Fight Detection in Public Places using AI

Technology stack used

● Python ● Machine Learning ● Deep Learning ● Computer Vision ● Google collab ● Fast Api

Installation

Step 1: Open the official Python website in your web browser. Navigate to the Downloads tab for Windows.
Step 2: Choose the latest Python 3 release. In our example, we choose the latest Python 3.7.3 version.
Step 3: Download the dataset from https://drive.google.com/drive/folders/1BXUmI8AgRXNSVaFKvpkQP7sQbaHWuwHT and copy in /data folder.
Step 4: Load model using

    #Mobnet_LSTM_model = tf.keras.models.load_model(folderlocation+'Mobnet_LSTM_model')
    #Mobnet_LSTM_model_history = np.load(folderlocation+'Mobnet_LSTM_model_history.npy',allow_pickle='TRUE').item()

Flowchart

Bibliography

1. https://docs.opencv.org/3.4/d7/dbd/group__imgproc.html
2. https://docs.python.org/3/tutorial/index.html
3. https://keras.io/api/applications/mobilenet/
4. https://keras.io/api/layers/recurrent_layers/lstm/
5. https://scikit-learn.org/stable/modules/generated/sklearn.met rics.confusion_matrix.html
6. https://keras.io/api/losses/
7. https://www.baeldung.com/cs/training-validation-loss-deep-le arning
8. https://keras.io/api/callbacks/
9. https://stackoverflow.com/

Declaration

We here by declare that the project report entitled “Fight Detection in Public
Places” submitted by us to University Institute of Engineering and
Technology, Panjab University, Chandigarh in partial fulfillment of the
requirement for the award of the degree of B.E. in INFORMATION
TECHNOLOGY is a record of project work carried out by us, under the
guidance of Dr Neelam Goel. We further declare that the work reported in
this project has not been submitted and will not be submitted, either in part
or in full, for the award of any other degree or diploma in this institute or any
other institute or university.
Date: 7 December 2022
Ekaant Garg UE198039
Hitesh Chawla UE198046