Giter Club home page Giter Club logo

buildametadataengine-1676393598509-repo's Introduction

BuildaMetadataEngine-1676393598509-repo

Mercor Challenge Repository

Task Overview

Type of Meta data I Used Are

  1. Visual Hotspot/Deadzone Detection
  • Scene Edit Detection - To complete this task i used PySceneDetect Adaptive or content Algorithm by minor changing in the internal structure of the pyscenedetect i did try to use manual diffrent algorithm but they are not accurate so i went with this Pyscenedetect

  • Focus Detection - To complete this task i used Fast Fourier Transform(FFT) Algorthim which use Laplacian method to detect the blue on the thresold of 10 you can change thresold acordingaly

  1. Person Detection(per frame) - To work on this i used Yolov8 Which is faster than any other ai model on the GPU

If i consider only visual hotspot detection or only Focus detection its very fast and work on Real Time Detection but using both the Detection Method Its make it somewhat Slower

Installation requirement - python 3.8.0+

  1. Clone the Repository
git clone <git repo link>
  1. Then install all the dependencies
pip install -r requirements.txt
  1. Then Import Engine class in your Python File as like as app.py file and add list of video path or single path in the engine class and it will generate
from  Engine import Engine


lists=['video.mp4','video2.mp4']

Engine(lists,yolo=True)

You can deselect yolo model as it take gpu to run by make the parameter yolo = False

Engine(lists,yolo=False)

It will generate Json File of Metadata of particual file with the name of the path of the file

buildametadataengine-1676393598509-repo's People

Contributors

manish06097 avatar mercor-project avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.