  • The datasets are expected to be in the structure as shown.
  • The models will be with their respective names.
projectbu
|
|-- dataset
|   |-- UCF101
|   |-- HMDB51
|
|-- dependencies
|   |-- Mask_RCNN
|
|-- scripts
|
|-- ALSTM
|   |-- autoencoders.py
|   |-- main_ae.py 
  • To extract the frames, run the command below:
bash scripts/frames.sh     # To extract just the frames
bash scripts/framesbr.sh   # To extract frames with Background Reduction

About

Code for our internship at Bennett University on the problem of human activity recognition

Resources

Releases

No releases published

Packages

No packages published

Languages