Data

Tools

Indexes

Applications

Experiments

Open Source Science

voilence-detection-and-highlight-generation-using-bilstm

A Deep Learning model that can detect Violence with high accuracy frame wise and also for the entire video in Video Footages and Live Feeds.

https://github.com/neverthesameagain/voilence-detection-and-highlight-generation-using-bilstm

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (13.8%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

A Deep Learning model that can detect Violence with high accuracy frame wise and also for the entire video in Video Footages and Live Feeds.

Basic Info
  • Host: GitHub
  • Owner: neverthesameagain
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 33.6 MB
Statistics
  • Stars: 3
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 2 years ago · Last pushed almost 2 years ago
Metadata Files
Readme Citation

README.md

Fight Scene Detection for Movie Highlight Generation System

Overview

This repository contains the code and documentation for a Fight Scene Detection (FSD) model used for generating highlights from movies. The system utilizes deep learning techniques, particularly Bidirectional Long Short-Term Memory (BiLSTM) networks, to automatically identify fight scenes in movies and compile them into captivating highlights.

Table of Contents

Introduction

In the era of AI-driven automation, this project addresses the need for efficient and reliable solutions in generating movie highlights, particularly focusing on identifying fight scenes. The system streamlines the process of highlight generation by automating the identification and compilation of fight scenes, reducing manual effort and enhancing the quality and consistency of the generated highlights.

Features

  • Fight Scene Detection (FSD) model based on BiLSTM networks.
  • Automated compilation of fight scenes into movie highlights.
  • User-friendly GUI for uploading videos and generating highlights.
  • Performance metrics evaluation and visualization.
  • Integration with Gradio for hosting the GUI as an API.

Installation

  1. Clone this repository to your local machine:

bash git clone https://github.com/neverthesameagain/Voilence-Detection-and-Highlight-Generation-using-BiLSTM.git

  1. Install the required dependencies:

bash pip install -r requirements.txt

Usage

  1. Navigate to the project directory:

bash cd fight-scene-detection

  1. Run the GUI interface:

bash python gui.py

  1. Upload a video file using the GUI and generate the highlights.

Results

The FSD model achieves an accuracy of 93.5% in identifying fight scenes in movies. Performance metrics such as precision, recall, and F1-score are evaluated and visualized for further analysis. The generated highlights provide users with a concise compilation of fight scenes from the input video.

Contributing

Contributions to this project are welcome! If you have any ideas for improvements or new features, feel free to submit a pull request. Please adhere to the code of conduct and follow the contribution guidelines.

License

This project is licensed under the MIT License.

Additional Resources

The generated model and the essential documents can be accessed here. ```

Owner

  • Name: Aryan Mathur
  • Login: neverthesameagain
  • Kind: user
  • Location: India
  • Company: IIT PALAKKAD

Hey there, I am an excited electron who is engrossed in exploring the infinity. In short words, a Freshman at IIT Palakkad, living the IIT dream and look

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: Violence Detection and Highlight Generation
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Aryan
    family-names: Mathur
    email: aryannmathur@gmail.com
repository-code: >-
  https://github.com/neverthesameagain/Voilence-Detection-and-Highlight-Generation-using-BiLSTM/tree/main
url: >-
  https://github.com/neverthesameagain/Voilence-Detection-and-Highlight-Generation-using-BiLSTM/tree/main

GitHub Events

Total
  • Watch event: 2
Last Year
  • Watch event: 2