Skip to content

Hamza-t/Real-world-Anomaly-Detection-in-Surveillance-Videos-with-CNN-RNN

Repository files navigation

Real world Anomaly Detection in Surveillance Videos with CNN+LSTM : Pytorch

This is the End of 4th year project at INSAT

Goal : Design and development of a crime forecasting system based on the videos of the surveillance cameras.

Datasets

Download following data link and unzip under your $DATA_ROOT_DIR. /workspace/DATA/UCF-Crime/all_rgbs

  • Directory tree
   DATA/
       UCF-Crime/ 
           ../all_rgbs
               ../~.npy
           ../all_flows
               ../~.npy
       train_anomaly.txt
       train_normal.txt
       test_anomaly.txt
       test_normal.txt
       

Architecture :

Prediction model :

image

IOT idea :

image

Results:

image

train-test script

python main.py
python mainlstm.py